Peer Revenue Returns subject to peer review

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Computer Vision

cs.CV Watch Computer Vision

Sunday 28 December

Computer Vision

Depth Anything in $360^\circ$: Towards Scale Invariance in the Wild

Hualie Jiang, Ziyang Song, Zhiqiang Lou et al. (+2 more)

Panoramic depth estimation captures the complete 360$^\circ$ scene geometry, being essential for robotics and AR/VR applications. While perspective depth models have achieved remarkable zero-shot generalization via large-scale training, panoramic methods lag behind, especially for open-world scenes, due to data scarcity. To bridge this gap, we introduce DA360, a panoramic-adapted version of Depth Anything V2. Our key insight is that the base DAV2 model, trained on perspective images to predict affine-invariant disparity, already exhibits good zero-shot performance on panoramas. Building on this, we design a lightweight adaptation framework that (i) learns a per-image shift from the ViT class token with scale-invariant supervision, transforming affine-invariant disparity into scale-invariant disparity that directly yields well-formed 3D point clouds, and (ii) integrates circular padding into the DPT decoder to eliminate seam artifacts, ensuring spatial coherence. Fine-tuned on a combination of synthetic indoor and outdoor panoramic data, DA360 is evaluated on standard real-world indoor benchmarks and our newly curated outdoor dataset, Metropolis. Results show that DA360 not only outperforms the original DAV2 by over 50% and 12% relative error reduction indoors and outdoors, but also surpasses prior specialized methods like PanDA by about 25–35% across all tests, establishing state-of-the-art zero-shot panoramic depth estimation.
Read the full abstract

All authors Hualie Jiang, Ziyang Song, Zhiqiang Lou, Rui Xu, Minglang Tan

Computer Vision

EgoReAct: Egocentric Video-Driven 3D Human Reaction Generation

Libo Zhang, Zekun Li, Tianyu Li et al. (+10 more)

Humans exhibit adaptive, context-sensitive responses to egocentric visual input. However, faithfully modeling such reactions from egocentric video remains challenging due to the dual requirements of strictly causal generation and precise 3D spatial alignment. To tackle this problem, we first construct the Human Reaction Dataset (HRD) to address data scarcity and misalignment by building a spatially aligned egocentric video-reaction dataset, as existing datasets (e.g., ViMo) suffer from significant spatial inconsistency between the egocentric video and reaction motion, e.g., dynamically moving motions are always paired with fixed-camera videos. Leveraging HRD, we present EgoReAct, the first autoregressive framework that generates 3D-aligned human reaction motions from egocentric video streams in real-time. We first compress the reaction motion into a compact yet expressive latent space via a Vector Quantised-Variational AutoEncoder and then train a Generative Pre-trained Transformer for reaction generation from the visual input. EgoReAct incorporates 3D dynamic features, i.e., metric depth, and head dynamics during the generation, which effectively enhance spatial grounding. Extensive experiments demonstrate that EgoReAct achieves remarkably higher realism, spatial consistency, and generation efficiency compared with prior methods, while maintaining strict causality during generation. We will release code, models, and data upon acceptance.
Read the full abstract

All authors Libo Zhang, Zekun Li, Tianyu Li, Zeyu Cao, Rui Xu, Xiaoxiao Long, Wenjia Wang, Jingbo Wang, Yuan Liu, Wenping Wang, Daquan Zhou, Taku Komura, Zhiyang Dou

Computer Vision · Cross-listed from cs.LG

ReDiF: Resource-Efficient Few-Step Diffusion Distillation via Reinforcement Learning

Amirhossein Tighkhorshid, Zahra Dehghanian and Hamid R. Rabiee

Step distillation accelerates diffusion sampling by training a few-step student to imitate a many-step teacher, but distillation itself remains expensive. Typically, this requires thousands of GPU-hours and a large pre-generated trajectory dataset. We introduce ReDiF, which casts step distillation as terminal-reward policy optimization rather than step-wise regression. The student is optimized against a reward computed on the terminal sample, measuring alignment with the teacher's output, instead of matching the teacher's intermediate trajectory under a reconstruction or consistency loss. Because the reward need not be differentiable or trajectory-aligned, ReDiF admits non-differentiable objectives, multi-objective combinations, and preferences the teacher does not express, while exploration lets the student find sampling paths matched to its own step schedule. ReDiF converges in 400 policy updates with 3200 rollouts on a single A100 GPU with 1,000 noise-class pairs and no paired dataset: about 4 GPU-hours, against roughly 336 A100-hours reported for DMD2 on the same EDM teacher. At 8 steps on ImageNet-64, it achieves an FID 3.64 points better than the strongest retrained distillation baseline in the low-training regime under the same single-GPU budget. The formulation is also orthogonal to existing distillation objectives: added to the DMD2 loss, it further improves DMD2's FID by 4.4.
Read the full abstract

Computer Vision

Evaluating the Performance of Open-Vocabulary Object Detection in Low-quality Image

Po-Chih Wu

Open-vocabulary object detection enables models to localize and recognize objects beyond a predefined set of categories and is expected to achieve recognition capabilities comparable to human performance. In this study, we aim to evaluate the performance of existing models on open-vocabulary object detection tasks under low-quality image conditions. For this purpose, we introduce a new dataset that simulates low-quality images in the real world. In our evaluation experiment, we find that although open-vocabulary object detection models exhibited no significant decrease in mAP scores under low-level image degradation, the performance of all models dropped sharply under high-level image degradation. OWLv2 models consistently performed better across different types of degradation, while OWL-ViT, GroundingDINO, and Detic showed significant performance declines. We will release our dataset and codes to facilitate future studies.
Read the full abstract

