Peer Revenue Past citations are no guarantee of future returns

Papers

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

Computer Science Computer Vision

cs.CV Watch Computer Vision (sign in to use)

Thursday 4 December

Computer Vision

MindDrive: An All-in-One Framework Bridging World Models and Vision-Language Model for End-to-End Autonomous Driving

End-to-End autonomous driving (E2E-AD) has emerged as a new paradigm, where trajectory planning plays a crucial role. Existing studies mainly follow two directions: trajectory generation oriented, which focuses on producing high-quality trajectories with simple decision mechanisms, and trajectory selection oriented, which performs multi-dimensional evaluation to select the best trajectory yet lacks sufficient generative capability. In this work, we propose MindDrive, a harmonized framework that integrates high-quality trajectory generation with comprehensive decision reasoning. It establishes a structured reasoning paradigm of "context simulation - candidate generation - multi-objective trade-off". In particular, the proposed Future-aware Trajectory Generator (FaTG), based on a World Action Model (WaM), performs ego-conditioned "what-if" simulations to predict potential future scenes and generate foresighted trajectory candidates. Building upon this, the VLM-oriented Evaluator (VLoE) leverages the reasoning capability of a large vision-language model to conduct multi-objective evaluations across safety, comfort, and efficiency dimensions, leading to reasoned and human-aligned decision making. Extensive experiments on the NAVSIM-v1 and NAVSIM-v2 benchmarks demonstrate that MindDrive achieves state-of-the-art performance across multi-dimensional driving metrics, significantly enhancing safety, compliance, and generalization. This work provides a promising path toward interpretable and cognitively guided autonomous driving.
Read the full abstract

All authors Bin Sun, Yaoguang Cao, Yan Wang, Rui Wang, Jiachen Shang, Xiejie Feng, Jiayi Lu, Jia Shi, Shichun Yang, Xiaoyu Yan, Ziying Song

Computer Vision

Self-Paced and Self-Corrective Masked Prediction for Movie Trailer Generation

As a challenging video editing task, movie trailer generation involves selecting and reorganizing movie shots to create engaging trailers. Currently, most existing automatic trailer generation methods employ a "selection-then-ranking" paradigm (i.e., first selecting key shots and then ranking them), which suffers from inevitable error propagation and limits the quality of the generated trailers. Beyond this paradigm, we propose a new self-paced and self-corrective masked prediction method called SSMP, which achieves state-of-the-art results in automatic trailer generation via bi-directional contextual modeling and progressive self-correction. In particular, SSMP trains a Transformer encoder that takes the movie shot sequences as prompts and generates corresponding trailer shot sequences accordingly. The model is trained via masked prediction, reconstructing each trailer shot sequence from its randomly masked counterpart. The mask ratio is self-paced, allowing the task difficulty to adapt to the model and thereby improving model performance. When generating a movie trailer, the model fills the shot positions with high confidence at each step and re-masks the remaining positions for the next prediction, forming a progressive self-correction mechanism that is analogous to how human editors work. Both quantitative results and user studies demonstrate the superiority of SSMP in comparison to existing automatic movie trailer generation methods. Demo is available at: https://github.com/Dixin-Lab/SSMP.
Read the full abstract

Computer Vision

Explainable Parkinsons Disease Gait Recognition Using Multimodal RGB-D Fusion and Large Language Models

Accurate and interpretable gait analysis plays a crucial role in the early detection of Parkinsons disease (PD),yet most existing approaches remain limited by single-modality inputs, low robustness, and a lack of clinical transparency. This paper presents an explainable multimodal framework that integrates RGB and Depth (RGB-D) data to recognize Parkinsonian gait patterns under realistic conditions. The proposed system employs dual YOLOv11-based encoders for modality-specific feature extraction, followed by a Multi-Scale Local-Global Extraction (MLGE) module and a Cross-Spatial Neck Fusion mechanism to enhance spatial-temporal representation. This design captures both fine-grained limb motion (e.g., reduced arm swing) and overall gait dynamics (e.g., short stride or turning difficulty), even in challenging scenarios such as low lighting or occlusion caused by clothing. To ensure interpretability, a frozen Large Language Model (LLM) is incorporated to translate fused visual embeddings and structured metadata into clinically meaningful textual explanations. Experimental evaluations on multimodal gait datasets demonstrate that the proposed RGB-D fusion framework achieves higher recognition accuracy, improved robustness to environmental variations, and clear visual-linguistic reasoning compared with single-input baselines. By combining multimodal feature learning with language-based interpretability, this study bridges the gap between visual recognition and clinical understanding, offering a novel vision-language paradigm for reliable and explainable Parkinsons disease gait analysis. Code:https://github.com/manaralnaasan/RGB-D_parkinson-LLM
Read the full abstract

Computer Vision

UTrice: Unifying Primitives in Differentiable Ray Tracing and Rasterization via Triangles for Particle-Based 3D Scenes

