Computer Vision
Evaluation of Image Matching for Art Skills Assessment
Asaad Alghamdi, Michael Poor, Trung-Nghia Le et al. (+1 more)
While some individuals possess a natural talent for drawing, mastering this skill requires dedicated training and practice. Determining one's skill in the art of drawing requires proper comprehensive assessment. In this paper, we propose a method to measure drawing skill by by matching the hand-drawn image with the original template. Existing techniques often involve complex processes. However, advancements in computer
vision allow us to train computers to perform these comparisons at a human-like level, thereby resolving the tedious and overwhelming traditional process. Using computer
vision applications, determining image similarity involves identifying the level of similarities in an image with a reference image. We have implemented and analyzed the SIFT feature and Siamese network to measure image similarity. Our results indicate that it is feasible to assess art skill levels. Through feature analysis, we found that SIFT-based key point matching provides a more effective means of detecting drawing skills.
Read the full abstract ▾
All authors Asaad Alghamdi, Michael Poor, Trung-Nghia Le, Tam V. Nguyen
Computer Vision
Distill Once, Adapt Life-Long: Exploring Dataset Distillation for Continual Test-Time Adaptation
Hyun-Kurl Jang, Jihun Kim, Hyeokjun Kweon et al. (+1 more)
Continual Test-Time Adaptation (CTTA) aims to maintain model performance under evolving target domains by adapting online without labeled data. However, practical deployments often cannot retain the source
dataset due to
privacy or licensing constraints, and purely source-free CTTA methods tend to become unstable under long-term distribution shift, suffering from compounding self-training errors and catastrophic forgetting. We introduce DO-ALL (Distill Once, Adapt Life-Long), a plug-and-play framework that revisits source information in a compact and
privacy-conscious form via
Dataset Distillation (DD). Before deployment, DO-ALL performs DD to produce a small set of synthetic distilled anchors that summarize the source distribution. During adaptation, each target sample is matched with its most semantically aligned anchor, which provides a stable reference for various CTTA via source replay, representation
alignment, and
manifold-smoothing regularization. DO-ALL can be seamlessly integrated into existing CTTA
algorithms, consistently improving long-term robustness across CIFAR100-C, ImageNet-C, and the CCC
benchmark. This demonstrates the potential of leveraging DD to enable stable and continuous adaptation without retaining raw source data. The code is available at https://github.com/blue-531/DOALL.
Read the full abstract ▾
All authors Hyun-Kurl Jang, Jihun Kim, Hyeokjun Kweon, Kuk-Jin Yoon
Computer Vision
HilDA: Hierarchical Distillation with Diffusion for Advancing Self-Supervised LiDAR Pre-training
Maciej Wozniak, Jesper Ericsson, Hariprasath Govindarajan et al. (+4 more)
Leveraging
Vision Foundation Models (VFMs) for camera-to-
LiDAR knowledge
distillation offers a promising solution to the scarcity of annotated data needed to represent the immense
geometric and kinematic diversity of real-world autonomous driving (AD). However, current approaches typically treat VFMs as black-box teachers, relying exclusively on frame-wise feature similarity. Consequently, they do not fully exploit the teacher's layer-wise semantic structure and global context, as well as the rich spatiotemporal information inherent in
LiDAR sequences. We propose HilDA, a self-supervised pretraining framework for
LiDAR backbones that better captures the semantic what and
geometric where needed for driving tasks. HilDA combines hierarchical
distillation comprising multi-layer
distillation for progressive semantic
alignment and global context
distillation for scene-level semantics, with a temporal occupancy
diffusion objective promoting spatiotemporal consistency. Models pre-trained with HilDA achieve state-of-the-art results on cross-modal
distillation benchmarks and outperform models trained via prior
distillation approaches on 3D object detection, scene flow, and semantic occupancy prediction. Code available at: https://maxiuw.github.io/hilda.