Computer Vision

Medical Scene Reconstruction and Segmentation based on 3D Gaussian Representation

Bin Liu, Wenyan Tian, Huangxin Fu et al. (+3 more)

3D reconstruction of medical images is a key technology in medical image analysis and clinical diagnosis, providing structural visualization support for disease assessment and surgical planning. Traditional methods are computationally expensive and prone to structural discontinuities and loss of detail in sparse slices, making it difficult to meet clinical accuracy requirements.To address these challenges, we propose an efficient 3D reconstruction method based on 3D Gaussian and tri-plane representations. This method not only maintains the advantages of Gaussian representation in efficient rendering and geometric representation but also significantly enhances structural continuity and semantic consistency under sparse slicing conditions. Experimental results on multimodal medical datasets such as US and MRI show that our proposed method can generate high-quality, anatomically coherent, and semantically stable medical images under sparse data conditions, while significantly improving reconstruction efficiency. This provides an efficient and reliable new approach for 3D visualization and clinical analysis of medical images.
Read the full abstract

All authors Bin Liu, Wenyan Tian, Huangxin Fu, Zizheng Li, Zhifen He, Bo Li

Computer Vision

VPTracker: Global Vision-Language Tracking via Visual Prompt

Jingchao Wang, Kaiwen Zhou, Zhijian Wu et al. (+3 more)

Vision-Language Tracking aims to continuously localize objects described by a visual template and a language description. Existing methods, however, are typically limited to local search, making them prone to failures under viewpoint changes, occlusions, and rapid target movements. In this work, we introduce the first global tracking framework based on Multimodal Large Language Models (VPTracker), exploiting their powerful semantic reasoning to locate targets across the entire image space. While global search improves robustness and reduces drift, it also introduces distractions from visually or semantically similar objects. To address this, we propose a location-aware visual prompting mechanism that incorporates spatial priors into the MLLM. Specifically, we construct a region-level prompt based on the target's previous location, enabling the model to prioritize region-level recognition and resort to global inference only when necessary. This design retains the advantages of global tracking while effectively suppressing interference from distracting visual content. Extensive experiments show that our approach significantly enhances tracking stability and target disambiguation under challenging scenarios, opening a new avenue for integrating MLLMs into visual tracking. Code is available at https://github.com/jcwang0602/VPTracker.
Read the full abstract

All authors Jingchao Wang, Kaiwen Zhou, Zhijian Wu, Kunhua Ji, Dingjiang Huang, Yefeng Zheng

Computer Vision

Parallel Diffusion Solver via Residual Dirichlet Policy Optimization

Ruoyu Wang, Ziyu Li, Beier Zhu et al. (+5 more)

Diffusion models (DMs) have achieved state-of-the-art generative performance but suffer from high sampling latency due to their sequential denoising nature. Existing solver-based acceleration methods often face significant image quality degradation under a low-latency budget, primarily due to accumulated truncation errors arising from the inability to capture high-curvature trajectory segments. In this paper, we propose the Ensemble Parallel Direction solver (dubbed as EPD-Solver), a novel ODE solver that mitigates these errors by incorporating multiple parallel gradient evaluations in each step. Motivated by the geometric insight that sampling trajectories are largely confined to a low-dimensional manifold, EPD-Solver leverages the Mean Value Theorem for vector-valued functions to approximate the integral solution more accurately. Importantly, since the additional gradient computations are independent, they can be fully parallelized, preserving low-latency sampling nature. We introduce a two-stage optimization framework. Initially, EPD-Solver optimizes a small set of learnable parameters via a distillation-based approach. We further propose a parameter-efficient Reinforcement Learning (RL) fine-tuning scheme that reformulates the solver as a stochastic Dirichlet policy. Unlike traditional methods that fine-tune the massive backbone, our RL approach operates strictly within the low-dimensional solver space, effectively mitigating reward hacking while enhancing performance in complex text-to-image (T2I) generation tasks. In addition, our method is flexible and can serve as a plugin (EPD-Plugin) to improve existing ODE samplers.
Read the full abstract

All authors Ruoyu Wang, Ziyu Li, Beier Zhu, Liangyu Yuan, Hanwang Zhang, Xun Yang, Xiaojun Chang, Chi Zhang

Computer Vision

Plug In, Grade Right: Psychology-Inspired AGIQA

Zhicheng Liao, Baoliang Chen, Hanwei Zhu et al. (+3 more)

Existing AGIQA models typically estimate image quality by measuring and aggregating the similarities between image embeddings and text embeddings derived from multi-grade quality descriptions. Although effective, we observe that such similarity distributions across grades usually exhibit multimodal patterns. For instance, an image embedding may show high similarity to both "excellent" and "poor" grade descriptions while deviating from the "good" one. We refer to this phenomenon as "semantic drift", where semantic inconsistencies between text embeddings and their intended descriptions undermine the reliability of text-image shared-space learning. To mitigate this issue, we draw inspiration from psychometrics and propose an improved Graded Response Model (GRM) for AGIQA. The GRM is a classical assessment model that categorizes a subject's ability across grades using test items with various difficulty levels. This paradigm aligns remarkably well with human quality rating, where image quality can be interpreted as an image's ability to meet various quality grades. Building on this philosophy, we design a two-branch quality grading module: one branch estimates image ability while the other constructs multiple difficulty levels. To ensure monotonicity in difficulty levels, we further model difficulty generation in an arithmetic manner, which inherently enforces a unimodal and interpretable quality distribution. Our Arithmetic GRM based Quality Grading (AGQG) module enjoys a plug-and-play advantage, consistently improving performance when integrated into various state-of-the-art AGIQA frameworks. Moreover, it also generalizes effectively to both natural and screen content image quality assessment, revealing its potential as a key component in future IQA models.
Read the full abstract