Ray tracing 3D Gaussian particles enables realistic effects such as depth of field, refractions, and flexible camera modeling for novel-view synthesis. However, existing methods trace Gaussians through proxy geometry, which requires constructing complex intermediate meshes and performing costly intersection tests. This limitation arises because Gaussian-based particles are not well suited as unified primitives for both ray tracing and rasterization. In this work, we propose a differentiable triangle-based ray tracing pipeline that directly treats triangles as rendering primitives without relying on any proxy geometry. Our results show that the proposed method achieves significantly higher rendering quality than existing ray tracing approaches while maintaining real-time rendering performance. Moreover, our pipeline can directly render triangles optimized by the rasterization-based method Triangle Splatting, thus unifying the primitives used in novel-view synthesis.
Read the full abstract

All authors Changhe Liu, Ehsan Javanmardi, Naren Bao, Alex Orsholits, Manabu Tsukada

Computer Vision

Dual-Stream Spectral Decoupling Distillation for Remote Sensing Object Detection

Knowledge distillation is an effective and hardware-friendly method, which plays a key role in lightweighting remote sensing object detection. However, existing distillation methods often encounter the issue of mixed features in remote sensing images (RSIs), and neglect the discrepancies caused by subtle feature variations, leading to entangled knowledge confusion. To address these challenges, we propose an architecture-agnostic distillation method named Dual-Stream Spectral Decoupling Distillation (DS2D2) for universal remote sensing object detection tasks. Specifically, DS2D2 integrates explicit and implicit distillation grounded in spectral decomposition. Firstly, the first-order wavelet transform is applied for spectral decomposition to preserve the critical spatial characteristics of RSIs. Leveraging this spatial preservation, a Density-Independent Scale Weight (DISW) is designed to address the challenges of dense and small object detection common in RSIs. Secondly, we show implicit knowledge hidden in subtle student-teacher feature discrepancies, which significantly influence predictions when activated by detection heads. This implicit knowledge is extracted via full-frequency and high-frequency amplifiers, which map feature differences to prediction deviations. Extensive experiments on DIOR and DOTA datasets validate the effectiveness of the proposed method. Specifically, on DIOR dataset, DS2D2 achieves improvements of 4.2% in AP50 for RetinaNet and 3.8% in AP50 for Faster R-CNN, outperforming existing distillation approaches. The source code will be available at https://github.com/PolarAid/DS2D2.
Read the full abstract

All authors Xiangyi Gao, Danpei Zhao, Bo Yuan, Wentao Li

Computer Vision

Performance Evaluation of Transfer Learning Based Medical Image Classification Techniques for Disease Detection

Medical image classification plays an increasingly vital role in identifying various diseases by classifying medical images, such as X-rays, MRIs and CT scans, into different categories based on their features. In recent years, deep learning techniques have attracted significant attention in medical image classification. However, it is usually infeasible to train an entire large deep learning model from scratch. To address this issue, one of the solutions is the transfer learning (TL) technique, where a pre-trained model is reused for a new task. In this paper, we present a comprehensive analysis of TL techniques for medical image classification using deep convolutional neural networks. We evaluate six pre-trained models (AlexNet, VGG16, ResNet18, ResNet34, ResNet50, and InceptionV3) on a custom chest X-ray dataset for disease detection. The experimental results demonstrate that InceptionV3 consistently outperforms other models across all the standard metrics. The ResNet family shows progressively better performance with increasing depth, whereas VGG16 and AlexNet perform reasonably well but with lower accuracy. In addition, we also conduct uncertainty analysis and runtime comparison to assess the robustness and computational efficiency of these models. Our findings reveal that TL is beneficial in most cases, especially with limited data, but the extent of improvement depends on several factors such as model architecture, dataset size, and domain similarity between source and target tasks. Moreover, we demonstrate that with a well-trained feature extractor, only a lightweight feedforward model is enough to provide efficient prediction. As such, this study contributes to the understanding of TL in medical image classification, and provides insights for selecting appropriate models based on specific requirements.
Read the full abstract

Computer Vision

Fourier-Attentive Representation Learning: A Fourier-Guided Framework for Few-Shot Generalization in Vision-Language Models

Large-scale pre-trained Vision-Language Models (VLMs) have demonstrated strong few-shot learning capabilities. However, these methods typically learn holistic representations where an image's domain-invariant structure is implicitly entangled with its domain-specific style. This presents an opportunity to further enhance generalization by disentangling these visual cues. In this paper, we propose Fourier-Attentive Representation Learning (FARL), a novel framework that addresses this by explicitly disentangling visual representations using Fourier analysis. The core of our method is a dual cross-attention mechanism, where learnable representation tokens separately query an image's structural features (from the phase spectrum) and stylistic features (from the amplitude spectrum). This process yields enriched, disentangled tokens that are then injected deep into the VLM encoders to guide adaptation. Our design, which includes an asymmetric injection strategy, forces the model to learn a more robust vision-language alignment. Extensive experiments on 15 datasets demonstrate the effectiveness of our approach.
Read the full abstract

Computer Vision

FMA-Net++: Motion- and Exposure-Aware Joint Video Super-Resolution and Deblurring