Read the full abstract ▾
All authors Maciej Wozniak, Jesper Ericsson, Hariprasath Govindarajan, Truls Nyberg, Thomas Gustafsson, Patric Jensfelt, Olov Andersson
Computer Vision
Evaluating and Enhancing Negation Comprehension in Remote Sensing MLLMs
Haochen Han, Jue Wang, Alex Jinpeng Wang et al. (+1 more)
Multimodal Large
Language Models (MLLMs) have demonstrated remarkable success in various Remote Sensing (RS) tasks. However, their ability to comprehend negation remains underexplored, limiting deployment in real-world applications where models must explicitly identify what is false or absent, e.g., emergency responders need to locate non-flooded routes for evacuation. To comprehensively study this limitation, we introduce RS-Neg, the first
benchmark to evaluate negation understanding across region-level to scene-level tasks. Specifically, we design an automated data generation pipeline for RS imagery, using LLMs to synthesize diverse negation queries, and introduce a dynamic visual focus module for verification. Our evaluation reveals that advanced RS MLLMs struggle with negation, exhibiting
hallucinations and substantial performance degradation. To close this gap, we propose NeFo, a novel test-time learning method that explicitly incorporates the logical role of negation into the model optimization. Remarkably, using about 5% unlabeled test samples, NeFo significantly improves the negation understanding of models and shows strong generalization to unseen tasks.
Read the full abstract ▾
All authors Haochen Han, Jue Wang, Alex Jinpeng Wang, Fangming Liu
Computer Vision
ARTEMIS: Agent-guided Reliability-aware Temporal Mask Evolution for Imperfectly Supervised Video Polyp Segmentation
Tong Wang, Siwen Wang, Yaolei Qi et al. (+4 more)
Imperfectly supervised
video polyp
segmentation (VPS) aims to learn dense, temporally consistent masks from inexpensive supervision, including weak annotations (points, scribbles) and semi-supervision with few densely labeled frames. This setting is clinically valuable but challenging due to weak contrast, ambiguous boundaries, motion blur, and specular highlights, compounded by sparse pixel-level guidance. While SAM2 can generate dense masks from sparse inputs, direct pseudo-labeling often yields geometry-degraded masks with boundary leakage, underutilizes temporal consistency, and ignores reliability. To address these issues, we propose ARTEMIS, a unified framework for imperfectly supervised VPS driven by
agent-guided reliability-aware temporal mask
evolution. ARTEMIS initializes coarse masks from available supervision: SAM2 converts points/scribbles, while dense labels serve as reliable anchors. A debate-and-judge
vision-
language agent selects reliable temporal anchors under weak supervision, which are propagated bidirectionally with SAM2 to refine unreliable or unlabeled frames. Finally, ARTEMIS trains the segmenter using temporal reliability-aware robust learning, incorporating reliability-guided reference selection, a Reference Prototype Transport Module, and reliability-aware robust loss. These components assess mask reliability, evolve anchors over time, transport target identity across frames, and down-weight noisy supervision instead of discarding difficult samples. Experiments on SUN-SEG and CVC-ClinicDB-612 under scribble, point, and limited-label settings demonstrate that ARTEMIS achieves state-of-the-art performance. Code will be released at https://github.com/wangtong627/ARTEMIS.
Read the full abstract ▾
All authors Tong Wang, Siwen Wang, Yaolei Qi, Jinxing Zhou, Yuting He, Guanyu Yang, Yutong Xie
Computer Vision
NAMESAKES: Probing Identity Memorization in Text-to-Image Models
Morris Alper, Vasudha Varadarajan, Moran Yanuka et al. (+2 more)
Text-to-image (T2I) models generate realistic likenesses of some individuals when prompted with their names, raising
privacy concerns. However, distinguishing whether a generated face is memorized or fabricated currently requires ground-truth photos, access to training data, or white-box access to model internals, limiting applicability. We introduce a fully black-box behavioral probe that distinguishes between memorized and unrecognized names, while requiring no reference photos or prior knowledge of training data. To
benchmark this task, we present the NAMESAKES
dataset of over one thousand names and faces of public figures spanning a wide range of fame levels, along with perturbed, less famous names. Experiments on state-of-the-art T2I models show that our probe substantially predicts identity memorization and separates memorized from unrecognized names, with further insights into differences across model families.