All authors Zhicheng Liao, Baoliang Chen, Hanwei Zhu, Lingyu Zhu, Shiqi Wang, Weisi Lin

Computer Vision · Cross-listed from cs.LG

Schrodinger AI: A Unified Spectral-Dynamical Framework for Classification, Reasoning, and Operator-Based Generalization

Truong Son Nguyen

We introduce Schrödinger AI, a unified machine learning framework inspired by quantum mechanics. The system is defined by three tightly coupled components: (1) a {time-independent wave-energy solver} that treats perception and classification as spectral decomposition under a learned Hamiltonian; (2) a {time-dependent dynamical solver} governing the evolution of semantic wavefunctions over time, enabling context-aware decision revision, re-routing, and reasoning under environmental changes; and (3) a {low-rank operator calculus} that learns symbolic transformations such as modular arithmetic through learned quantum-like transition operators. Together, these components form a coherent physics-driven alternative to conventional cross-entropy training and transformer attention, providing robust generalization, interpretable semantics, and emergent topology. Empirically, Schrödinger AI demonstrates: (a) emergent semantic manifolds that reflect human-conceived class relations without explicit supervision; (b) dynamic reasoning that adapts to changing environments, including maze navigation with real-time potential-field perturbations; and (c) exact operator generalization on modular arithmetic tasks, where the system learns group actions and composes them across sequences far beyond training length. These results suggest a new foundational direction for machine learning, where learning is cast as discovering and navigating an underlying semantic energy landscape.
Read the full abstract

Computer Vision

Next Best View Selections for Semantic and Dynamic 3D Gaussian Splatting

Yiqian Li, Wen Jiang and Kostas Daniilidis

Understanding semantics and dynamics has been crucial for embodied agents in various tasks. Both tasks have much more data redundancy than the static scene understanding task. We formulate the view selection problem as an active learning problem, where the goal is to prioritize frames that provide the greatest information gain for model training. To this end, we propose an active learning algorithm with Fisher Information that quantifies the informativeness of candidate views with respect to both semantic Gaussian parameters and deformation networks. This formulation allows our method to jointly handle semantic reasoning and dynamic scene modeling, providing a principled alternative to heuristic or random strategies. We evaluate our method on large-scale static images and dynamic video datasets by selecting informative frames from multi-camera setups. Experimental results demonstrate that our approach consistently improves rendering quality and semantic segmentation performance, outperforming baseline methods based on random selection and uncertainty-based heuristics.
Read the full abstract

Computer Vision · Cross-listed from eess.IV

SwinCCIR: An end-to-end deep network for Compton camera imaging reconstruction

Minghao Dong, Xinyang Luo, Xujian Ouyang et al. (+1 more)

Compton cameras (CCs) are a kind of gamma cameras which are designed to determine the directions of incident gammas based on the Compton scatter. However, the reconstruction of CCs face problems of severe artifacts and deformation due to the fundamental reconstruction principle of back-projection of Compton cones. Besides, a part of systematic errors originated from the performance of devices are hard to remove through calibration, leading to deterioration of imaging quality. Iterative algorithms and deep-learning based methods have been widely used to improve reconstruction. But most of them are optimization based on the results of back-projection. Therefore, we proposed an end-to-end deep learning framework, SwinCCIR, for CC imaging. Through adopting swin-transformer blocks and a transposed convolution-based image generation module, we established the relationship between the list-mode events and the radioactive source distribution. SwinCCIR was trained and validated on both simulated and practical dataset. The experimental results indicate that SwinCCIR effectively overcomes problems of conventional CC imaging, which are expected to be implemented in practical applications.
Read the full abstract

All authors Minghao Dong, Xinyang Luo, Xujian Ouyang, Yongshun Xiao

Computer Vision

Neighbor-Aware Token Reduction via Hilbert Curve for Vision Transformers

Yunge Li and Lanyu Xu

Vision Transformers (ViTs) have achieved remarkable success in visual recognition tasks, but redundant token representations limit their computational efficiency. Existing token merging and pruning strategies often overlook spatial continuity and neighbor relationships, resulting in the loss of local context. This paper proposes novel neighbor-aware token reduction methods based on Hilbert curve reordering, which explicitly preserves the neighbor structure in a 2D space using 1D sequential representations. Our method introduces two key strategies: Neighbor-Aware Pruning (NAP) for selective token retention and Merging by Adjacent Token similarity (MAT) for local token aggregation. Experiments demonstrate that our approach achieves state-of-the-art accuracy-efficiency trade-offs compared to existing methods. This work highlights the importance of spatial continuity and neighbor structure, offering new insights for the architectural optimization of ViTs.
Read the full abstract

Computer Vision

TrimTokenator-LC: Towards Adaptive Visual Token Pruning for Large Multimodal Models with Long Contexts