Joint video super-resolution and deblurring (VSRDB) requires both efficient long-range temporal modeling and robustness to frame-wise exposure-duration variation, which changes the extent of motion blur across video frames. We propose FMA-Net++, a non-recurrent, sequence-level framework built from Hierarchical Refinement with Bidirectional Aggregation (HRBA) blocks. By stacking HRBA blocks, FMA-Net++ processes video frames in parallel while hierarchically expanding the temporal receptive field, avoiding the limited temporal receptive field of sliding-window designs and the sequential bottleneck of recurrent ones. To handle exposure-duration-dependent blur, we introduce an Exposure Time-aware Modulation (ETM) layer that conditions HRBA features on exposure embeddings from an Exposure Time-aware Feature Extractor (ETE). The conditioned features guide an exposure-aware flow-guided dynamic filtering module to predict motion- and exposure-aware degradation kernels. FMA-Net++ decouples degradation learning from restoration: the former predicts degradation priors and the latter exploits them for efficient high-resolution restoration. To evaluate VSRDB under controlled exposure-duration variation, we introduce the REDS-ME (multi-exposure) and REDS-RE (random-exposure) benchmarks. Trained solely on synthetic data, FMA-Net++ achieves state-of-the-art accuracy and temporal consistency on these benchmarks. It further shows strong out-of-distribution performance on GoPro and challenging real-world videos, while outperforming recent methods in both restoration quality and inference speed.
Read the full abstract

Computer Vision · Cross-listed from cs.LG

STeP-Diff: Spatio-Temporal Physics-Informed Diffusion Models for Mobile Fine-Grained Pollution Forecasting

Fine-grained air pollution forecasting is crucial for urban management and the development of healthy buildings. Deploying portable sensors on mobile platforms such as cars and buses offers a low-cost, easy-to-maintain, and wide-coverage data collection solution. However, due to the random and uncontrollable movement patterns of these non-dedicated mobile platforms, the resulting sensor data are often incomplete and temporally inconsistent. By exploring potential training patterns in the reverse process of diffusion models, we propose Spatio-Temporal Physics-Informed Diffusion Models (STeP-Diff). STeP-Diff leverages DeepONet to model the spatial sequence of measurements along with a PDE-informed diffusion model to forecast the spatio-temporal field from incomplete and time-varying data. Through a PDE-constrained regularization framework, the denoising process asymptotically converges to the convection-diffusion dynamics, ensuring that predictions are both grounded in real-world measurements and aligned with the fundamental physics governing pollution dispersion. To assess the performance of the system, we deployed 59 self-designed portable sensing devices in two cities, operating for 14 days to collect air pollution data. Compared to the second-best performing algorithm, our model achieved improvements of up to 89.12% in MAE, 82.30% in RMSE, and 25.00% in MAPE, with extensive evaluations demonstrating that STeP-Diff effectively captures the spatio-temporal dependencies in air pollution fields.
Read the full abstract

All authors Nan Zhou, Weijie Hong, Huandong Wang, Jianfeng Zheng, Qiuhua Wang, Yali Song, Xiao-Ping Zhang, Yong Li, Xinlei Chen

Computer Vision

MAFNet:Multi-frequency Adaptive Fusion Network for Real-time Stereo Matching

Existing stereo matching networks typically rely on either cost-volume construction based on 3D convolutions or deformation methods based on iterative optimization. The former incurs significant computational overhead during cost aggregation, whereas the latter often lacks the ability to model non-local contextual information. These methods exhibit poor compatibility on resource-constrained mobile devices, limiting their deployment in real-time applications. To address this, we propose a Multi-frequency Adaptive Fusion Network (MAFNet), which can produce high-quality disparity maps using only efficient 2D convolutions. Specifically, we design an adaptive frequency-domain filtering attention module that decomposes the full cost volume into high-frequency and low-frequency volumes, performing frequency-aware feature aggregation separately. Subsequently, we introduce a Linformer-based low-rank attention mechanism to adaptively fuse high- and low-frequency information, yielding more robust disparity estimation. Extensive experiments demonstrate that the proposed MAFNet significantly outperforms existing real-time methods on public datasets such as Scene Flow and KITTI 2015, showing a favorable balance between accuracy and real-time performance.
Read the full abstract

All authors Ao Xu, Rujin Zhao, Xiong Xu, Boceng Huang, Yujia Jia, Hongfeng Long, Fuxuan Chen, Zilong Cao, Fangyuan Chen

Computer Vision

Mitigating Object and Action Hallucinations in Multimodal LLMs via Self-Augmented Contrastive Alignment