Read the full abstract ▾
All authors Morris Alper, Vasudha Varadarajan, Moran Yanuka, Angelina Wang, Hadar Averbuch-Elor
Computer Vision
HEad and neCK TumOR (HECKTOR) 2025: Benchmark of Segmentation, Diagnosis, and Prognosis in Multimodal PET/CT
Numan Saeed, Salma Hassan, Shahad Hardan et al. (+27 more)
Head and neck cancers (HNC) represent a significant global health burden, with accurate tumor delineation being essential for effective radiotherapy planning. The complexity of the oropharyngeal anatomy, combined with the heterogeneous appearance of tumors on imaging, makes manual
segmentation time-intensive and subject to inter-observer variability. Beyond
segmentation, predicting long-term clinical outcomes, such as recurrence-free survival (RFS), and determining human papillomavirus (HPV) status from noninvasive imaging, remain challenging yet clinically valuable goals. The HECKTOR 2025 challenge addresses these needs by establishing a comprehensive
benchmark for automated HNC analysis using
multimodal PET/CT imaging and electronic health records. Building on previous editions (2020-2022), this challenge features an expanded multi-institutional
dataset comprising over 1,100 patients from 10 centers worldwide. Participants were tasked with three complementary objectives: (1) segmenting primary gross tumor volumes (GTVp) and metastatic lymph nodes (GTVn), (2) predicting recurrence-free survival, and (3) classifying HPV status. The challenge attracted 35 registered teams, with 15 final submissions evaluated on a held-out test set. Top-performing
algorithms achieved a mean Dice similarity coefficient of 0.75 for
segmentation, a concordance index of 0.66 for survival prediction, and a balanced accuracy of 0.56 for HPV classification. This paper presents a comprehensive analysis of the submitted methodologies, evaluates their performance across different lesion characteristics, and discusses their implications for clinical translation in automated oncology workflows and decision support systems.
Read the full abstract ▾
All authors Numan Saeed, Salma Hassan, Shahad Hardan, Lishan Cai, Xinglong Liang, Moona Mazher, Abdul Qayyum, Yansong Bu, Mengye Lyu, Yue Lin, Mingyuan Meng, Chuanyi Huang, Lisheng Wang, Dalal Chamseddine, Shamimeh Ahrari, Beining Wu, Yifei Chen, Fuyou Mao, Hao Zhang, Baixiang Zhao, Surajit Ray, Muzi Guo, Lei Xiang, Jakob Dexl, Michael Ingrisch, Adrien Depeursinge, Arman Rahmim, Mathieu Hatt, Vincent Andrearczyk, Mohammad Yaqub
Computer Vision
SA-VIS: Sparse frame Annotations for training Video Instance Segmentation
Edoardo Mello Rella, Ajad Chhatkuli, Shipra Jain et al. (+2 more)
Recent online
video instance
segmentation (VIS) methods have achieved impressive results, thus becoming the preferred approach to segment instances in
videos. Despite the resurgence of impressive single image models, the online (or semi-online) VIS approaches outperform single-image models (e.g., based on SAM) by using long sequences of densely annotated frames during training. However,such a training setup of VIS is expensive in the sense of compute as well as dense annotations required. In order to solve these major flaws, we argue that the effective modeling of the instances and their
evolution in
videos do not require densely annotated frames. To that end, we propose a simple and effective module, called Past-frames Feature Propagation (PFP) which aggregates low-dimensional features from the image encoder of multiple frames. This simple low-compute module provides tremendous learning capability in using sparse
video frame labels for end-to-end training. Combined with a light-weight frame-specific Instance Queries, our Sparse frame Annotation VIS (SA-VIS) significantly improves performance over its baseline. Most interestingly, our simple design that avoids complexities effectively bridges the gap in accuracy between training on sparsely and densely annotated
video sequences. This translates to a mere 0.4% drop in performance of SA-VIS when using annotations for only 1/5 of the images in the
dataset. Empirically, SA-VIS shows strong improvements over the baseline on YouTube-VIS 2019/2021/2022 and Occluded VIS (OVIS) and an over 1% improvement in AP on the state-of-the-art in a limited annotations scenario.