Hao Zhang, Mengsi Lyu, Bo Huang et al. (+2 more)

Large Multimodal Models (LMMs) have proven effective on various tasks. They typically encode visual inputs into Original Model sequences of tokens, which are then concatenated with textual tokens and jointly processed by the language model. However, the growing number of visual tokens greatly increases inference cost. Visual token pruning has emerged as a promising solution. However, existing methods often overlook scenarios involving long context inputs with multiple images. In this paper, we analyze the challenges of visual token pruning in long context, multi-image settings and introduce an adaptive pruning method tailored for such scenarios. We decompose redundancy into intra-image and inter-image components and quantify them through intra-image diversity and inter-image variation, which jointly guide dynamic budget allocation. Our approach consists of two stages. The intra-image stage allocates each image a content-aware token budget and greedily selects its most representative tokens. The inter-image stage performs global diversity filtering to form a candidate pool and then applies a Pareto selection procedure that balances diversity with text alignment. Extensive experiments show that our approach can reduce up to 80% of visual tokens while maintaining performance in long context settings.
Read the full abstract

All authors Hao Zhang, Mengsi Lyu, Bo Huang, Yulong Ao, Yonghua Lin

Computer Vision

Split4D: Decomposed 4D Scene Reconstruction Without Video Segmentation

Yongzhen Hu, Yihui Yang, Haotong Lin et al. (+8 more)

This paper addresses the problem of decomposed 4D scene reconstruction from multi-view videos. Recent methods achieve this by lifting video segmentation results to a 4D representation through differentiable rendering techniques. Therefore, they heavily rely on the quality of video segmentation maps, which are often unstable, leading to unreliable reconstruction results. To overcome this challenge, our key idea is to represent the decomposed 4D scene with the Freetime FeatureGS and design a streaming feature learning strategy to accurately recover it from per-image segmentation maps, eliminating the need for video segmentation. Freetime FeatureGS models the dynamic scene as a set of Gaussian primitives with learnable features and linear motion ability, allowing them to move to neighboring regions over time. We apply a contrastive loss to Freetime FeatureGS, forcing primitive features to be close or far apart based on whether their projections belong to the same instance in the 2D segmentation map. As our Gaussian primitives can move across time, it naturally extends the feature learning to the temporal dimension, achieving 4D segmentation. Furthermore, we sample observations for training in a temporally ordered manner, enabling the streaming propagation of features over time and effectively avoiding local minima during the optimization process. Experimental results on several datasets show that the reconstruction quality of our method outperforms recent methods by a large margin.
Read the full abstract

All authors Yongzhen Hu, Yihui Yang, Haotong Lin, Yifan Wang, Junting Dong, Yifu Deng, Xinyu Zhu, Fan Jia, Hujun Bao, Xiaowei Zhou, Sida Peng

Computer Vision

Improved cystic hygroma detection from prenatal imaging using ultrasound-specific self-supervised representation learning

Youssef Megahed, Robin Ducharme, Inok Lee et al. (+4 more)

Cystic hygroma is a high-risk prenatal ultrasound finding that portends high rates of chromosomal abnormalities, structural malformations, and adverse pregnancy outcomes. Automated detection can increase reproducibility and support scalable early screening programs, but supervised deep learning methods are limited by small labelled datasets. This study assesses whether ultrasound-specific self-supervised pretraining can facilitate accurate, robust deep learning detection of cystic hygroma in first-trimester ultrasound images. We fine-tuned the Ultrasound Self-Supervised Foundation Model with Masked Autoencoding (USF-MAE), pretrained on over 370,000 unlabelled ultrasound images, for binary classification of normal controls and cystic hygroma cases used in this study. Performance was evaluated on the same curated ultrasound dataset, preprocessing pipeline, and 4-fold cross-validation protocol as for the DenseNet-169 baseline, using accuracy, sensitivity, specificity, and the area under the receiver operating characteristic curve (ROC-AUC). Model interpretability was analyzed qualitatively using Score-CAM visualizations. USF-MAE outperformed the DenseNet-169 baseline on all evaluation metrics. The proposed model yielded a mean accuracy of 0.96, sensitivity of 0.94, specificity of 0.98, and ROC-AUC of 0.98 compared to 0.93, 0.92, 0.94, and 0.94 for the DenseNet-169 baseline, respectively. Qualitative Score-CAM visualizations of model predictions demonstrated clinical relevance by highlighting expected regions in the fetal neck for both positive and negative cases. Paired statistical analysis using a Wilcoxon signed-rank test confirmed that performance improvements achieved by USF-MAE were statistically significant (p = 0.0057).
Read the full abstract

All authors Youssef Megahed, Robin Ducharme, Inok Lee, Inbal Willner, Adrian D. C. Chan, Mark Walker, Steven Hawken

Saturday 27 December

Computer Vision · Cross-listed from cs.DL

A Global Atlas of Digital Dermatology to Map Innovation and Disparities

Fabian Gröger, Simone Lionetti, Philippe Gottfrois et al. (+7 more)