Recent advancement in multimodal LLMs (MLLMs) has demonstrated their remarkable capability to generate descriptive captions for input videos. However, these models suffer from factual inaccuracies in the generated descriptions, causing severe hallucination issues. While prior works have explored alleviating hallucinations for static images, jointly mitigating visual object and temporal action hallucinations for dynamic videos remains a challenging and unsolved task. To tackle this challenge, we propose a Self-Augmented Contrastive Alignment (SANTA) framework for enabling object and action faithfulness by exempting the spurious correlations and enforcing the emphasis on visual facts. SANTA employs a hallucinative self-augmentation scheme to identify the potential hallucinations that lie in the MLLM and transform the original captions to the contrasted negatives. Furthermore, we develop a tracklet-phrase contrastive alignment to match the regional objects and relation-guided actions with their corresponding visual and temporal phrases. Extensive experiments demonstrate that SANTA outperforms existing methods in alleviating object and action hallucinations, yielding superior performance on the hallucination examination benchmarks.
Read the full abstract

All authors Kai-Po Chang, Wei-Yuan Cheng, Chi-Pin Huang, Fu-En Yang, Yu-Chiang Frank Wang

Wednesday 3 December

Computer Vision · Cross-listed from cs.IR

Adaptive Prefiltering for High-Dimensional Similarity Search: A Frequency-Aware Approach

High-dimensional similarity search underpins modern retrieval systems, yet uniform search strategies fail to exploit the heterogeneous nature of real-world query distributions. We present an adaptive prefiltering framework that leverages query frequency patterns and cluster coherence metrics to dynamically allocate computational budgets. Our approach partitions the query space into frequency tiers following Zipfian distributions and assigns differentiated search policies based on historical access patterns and local density characteristics. Experiments on ImageNet-1k using CLIP embeddings demonstrate that frequency-aware budget allocation achieves equivalent recall with 20.4% fewer distance computations compared to static nprobe selection, while maintaining sub-millisecond latency on GPU-accelerated FAISS indices. The framework introduces minimal overhead through lightweight frequency tracking and provides graceful degradation for unseen queries through coherence-based fallback policies.
Read the full abstract

Computer Vision · Cross-listed from q-bio.QM

Vision Foundry: A System for Training Foundational Vision AI Models

Self-supervised learning (SSL) leverages vast unannotated medical datasets, yet steep technical barriers limit adoption by clinical researchers. We introduce Vision Foundry, a code-free, HIPAA-compliant platform that democratizes pre-training, adaptation, and deployment of foundational vision models. The system integrates the DINO-MX framework, abstracting distributed infrastructure complexities while implementing specialized strategies like Magnification-Aware Distillation (MAD) and Parameter-Efficient Fine-Tuning (PEFT). We validate the platform across domains, including neuropathology segmentation, lung cellularity estimation, and coronary calcium scoring. Our experiments demonstrate that models trained via Vision Foundry significantly outperform generic baselines in segmentation fidelity and regression accuracy, while exhibiting robust zero-shot generalization across imaging protocols. By bridging the gap between advanced representation learning and practical application, Vision Foundry enables domain experts to develop state-of-the-art clinical AI tools with minimal annotation overhead, shifting focus from engineering optimization to clinical discovery.
Read the full abstract

All authors Mahmut S. Gokmen, Mitchell A. Klusty, Evan W. Damron, W. Vaiden Logan, Aaron D. Mullen, Caroline N. Leach, Emily B. Collier, Samuel E. Armstrong, V.K. Cody Bumgardner

Computer Vision · Cross-listed from cs.LG

Soft Decision Tree classifier: explainable and extendable PyTorch implementation

We implemented a Soft Decision Tree (SDT) and a Short-term Memory Soft Decision Tree (SM-SDT) using PyTorch. The methods were extensively tested on simulated and clinical datasets. The SDT was visualized to demonstrate the potential for its explainability. SDT, SM-SDT, and XGBoost demonstrated similar area under the curve (AUC) values. These methods were better than Random Forest, Logistic Regression, and Decision Tree. The results on clinical datasets suggest that, aside from a decision tree, all tested classification methods yield comparable results. The code and datasets are available online on GitHub: https://github.com/KI-Research-Institute/Soft-Decision-Tree
Read the full abstract

Computer Vision · Cross-listed from cs.LG

On the Design of One-step Diffusion via Shortcutting Flow Paths

Recent advances in few-step diffusion models have demonstrated their efficiency and effectiveness by shortcutting the probabilistic paths of diffusion models, especially in training one-step diffusion models from scratch (a.k.a. shortcut models). However, their theoretical derivation and practical implementation are often closely coupled, which obscures the design space. To address this, we propose a common design framework for representative shortcut models. This framework provides theoretical justification for their validity and disentangles concrete component-level choices, thereby enabling systematic identification of improvements. With our proposed improvements, the resulting one-step model achieves a new state-of-the-art FID50k of 2.85 on ImageNet-256x256 under the classifier-free guidance setting with one step generation, and further reaches FID50k of 2.53 with 2x training steps. Remarkably, the model requires no pre-training, distillation, or curriculum learning. We believe our work lowers the barrier to component-level innovation in shortcut models and facilitates principled exploration of their design space.
Read the full abstract

All authors Haitao Lin, Peiyan Hu, Minsi Ren, Zhifeng Gao, Zhi-Ming Ma, Guolin ke, Tailin Wu, Stan Z. Li