Read the full abstract ▾
All authors Edoardo Mello Rella, Ajad Chhatkuli, Shipra Jain, Ender Konukoglu, Luc Van Gool
Computer Vision
TriFlow: Generating Artist-Like 3D Mesh Topology via Nearest-Vertex Vector Fields
Haoxuan Li, Ziya Erkoç, Daniele Sirigatti et al. (+4 more)
We present TriFlow, a new generative approach for producing compact 3D meshes with artist-like triangle
topology directly from input geometry conditions such as signed distance fields. Our key insight is to represent mesh
topology as a nearest-vertex vector field (NVF) defined over the surface, where each point encodes its association to the nearest triangle vertex in the local barycentric frame. We train a latent flow-matching model to synthesize this field, enabling
topology generation conditioned on the input geometry. To extract a coherent mesh, we cluster surface regions using the generated NVF and guide a constrained quadric error metric (QEM) mesh simplification with
topology-aware optimization. This yields output meshes that closely match the input geometry while exhibiting structured, artist-like connectivity. Experiments demonstrate that TriFlow achieves stronger generalization and significantly improved
topology quality compared to state-of-the-art learning-based approaches, alongside 90% lower Chamfer Distance and an 8x speedup.
Read the full abstract ▾
All authors Haoxuan Li, Ziya Erkoç, Daniele Sirigatti, Vladislav Rosov, Lei Li, Angela Dai, Matthias Nießner
Computer Vision
Xuesong Wang
We describe our 4th-place entry to the ICRA 2026 GOOSE 2D Fine-Grained Semantic
Segmentation Challenge, which reached a composite mean Intersection-over-Union (mIoU) of 69.73% on the official 1,815-image test set. Our model adapts the image encoder of a recent visual foundation model, Segment Anything Model 3 (SAM3), with a lightweight decoder. Beyond this, we contribute two techniques and one empirical finding: (i) a self-
distillation scheme that re-uses SAM3 itself, prompted with ground-truth boxes, as a teacher on the classes where it outperforms our own model; (ii) an image-level multi-scale test-time augmentation scheme that restores multi-scale inference for a fixed-input-size model by rescaling the image rather than the model input; and (iii) the finding that an aggressive photometric distortion from a winning 2025 GOOSE 2D entry, transplanted onto our pipeline, is its single largest source of improvement.
Read the full abstract ▾
Computer Vision · Cross-listed from cs.LG
When Average Calibration Fails: Site-Conditional Federated Conformal Risk Control
Nafis Fuad Shahid
Conformal risk control (CRC) provides distribution-free
segmentation guarantees by calibrating a prediction-set threshold on held-out data. In
federated deployments, the standard approach pools calibration scores into a single threshold. We quantify, on real multi-institutional
brain tumor data (FeTS-2022, 1,251 subjects, 20 institutions), a critical failure: naive pooled CRC protects the average hospital but violates coverage at 40% of individual institutions, with the worst site exceeding the target false-negative rate by 7.8 percentage points. We trace this failure to a hidden design choice: the aggregation weights implicitly determine whose coverage is protected. Sample-size weighting optimizes patient-level validity but can sacrifice institution-level reliability; equal-site weighting improves institution-level reliability on this
benchmark at comparable efficiency, using only a single scalar per site. We propose risk-curve shrinkage as a principled mechanism: each site transmits its empirical risk curve (G scalars) and a single hyperparameter n0 smoothly interpolates between site-specific local calibration and sample-size-weighted pooled calibration. Leave-one-site-out sensitivity analysis identifies n0=19, achieving 2.7/20 violations at 2.0x stretch. Direct Lagrangian budget optimization fails by concentrating risk on vulnerable hospitals; the finite-sample correction term is essential: removing it triples violations. No patient-level images, masks, or per-volume scores leave any site.