The adoption of artificial intelligence in dermatology promises democratized access to healthcare, but model reliability depends on the quality and comprehensiveness of the data fueling these models. Despite rapid growth in publicly available dermatology images, the field lacks quantitative key performance indicators to measure whether new datasets expand clinical coverage or merely replicate what is already known. Here we present SkinMap, a multi-modal framework for the first comprehensive audit of the field's entire data basis. We unify the publicly available dermatology datasets into a single, queryable semantic atlas comprising more than 1.1 million images of skin conditions and quantify (i) informational novelty over time, (ii) dataset redundancy, and (iii) representation gaps across demographics and diagnoses. Despite exponential growth in dataset sizes, informational novelty across time has somewhat plateaued: Some clusters, such as common neoplasms on fair skin, are densely populated, while underrepresented skin types and many rare diseases remain unaddressed. We further identify structural gaps in coverage: Darker skin tones (Fitzpatrick V-VI) constitute only 5.8% of images and pediatric patients only 3.0%, while many rare diseases and phenotype combinations remain sparsely represented. SkinMap provides infrastructure to measure blind spots and steer strategic data acquisition toward undercovered regions of clinical space.
Read the full abstract

All authors Fabian Gröger, Simone Lionetti, Philippe Gottfrois, Alvaro Gonzalez-Jimenez, Lea Habermacher, Labelling Consortium, Ludovic Amruthalingam, Matthew Groh, Marc Pouly, Alexander A. Navarini

Computer Vision

Unified Review and Benchmark of Deep Segmentation Architectures for Cardiac Ultrasound on CAMUS

Zahid Ullah, Muhammad Hilal, Eunsoo Lee et al. (+2 more)

Several review papers summarize cardiac imaging and DL advances, few works connect this overview to a unified and reproducible experimental benchmark. In this study, we combine a focused review of cardiac ultrasound segmentation literature with a controlled comparison of three influential architectures, U-Net, Attention U-Net, and TransUNet, on the Cardiac Acquisitions for Multi-Structure Ultrasound Segmentation (CAMUS) echocardiography dataset. Our benchmark spans multiple preprocessing routes, including native NIfTI volumes, 16-bit PNG exports, GPT-assisted polygon-based pseudo-labels, and self-supervised pretraining (SSL) on thousands of unlabeled cine frames. Using identical training splits, losses, and evaluation criteria, a plain U-Net achieved a 94% mean Dice when trained directly on NIfTI data (preserving native dynamic range), while the PNG-16-bit workflow reached 91% under similar conditions. Attention U-Net provided modest improvements on small or low-contrast regions, reducing boundary leakage, whereas TransUNet demonstrated the strongest generalization on challenging frames due to its ability to model global spatial context, particularly when initialized with SSL. Pseudo-labeling expanded the training set and improved robustness after confidence filtering. Overall, our contributions are threefold: a harmonized, apples-to-apples benchmark of U-Net, Attention U-Net, and TransUNet under standardized CAMUS preprocessing and evaluation; practical guidance on maintaining intensity fidelity, resolution consistency, and alignment when preparing ultrasound data; and an outlook on scalable self-supervision and emerging multimodal GPT-based annotation pipelines for rapid labeling, quality assurance, and targeted dataset curation.
Read the full abstract

All authors Zahid Ullah, Muhammad Hilal, Eunsoo Lee, Dragan Pamucar, Jihie Kim

Computer Vision · Cross-listed from eess.IV

Leveraging Machine Learning for Early Detection of Lung Diseases

Bahareh Rahmani, Harsha Reddy Bindela, Rama Kanth Reddy Gosula et al. (+6 more)

A combination of traditional image processing methods with advanced neural networks concretes a predictive and preventive healthcare paradigm. This study offers rapid, accurate, and non-invasive diagnostic solutions that can significantly impact patient outcomes, particularly in areas with limited access to radiologists and healthcare resources. In this project, deep learning methods apply in enhancing the diagnosis of respiratory diseases such as COVID-19, lung cancer, and pneumonia from chest x-rays. We trained and validated various neural network models, including CNNs, VGG16, InceptionV3, and EfficientNetB0, with high accuracy, precision, recall, and F1 scores to highlight the models' reliability and potential in real-world diagnostic applications.
Read the full abstract

All authors Bahareh Rahmani, Harsha Reddy Bindela, Rama Kanth Reddy Gosula, Krishna Yedubati, Mohammad Amir Salari, Leslie Hinyard, Payam Norouzzadeh, Eli Snir, Martin Schoen

Computer Vision · Cross-listed from cs.AI

Memento 2: Learning by Stateful Reflective Memory

Jun Wang

We present a theoretical study of continual and experiential learning in large language model agents that combine episodic memory with reinforcement learning. We argue that the key mechanism for continual adaptation, without updating model parameters, is reflection: the agent's ability to use past experience to guide future actions. Empirical findings suggest that episodic, experience-driven reflection enables generalised adaptation across a wide range of open-ended, long-horizon tasks. This indicates that efficient learning can occur during deployment and weakens the traditional separation between training and testing. Motivated by this, we introduce the Stateful Reflective Decision Process, a formal model of reflective memory dynamics. In this abstraction, an agent maintains an episodic memory and performs two core operations. Writing stores interaction outcomes and plays the role of policy evaluation. Reading retrieves relevant past cases to inform decisions and plays the role of policy improvement. This perspective treats reflective memory as a control object that can be analysed using classical reinforcement learning tools. We then develop a read-write reflective learning framework by integrating retrieval into soft policy iteration and establish convergence guarantees. We show that as memory grows and provides denser coverage of the state space, the resulting composite policy converges to the optimal solution. Overall, this framework connects practical memory-based methods with principled reinforcement learning, providing a rigorous mathematical basis for building reflective, memory-embedded agents capable of continual general-purpose learning.
Read the full abstract