Computer Vision

Benchmarking CXR Foundation Models With Publicly Available MIMIC-CXR and NIH-CXR14 Datasets

Recent foundation models have demonstrated strong performance in medical image representation learning, yet their comparative behaviour across datasets remains underexplored. This work benchmarks two large-scale chest X-ray (CXR) embedding models (CXR-Foundation (ELIXR v2.0) and MedImagelnsight) on public MIMIC-CR and NIH ChestX-ray14 datasets. Each model was evaluated using a unified preprocessing pipeline and fixed downstream classifiers to ensure reproducible comparison. We extracted embeddings directly from pre-trained encoders, trained lightweight LightGBM classifiers on multiple disease labels, and reported mean AUROC, and F1-score with 95% confidence intervals. MedImageInsight achieved slightly higher performance across most tasks, while CXR-Foundation exhibited strong cross-dataset stability. Unsupervised clustering of MedImageIn-sight embeddings further revealed a coherent disease-specific structure consistent with quantitative results. The results highlight the need for standardised evaluation of medical foundation models and establish reproducible baselines for future multimodal and clinical integration studies.
Read the full abstract

Computer Vision

VAT: Vision Action Transformer by Unlocking Full Representation of ViT

In robot learning, Vision Transformers (ViTs) are standard for visual perception, yet most methods discard valuable information by using only the final layer's features. We argue this provides an insufficient representation and propose the Vision Action Transformer (VAT), a novel architecture that is extended from ViT and unlocks the full feature hierarchy of ViT. VAT processes specialized action tokens with visual features across all transformer layers, enabling a deep and progressive fusion of perception and action generation. On a suite of simulated manipulation tasks, VAT achieves a 98.15% average success rate across four LIBERO benchmarks, establishing a new state-of-the-art by outperforming prior methods like OpenVLA-OFT. Our work presents not only a powerful model for imitation learning but also demonstrates the critical importance of leveraging the complete ”representation trajectory” of vision models to advance robotic policy. The GitHub URL for the project code is https://github.com/sellerbubble/VAT.
Read the full abstract

Computer Vision

High-Throughput Unsupervised Profiling of the Morphology of 316L Powder Particles for Use in Additive Manufacturing

Selective Laser Melting (SLM) is a powder-bed additive manufacturing technique whose part quality depends critically on feedstock morphology. However, conventional powder characterization methods are low-throughput and qualitative, failing to capture the heterogeneity of industrial-scale batches. We present an automated, machine learning framework that couples high-throughput imaging with shape extraction and clustering to profile metallic powder morphology at scale. We develop and evaluate three clustering pipelines: an autoencoder pipeline, a shape-descriptor pipeline, and a functional-data pipeline. Across a dataset of approximately 126,000 powder images (0.5-102 micrometer diameter), internal validity metrics identify the Fourier-descriptor + k-means pipeline as the most effective, achieving the lowest Davies-Bouldin index and highest Calinski-Harabasz score while maintaining sub-millisecond runtime per particle on a standard desktop workstation. Although the present work focuses on establishing the morphological-clustering framework, the resulting shape groups form a basis for future studies examining their relationship to flowability, packing density, and SLM part quality. Overall, this unsupervised learning framework enables rapid, automated assessment of powder morphology and supports tracking of shape evolution across reuse cycles, offering a path toward real-time feedstock monitoring in SLM workflows.
Read the full abstract

All authors Emmanuel Akeweje, Conall Kirk, Chi-Wai Chan, Denis Dowling, Mimi Zhang

Computer Vision

Fast and Flexible Robustness Certificates for Semantic Segmentation

Deep Neural Networks are vulnerable to small perturbations that can drastically alter their predictions for perceptually unchanged inputs. The literature on adversarially robust Deep Learning attempts to either enhance the robustness of neural networks (e.g, via adversarial training) or to certify their decisions up to a given robustness level (e.g, by using randomized smoothing, formal methods or Lipschitz bounds). These studies mostly focus on classification tasks and few efficient certification procedures currently exist for semantic segmentation. In this work, we introduce a new class of certifiably robust Semantic Segmentation networks with built-in Lipschitz constraints that are efficiently trainable and achieve competitive pixel accuracy on challenging datasets such as Cityscapes. Additionally, we provide a novel framework that generalizes robustness certificates for semantic segmentation tasks, where we showcase the flexibility and computational efficiency of using Lipschitz networks. Our approach unlocks real-time compatible certifiably robust semantic segmentation for the first time. Moreover, it allows the computation of worst-case performance under $\ell_2$ attacks of radius $\epsilon$ across a wide range of performance measures. Crucially, we benchmark the runtime of our certification process and find our approach to be around 600 times faster than randomized smoothing methods at inference with comparable certificates on an NVIDIA A100 GPU. Finally, we evaluate the tightness of our worstcase certificates against state-of-the-art adversarial attacks to further validate the performance of our method.
Read the full abstract

All authors Thomas Massena, Corentin Friedrich, Franck Mamalet, Mathieu Serrurier