Computer Vision

SCPainter: A Unified Framework for Realistic 3D Asset Insertion and Novel View Synthesis

Paul Dobre, Jackson Cooper, Xin Wang et al. (+1 more)

3D Asset insertion and novel view synthesis (NVS) are key components for autonomous driving simulation, enhancing the diversity of training data. With better training data that is diverse and covers a wide range of situations, including long-tailed driving scenarios, autonomous driving models can become more robust and safer. This motivates a unified simulation framework that can jointly handle realistic integration of inserted 3D assets and NVS. Recent 3D asset reconstruction methods enable reconstruction of dynamic actors from video, supporting their re-insertion into simulated driving scenes. While the overall structure and appearance can be accurate, it still struggles to capture the realism of 3D assets through lighting or shadows, particularly when inserted into scenes. In parallel, recent advances in NVS methods have demonstrated promising results in synthesizing viewpoints beyond the originally recorded trajectories. However, existing approaches largely treat asset insertion and NVS capabilities in isolation. To allow for interaction with the rest of the scene and to enable more diverse creation of new scenarios for training, realistic 3D asset insertion should be combined with NVS. To address this, we present SCPainter (Street Car Painter), a unified framework which integrates 3D Gaussian Splat (GS) car asset representations and 3D scene point clouds with diffusion-based generation to jointly enable realistic 3D asset insertion and NVS. The 3D GS assets and 3D scene point clouds are projected together into novel views, and these projections are used to condition a diffusion model to generate high quality images. Evaluation on the Waymo Open Dataset demonstrate the capability of our framework to enable 3D asset insertion and NVS, facilitating the creation of diverse and realistic driving data.
Read the full abstract

All authors Paul Dobre, Jackson Cooper, Xin Wang, Hongzhou Yang

Computer Vision · Cross-listed from cs.MM

Mesquite MoCap: Democratizing Real-Time Motion Capture with Affordable, Bodyworn IoT Sensors and WebXR SLAM

Poojan Vanani, Darsh Patel, Danyal Khorami et al. (+8 more)

Motion capture remains costly and complex to deploy, limiting use outside specialized laboratories. We present Mesquite, an open-source, low-cost inertial motion-capture system that combines a body-worn network of 15 IMU sensor nodes with a hip-worn Android smartphone for position tracking. A low-power wireless link streams quaternion orientations to a central USB dongle and a browser-based application for real-time visualization and recording. Built on modern web technologies – WebGL for rendering, WebXR for SLAM, WebSerial and WebSockets for device and network I/O, and Progressive Web Apps for packaging – the system runs cross-platform entirely in the browser. In benchmarks against a commercial optical system, Mesquite achieves mean joint-angle error of 2-5 degrees while operating at approximately 5% of the cost. The system sustains 30 frames per second with end-to-end latency under 15ms and a packet delivery rate of at least 99.7% in standard indoor environments. By leveraging IoT principles, edge processing, and a web-native stack, Mesquite lowers the barrier to motion capture for applications in entertainment, biomechanics, healthcare monitoring, human-computer interaction, and virtual reality. We release hardware designs, firmware, and software under an open-source license (GNU GPL).
Read the full abstract

All authors Poojan Vanani, Darsh Patel, Danyal Khorami, Siva Munaganuru, Pavan Reddy, Varun Reddy, Bhargav Raghunath, Ishrat Lallmamode, Romir Patel, Assegid Kidané, Tejaswi Gowda

Computer Vision

Multimodal Diffeomorphic Registration with Neural ODEs and Structural Descriptors

Salvador Rodriguez-Sanz and Monica Hernandez

This work proposes a multimodal diffeomorphic registration method using Neural Ordinary Differential Equations (Neural ODEs). Nonrigid registration algorithms exhibit tradeoffs between their accuracy, the computational complexity of their deformation model, and its proper regularization. In addition, they also assume intensity correlation in anatomically homologous regions of interest among image pairs, limiting their applicability to the monomodal setting. Unlike learning-based models, we propose an instance-specific framework that is not subject to high scan requirements for training and does not suffer performance degradation at inference time on modalities unseen during training. Our method exploits the potential of continuous-depth networks in the Neural ODE paradigm with structural descriptors, widely adopted as modality-agnostic metric models which exploit self-similarities on parameterized neighborhood geometries. We propose three different variants that integrate image-based or feature-based structural descriptors and nonstructural image similarities computed by local mutual information. We conduct extensive evaluations on different experiments formed by scan dataset combinations and show surpassing qualitative and quantitative results compared to state-of-the-art baselines adequate for large or small deformations, and specific of multimodal registration. Lastly, we also demonstrate the underlying robustness of the proposed framework to varying levels of explicit regularization while maintaining low error, its suitability for registration at varying scales, and its efficiency with respect to other methods targeted to large-deformation registration.
Read the full abstract

Computer Vision

Autoregressive Flow Matching for Motion Prediction

Johnathan Xie, Stefan Stojanov, Cristobal Eyzaguirre et al. (+2 more)

Motion prediction has been studied in different contexts with models trained on narrow distributions and applied to downstream tasks in human motion prediction and robotics. Simultaneously, recent efforts in scaling video prediction have demonstrated impressive visual realism, yet they struggle to accurately model complex motions despite massive scale. Inspired by the scaling of video generation, we develop autoregressive flow matching (ARFM), a new method for probabilistic modeling of sequential continuous data and train it on diverse video datasets to generate future point track locations over long horizons. To evaluate our model, we develop benchmarks for evaluating the ability of motion prediction models to predict human and robot motion. Our model is able to predict complex motions, and we demonstrate that conditioning robot action prediction and human motion prediction on predicted future tracks can significantly improve downstream task performance. Code and models publicly available at: https://github.com/Johnathan-Xie/arfm-motion-prediction.
Read the full abstract

All authors Johnathan Xie, Stefan Stojanov, Cristobal Eyzaguirre, Daniel L. K. Yamins, Jiajun Wu

Computer Vision

CritiFusion: Semantic Critique and Spectral Alignment for Faithful Text-to-Image Generation

ZhenQi Chen, TsaiChing Ni and YuanFu Yang

Recent text-to-image diffusion models have achieved remarkable visual fidelity but often struggle with semantic alignment to complex prompts. We introduce CritiFusion, a novel inference-time framework that integrates a multimodal semantic critique mechanism with frequency-domain refinement to improve text-to-image consistency and detail. The proposed CritiCore module leverages a vision-language model and multiple large language models to enrich the prompt context and produce high-level semantic feedback, guiding the diffusion process to better align generated content with the prompt's intent. Additionally, SpecFusion merges intermediate generation states in the spectral domain, injecting coarse structural information while preserving high-frequency details. No additional model training is required. CritiFusion serves as a plug-in refinement stage compatible with existing diffusion backbones. Experiments on standard benchmarks show that our method notably improves human-aligned metrics of text-to-image correspondence and visual quality. CritiFusion consistently boosts performance on human preference scores and aesthetic evaluations, achieving results on par with state-of-the-art reward optimization approaches. Qualitative results further demonstrate superior detail, realism, and prompt fidelity, indicating the effectiveness of our semantic critique and spectral alignment strategy.
Read the full abstract

Computer Vision · Cross-listed from eess.IV

Semantic contrastive learning for orthogonal X-ray computed tomography reconstruction

Jiashu Dong, Jiabing Xiang, Lisheng Geng et al. (+2 more)

X-ray computed tomography (CT) is widely used in medical imaging, with sparse-view reconstruction offering an effective way to reduce radiation dose. However, ill-posed conditions often result in severe streak artifacts. Recent advances in deep learning-based methods have improved reconstruction quality, but challenges still remain. To address these challenges, we propose a novel semantic feature contrastive learning loss function that evaluates semantic similarity in high-level latent spaces and anatomical similarity in shallow latent spaces. Our approach utilizes a three-stage U-Net-based architecture: one for coarse reconstruction, one for detail refinement, and one for semantic similarity measurement. Tests on a chest dataset with orthogonal projections demonstrate that our method achieves superior reconstruction quality and faster processing compared to other algorithms. The results show significant improvements in image quality while maintaining low computational complexity, making it a practical solution for orthogonal CT reconstruction.
Read the full abstract

All authors Jiashu Dong, Jiabing Xiang, Lisheng Geng, Suqing Tian, Wei Zhao

Computer Vision

INTERACT-CMIL: Multi-Task Shared Learning and Inter-Task Consistency for Conjunctival Melanocytic Intraepithelial Lesion Grading

Mert Ikinci, Luna Toma, Karin U. Loeffler et al. (+6 more)

Accurate grading of Conjunctival Melanocytic Intraepithelial Lesions (CMIL) is essential for treatment and melanoma prediction but remains difficult due to subtle morphological cues and interrelated diagnostic criteria. We introduce INTERACT-CMIL, a multi-head deep learning framework that jointly predicts five histopathological axes; WHO4, WHO5, horizontal spread, vertical spread, and cytologic atypia, through Shared Feature Learning with Combinatorial Partial Supervision and an Inter-Dependence Loss enforcing cross-task consistency. Trained and evaluated on a newly curated, multi-center dataset of 486 expert-annotated conjunctival biopsy patches from three university hospitals, INTERACT-CMIL achieves consistent improvements over CNN and foundation-model (FM) baselines, with relative macro F1 gains up to 55.1% (WHO4) and 25.0% (vertical spread). The framework provides coherent, interpretable multi-criteria predictions aligned with expert grading, offering a reproducible computational benchmark for CMIL diagnosis and a step toward standardized digital ocular pathology.
Read the full abstract

All authors Mert Ikinci, Luna Toma, Karin U. Loeffler, Leticia Ussem, Daniela Süsskind, Julia M. Weller, Yousef Yeganeh, Martina C. Herwig-Carl, Shadi Albarqouni

Computer Vision

Unleashing Foundation Vision Models: Adaptive Transfer for Diverse Data-Limited Scientific Domains

Qiankun Li, Feng He, Huabao Chen et al. (+3 more)