Computer Vision · Cross-listed from eess.IV

Semantic Temporal Single-photon LiDAR

Temporal single-photon (TSP-) LiDAR presents a promising solution for imaging-free target recognition over long distances with reduced size, cost, and power consumption. However, existing TSP-LiDAR approaches are ineffective in handling open-set scenarios where unknown targets emerge, and they suffer significant performance degradation under low signal-to-noise ratio (SNR) and short acquisition times (fewer photons). Here, inspired by semantic communication, we propose a semantic TSP-LiDAR based on a self-updating semantic knowledge base (SKB), in which the target recognition processing of TSP-LiDAR is formulated as a semantic communication. The results, both simulation and experiment, demonstrate that our approach surpasses conventional methods, particularly under challenging conditions of low SNR and limited acquisition time. More importantly, our self-updating SKB mechanism can dynamically update the semantic features of newly encountered targets in the SKB, enabling continuous adaptation without the need for extensive retraining of the neural network. In fact, a recognition accuracy of 89% is achieved on nine types of unknown targets in real-world experiments, compared to 66% without the updating mechanism. These findings highlight the potential of our framework for adaptive and robust target recognition in complex and dynamic environments.
Read the full abstract

All authors Fang Li, Tonglin Mu, Shuling Li, Junran Guo, Keyuan Li, Jianing Li, Ziyang Luo, Xiaodong Fan, Ye Chen, Yunfeng Liu, Hong Cai, Lip Ket Chin, Jinbei Zhang, Shihai Sun

Computer Vision

EFDiT: Efficient Fine-grained Image Generation Using Diffusion Transformer Models

Diffusion models are highly regarded for their controllability and the diversity of images they generate. However, class-conditional generation methods based on diffusion models often focus on more common categories. In large-scale fine-grained image generation, issues of semantic information entanglement and insufficient detail in the generated images still persist. This paper attempts to introduce a concept of a tiered embedder in fine-grained image generation, which integrates semantic information from both super and child classes, allowing the diffusion model to better incorporate semantic information and address the issue of semantic entanglement. To address the issue of insufficient detail in fine-grained images, we introduce the concept of super-resolution during the perceptual information generation stage, enhancing the detailed features of fine-grained images through enhancement and degradation models. Furthermore, we propose an efficient ProAttention mechanism that can be effectively implemented in the diffusion model. We evaluate our method through extensive experiments on public benchmarks, demonstrating that our approach outperforms other state-of-the-art fine-tuning methods in terms of performance.
Read the full abstract

All authors Kun Wang, Donglin Di, Tonghua Su, Lei Fan

Computer Vision

TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows

Recent advances in large multi-modal generative models have demonstrated impressive capabilities in multi-modal generation, including image and video generation. These models are typically built upon multi-step frameworks like diffusion and flow matching, which inherently limits their inference efficiency (requiring 40-100 Number of Function Evaluations (NFEs)). While various few-step methods aim to accelerate the inference, existing solutions have clear limitations. Prominent distillation-based methods, such as progressive and consistency distillation, either require an iterative distillation procedure or show significant degradation at very few steps (< 4-NFE). Meanwhile, integrating adversarial training into distillation (e.g., DMD/DMD2 and SANA-Sprint) to enhance performance introduces training instability, added complexity, and high GPU memory overhead due to the auxiliary trained models. To this end, we propose TwinFlow, a simple yet effective framework for training 1-step generative models that bypasses the need of fixed pretrained teacher models and avoids standard adversarial networks during training, making it ideal for building large-scale, efficient models. On text-to-image tasks, our method achieves a GenEval score of 0.83 in 1-NFE, outperforming strong baselines like SANA-Sprint (a GAN loss-based framework) and RCGM (a consistency-based framework). Notably, we demonstrate the scalability of TwinFlow by full-parameter training on Qwen-Image-20B and transform it into an efficient few-step generator. With just 1-NFE, our approach matches the performance of the original 100-NFE model on both the GenEval and DPG-Bench benchmarks, reducing computational cost by $100\times$ with minor quality degradation. Project page is available at https://zhenglin-cheng.com/twinflow.
Read the full abstract

All authors Zhenglin Cheng, Peng Sun, Jianguo Li, Tao Lin

Computer Vision

Open Set Face Forgery Detection via Dual-Level Evidence Collection

The surge in face forgeries has increasingly undermined confidence in the authenticity of online content. As generation algorithms rapidly evolve, new fake categories will constantly emerge, severely challenging existing face forgery detection methods. Although face forgery detection has recently improved, current techniques remain largely confined to binary Real-vs-Fake classification or the recognition of known fake categories. Moreover, they fail to identify the emergence of entirely new forgery methods. In this work, we study the Open Set Face Forgery Detection (OSFFD) problem, which requires the detection model to identify novel fake categories. To enhance its real-world applicability, we reformulate the OSFFD problem and address it through uncertainty estimation. Specifically, we propose the Dual-Level Evidential face forgery Detection (DLED) approach, which estimates prediction uncertainty by extracting and integrating category-specific evidence on the spatial and frequency levels. Comprehensive experiments across diverse settings demonstrate that our proposed DLED approach achieves state-of-the-art performance. Notably, it surpasses various existing baseline models by a $20\%$ margin on average when identifying forgeries from novel fake categories. Concurrently, our DLED method yields competitive performance on the standard binary Real-versus-Fake face forgery detection task.
Read the full abstract