In the big data era, the computer vision field benefits from large-scale datasets such as LAION-2B, LAION-400M, and ImageNet-21K, Kinetics, on which popular models like the ViT and ConvNeXt series have been pre-trained, acquiring substantial knowledge. However, numerous downstream tasks in specialized and data-limited scientific domains continue to pose significant challenges. In this paper, we propose a novel Cluster Attention Adapter (CLAdapter), which refines and adapts the rich representations learned from large-scale data to various data-limited downstream tasks. Specifically, CLAdapter introduces attention mechanisms and cluster centers to personalize the enhancement of transformed features through distribution correlation and transformation matrices. This enables models fine-tuned with CLAdapter to learn distinct representations tailored to different feature sets, facilitating the models' adaptation from rich pre-trained features to various downstream scenarios effectively. In addition, CLAdapter's unified interface design allows for seamless integration with multiple model architectures, including CNNs and Transformers, in both 2D and 3D contexts. Through extensive experiments on 10 datasets spanning domains such as generic, multimedia, biological, medical, industrial, agricultural, environmental, geographical, materials science, out-of-distribution (OOD), and 3D analysis, CLAdapter achieves state-of-the-art performance across diverse data-limited scientific domains, demonstrating its effectiveness in unleashing the potential of foundation vision models via adaptive transfer. Code is available at https://github.com/qklee-lz/CLAdapter.
Read the full abstract

All authors Qiankun Li, Feng He, Huabao Chen, Xin Ning, Kun Wang, Zengfu Wang

Computer Vision

Investigating Deep Learning Models for Ejection Fraction Estimation from Echocardiography Videos

Shravan Saranyan and Pramit Saha

Left ventricular ejection fraction (LVEF) is a key indicator of cardiac function and plays a central role in the diagnosis and management of cardiovascular disease. Echocardiography, as a readily accessible and non-invasive imaging modality, is widely used in clinical practice to estimate LVEF. However, manual assessment of cardiac function from echocardiograms is time-consuming and subject to considerable inter-observer variability. Deep learning approaches offer a promising alternative, with the potential to achieve performance comparable to that of experienced human experts. In this study, we investigate the effectiveness of several deep learning architectures for LVEF estimation from echocardiography videos, including 3D Inception, two-stream, and CNN-RNN models. We systematically evaluate architectural modifications and fusion strategies to identify configurations that maximize prediction accuracy. Models were trained and evaluated on the EchoNet-Dynamic dataset, comprising 10,030 echocardiogram videos. Our results demonstrate that modified 3D Inception architectures achieve the best overall performance, with a root mean squared error (RMSE) of 6.79%. Across architectures, we observe a tendency toward overfitting, with smaller and simpler models generally exhibiting improved generalization. Model performance was also found to be highly sensitive to hyperparameter choices, particularly convolutional kernel sizes and normalization strategies. While this study focuses on echocardiography-based LVEF estimation, the insights gained regarding architectural design and training strategies may be applicable to a broader range of medical and non-medical video analysis tasks.
Read the full abstract

Computer Vision

Visual Autoregressive Modelling for Monocular Depth Estimation

Amir El-Ghoussani, André Kaup, Nassir Navab et al. (+2 more)

We propose a monocular depth estimation method based on visual autoregressive (VAR) priors, offering an alternative to diffusion-based approaches. Our method adapts a large-scale text-to-image VAR model and introduces a scale-wise conditional upsampling mechanism with classifier-free guidance. Our approach performs inference in ten fixed autoregressive stages, requiring only 74K synthetic samples for fine-tuning, and achieves competitive results. We report state-of-the-art performance in indoor benchmarks under constrained training conditions, and strong performance when applied to outdoor datasets. This work establishes autoregressive priors as a complementary family of geometry-aware generative models for depth estimation, highlighting advantages in data scalability, and adaptability to 3D vision tasks. Code available at "https://github.com/AmirMaEl/VAR-Depth".
Read the full abstract

All authors Amir El-Ghoussani, André Kaup, Nassir Navab, Gustavo Carneiro, Vasileios Belagiannis

Computer Vision

FinPercep-RM: A Fine-grained Reward Model and Co-evolutionary Curriculum for RL-based Real-world Super-Resolution

Yidi Liu, Zihao Fan, Jie Huang et al. (+6 more)

Reinforcement Learning with Human Feedback (RLHF) has proven effective in image generation field guided by reward models to align human preferences. Motivated by this, adapting RLHF for Image Super-Resolution (ISR) tasks has shown promise in optimizing perceptual quality with Image Quality Assessment (IQA) model as reward models. However, the traditional IQA model usually output a single global score, which are exceptionally insensitive to local and fine-grained distortions. This insensitivity allows ISR models to produce perceptually undesirable artifacts that yield spurious high scores, misaligning optimization objectives with perceptual quality and results in reward hacking. To address this, we propose a Fine-grained Perceptual Reward Model (FinPercep-RM) based on an Encoder-Decoder architecture. While providing a global quality score, it also generates a Perceptual Degradation Map that spatially localizes and quantifies local defects. We specifically introduce the FGR-30k dataset to train this model, consisting of diverse and subtle distortions from real-world super-resolution models. Despite the success of the FinPercep-RM model, its complexity introduces significant challenges in generator policy learning, leading to training instability. To address this, we propose a Co-evolutionary Curriculum Learning (CCL) mechanism, where both the reward model and the ISR model undergo synchronized curricula. The reward model progressively increases in complexity, while the ISR model starts with a simpler global reward for rapid convergence, gradually transitioning to the more complex model outputs. This easy-to-hard strategy enables stable training while suppressing reward hacking. Experiments validates the effectiveness of our method across ISR models in both global quality and local realism on RLHF methods.
Read the full abstract

All authors Yidi Liu, Zihao Fan, Jie Huang, Jie Xiao, Dong Li, Wenlong Zhang, Lei Bai, Xueyang Fu, Zheng-Jun Zha