All authors Zhongyi Cai, Bryce Gernon, Wentao Bao, Yifan Li, Matthew Wright, Yu Kong

Computer Vision

A Retrieval-Augmented Generation Approach to Extracting Algorithmic Logic from Neural Networks

Reusing existing neural-network components is central to research efficiency, yet discovering, extracting, and validating such modules across thousands of open-source repositories remains difficult. We introduce NN-RAG, a retrieval-augmented generation system that converts large, heterogeneous PyTorch codebases into a searchable and executable library of validated neural modules. Unlike conventional code search or clone-detection tools, NN-RAG performs scope-aware dependency resolution, import-preserving reconstruction, and validator-gated promotion – ensuring that every retrieved block is scope-closed, compilable, and runnable. Applied to 19 major repositories, the pipeline extracted 1,289 candidate blocks, validated 941 (73.0%), and demonstrated that over 80% are structurally unique. Through multi-level de-duplication (exact, lexical, structural), we find that NN-RAG contributes the overwhelming majority of unique architectures to the LEMUR dataset, supplying approximately 72% of all novel network structures. Beyond quantity, NN-RAG uniquely enables cross-repository migration of architectural patterns, automatically identifying reusable modules in one project and regenerating them, dependency-complete, in another context. To our knowledge, no other open-source system provides this capability at scale. The framework's neutral specifications further allow optional integration with language models for synthesis or dataset registration without redistributing third-party code. Overall, NN-RAG transforms fragmented vision code into a reproducible, provenance-tracked substrate for algorithmic discovery, offering a first open-source solution that both quantifies and expands the diversity of executable neural architectures across repositories.
Read the full abstract

Computer Vision

Bayes-DIC Net: Estimating Digital Image Correlation Uncertainty with Bayesian Neural Networks

This paper introduces a novel method for generating high-quality Digital Image Correlation (DIC) dataset based on non-uniform B-spline surfaces. By randomly generating control point coordinates, we construct displacement fields that encompass a variety of realistic displacement scenarios, which are subsequently used to generate speckle pattern datasets. This approach enables the generation of a large-scale dataset that capture real-world displacement field situations, thereby enhancing the training and generalization capabilities of deep learning-based DIC algorithms. Additionally, we propose a novel network architecture, termed Bayes-DIC Net, which extracts information at multiple levels during the down-sampling phase and facilitates the aggregation of information across various levels through a single skip connection during the up-sampling phase. Bayes-DIC Net incorporates a series of lightweight convolutional blocks designed to expand the receptive field and capture rich contextual information while minimizing computational costs. Furthermore, by integrating appropriate dropout modules into Bayes-DIC Net and activating them during the network inference stage, Bayes-DIC Net is transformed into a Bayesian neural network. This transformation allows the network to provide not only predictive results but also confidence levels in these predictions when processing real unlabeled datasets. This feature significantly enhances the practicality and reliability of our network in real-world displacement field prediction tasks. Through these innovations, this paper offers new perspectives and methods for dataset generation and algorithm performance enhancement in the field of DIC.
Read the full abstract

All authors Biao Chen, Zhenhua Lei, Yahui Zhang, Tongzhi Niu

Computer Vision

SyncTrack4D: Cross-Video Motion Alignment and Video Synchronization for Multi-Video 4D Gaussian Splatting

Modeling dynamic 3D scenes is challenging due to their high-dimensional nature, which requires aggregating information from multiple views to reconstruct time-evolving 3D geometry and motion. We present a novel multi-video 4D Gaussian Splatting (4DGS) approach designed to handle real-world, unsynchronized video sets. Our approach, SyncTrack4D, directly leverages dense 4D track representation of dynamic scene parts as cues for simultaneous cross-video synchronization and 4DGS reconstruction. We first compute dense per-video 4D feature tracks and cross-video track correspondences by Fused Gromov-Wasserstein optimal transport approach. Next, we perform global frame-level temporal alignment to maximize overlapping motion of matched 4D tracks. Finally, we achieve sub-frame synchronization through our multi-video 4D Gaussian splatting built upon a motion-spline scaffold representation. The final output is a synchronized 4DGS representation with dense, explicit 3D trajectories, and temporal offsets for each video. We evaluate our approach on the Panoptic Studio and SyncNeRF Blender, demonstrating sub-frame synchronization accuracy with an average temporal error below 0.26 frames, and high-fidelity 4D reconstruction reaching 26.3 PSNR scores on the Panoptic Studio dataset. To the best of our knowledge, our work is the first general 4D Gaussian Splatting approach for unsynchronized video sets, without assuming the existence of predefined scene objects or prior models.
Read the full abstract

All authors Yonghan Lee, Tsung-Wei Huang, Shiv Gehlot, Jaehoon Choi, Guan-Ming Su, Dinesh Manocha

Computer Vision

DisentangleFormer: Spatial-Channel Decoupling for Multi-Channel Vision

Vision Transformers face a fundamental limitation: standard self-attention jointly processes spatial and channel dimensions, leading to entangled representations that prevent independent modeling of structural and semantic dependencies. This problem is especially pronounced in hyperspectral imaging, from satellite hyperspectral remote sensing to infrared pathology imaging, where channels capture distinct biophysical or biochemical cues. We propose DisentangleFormer, an architecture that achieves robust multi-channel vision representation through principled spatial-channel decoupling. Motivated by information-theoretic principles of decorrelated representation learning, our parallel design enables independent modeling of structural and semantic cues while minimizing redundancy between spatial and channel streams. Our design integrates three core components: (1) Parallel Disentanglement: Independently processes spatial-token and channel-token streams, enabling decorrelated feature learning across spatial and spectral dimensions, (2) Squeezed Token Enhancer: An adaptive calibration module that dynamically fuses spatial and channel streams, and (3) Multi-Scale FFN: complementing global attention with multi-scale local context to capture fine-grained structural and semantic dependencies. Extensive experiments on hyperspectral benchmarks demonstrate that DisentangleFormer achieves state-of-the-art performance, consistently outperforming existing models on Indian Pine, Pavia University, and Houston, the large-scale BigEarthNet remote sensing dataset, as well as an infrared pathology dataset. Moreover, it retains competitive accuracy on ImageNet while reducing computational cost by 17.8% in FLOPs. The code will be made publicly available upon acceptance.
Read the full abstract

All authors Jiashu Liao, Pietro Liò, Marc de Kamps, Duygu Sarikaya

Computer Vision

Mind-to-Face: Neural-Driven Photorealistic Avatar Synthesis via EEG Decoding

Current expressive avatar systems rely heavily on visual cues, failing when faces are occluded or when emotions remain internal. We present Mind-to-Face, the first framework that decodes non-invasive electroencephalogram (EEG) signals directly into high-fidelity facial expressions. We build a dual-modality recording setup to obtain synchronized EEG and multi-view facial video during emotion-eliciting stimuli, enabling precise supervision for neural-to-visual learning. Our model uses a CNN-Transformer encoder to map EEG signals into dense 3D position maps, capable of sampling over 65k vertices, capturing fine-scale geometry and subtle emotional dynamics, and renders them through a modified 3D Gaussian Splatting pipeline for photorealistic, view-consistent results. Through extensive evaluation, we show that EEG alone can reliably predict dynamic, subject-specific facial expressions, including subtle emotional responses, demonstrating that neural signals contain far richer affective and geometric information than previously assumed. Mind-to-Face establishes a new paradigm for neural-driven avatars, enabling personalized, emotion-aware telepresence and cognitive interaction in immersive environments.
Read the full abstract

All authors Haolin Xiong, Tianwen Fu, Pratusha Bhuvana Prasad, Yunxuan Cai, Haiwei Chen, Wenbin Teng, Hanyuan Xiao, Yajie Zhao

Computer Vision

Real-time Cricket Sorting By Sex

The global demand for sustainable protein sources is driving increasing interest in edible insects, with Acheta domesticus (house cricket) identified as one of the most suitable species for industrial production. Current farming practices typically rear crickets in mixed-sex populations without automated sex sorting, despite potential benefits such as selective breeding, optimized reproduction ratios, and nutritional differentiation. This work presents a low-cost, real-time system for automated sex-based sorting of Acheta domesticus, combining computer vision and physical actuation. The device integrates a Raspberry Pi 5 with the official Raspberry AI Camera and a custom YOLOv8 nano object detection model, together with a servo-actuated sorting arm. The model reached a mean Average Precision at IoU 0.5 (mAP@0.5) of 0.977 during testing, and real-world experiments with groups of crickets achieved an overall sorting accuracy of 86.8%. These results demonstrate the feasibility of deploying lightweight deep learning models on resource-constrained devices for insect farming applications, offering a practical solution to improve efficiency and sustainability in cricket production.
Read the full abstract

Computer Vision

Text-Only Training for Image Captioning with Retrieval Augmentation and Modality Gap Correction

Image captioning has drawn considerable attention from the natural language processing and computer vision fields. Aiming to reduce the reliance on curated data, several studies have explored image captioning without any humanly-annotated image-text pairs for training, although existing methods are still outperformed by fully supervised approaches. This paper proposes TOMCap, i.e., an improved text-only training method that performs captioning without the need for aligned image-caption pairs. The method is based on prompting a pre-trained language model decoder with information derived from a CLIP representation, after undergoing a process to reduce the modality gap. We specifically tested the combined use of retrieved examples of captions, and latent vector representations, to guide the generation process. Through extensive experiments, we show that TOMCap outperforms other training-free and text-only methods. We also analyze the impact of different choices regarding the configuration of the retrieval-augmentation and modality gap reduction components.
Read the full abstract