Read the full abstract ▾
Computer Vision
Pixel-Level Residual Diffusion Transformer: Scalable 3D CT Volume Generation
Zhenkai Zhang, Markus Hiller, Krista A. Ehinger et al. (+1 more)
Generating high-resolution 3D CT volumes with fine details remains challenging due to substantial computational demands and optimization difficulties inherent to existing generative models. In this paper, we propose the Pixel-Level Residual
Diffusion Transformer (PRDiT), a scalable generative framework that synthesizes high-quality 3D medical volumes directly at voxel-level. PRDiT introduces a two-stage training architecture comprising 1) a local denoiser in the form of an MLP-based blind
estimator operating on overlapping 3D patches to separate low-frequency structures efficiently, and 2) a global residual
diffusion transformer employing
memory-efficient
attention to model and refine high-frequency residuals across entire volumes. This coarse-to-fine modeling strategy simplifies optimization, enhances training stability, and effectively preserves subtle structures without the limitations of an autoencoder bottleneck. Extensive experiments conducted on the LIDC-IDRI and RAD-ChestCT
datasets demonstrate that PRDiT consistently outperforms state-of-the-art models, such as HA-GAN, 3D LDM and WDM-3D, achieving significantly lower 3D FID, MMD and Wasserstein distance scores.
Read the full abstract ▾
All authors Zhenkai Zhang, Markus Hiller, Krista A. Ehinger, Tom Drummond
Computer Vision
FrozenDrive: Zero-Shot Text-Guided Driving Scene Generation and Data Augmentation with Parameter-Free Frozen Diffusion Model
Yuhwan Jeong, Hyeonseong Kim, Daehyun We et al. (+5 more)
Synthetic data for autonomous driving is surging, powered by
diffusion models that promise scalable scene generation. Yet key obstacles remain, as enforcing multi-view and temporal consistency often relies on backbone fine-tuning or added layers, which erodes pre-trained knowledge and weakens text
alignment. Models also stay close to the training distribution, struggling under adverse weather and unseen configurations, and fidelity favors frequent over rare classes. We address these gaps with FrozenDrive, a controllable generative framework that preserves a pretrained
diffusion models knowledge while achieving strong consistency. FrozenDrive conditions on rich driving-stack signals and text
prompts, and introduces knowledge-preserving spatio-temporal
attention to impose cross-view
alignment and temporal coherence in a single pass within a parameter-free frozen
diffusion backbone. An additional object-focused constraint improves per-object fidelity for rare categories. Without any weather- or scene-specific fine-tuning, our model synthesizes globally coherent multi-view driving scenes from text, particularly under adverse and rare conditions, and surpasses prior baselines. On nuScenes, FrozenDrive augmented data significantly improves AD models performance, especially at night and in rain, demonstrating stronger robustness when trained with our scenario-targeted data.
Read the full abstract ▾
All authors Yuhwan Jeong, Hyeonseong Kim, Daehyun We, Seonkyu Song, Jinnyeong Yang, Hyun-Kurl Jang, Youngho Yoon, Kuk-Jin Yoon
Computer Vision
EFIQA: Explainable Fundus Image Quality Assessment via Anatomical Priors
Pengwei Wang, José Morano, Qian Wan et al. (+1 more)
Image quality control is vital for a wide range of downstream applications. Deep learning-based image quality assessment methods typically train classifiers on
dataset-specific quality labels, inheriting two limitations: (1) generalization is tied to the labeling criteria of the training set and (2) these methods cannot provide spatial feedback on where the quality is degraded, lacking explainability. In this work, we propose EFIQA, a framework that requires no quality-related supervision and produces spatial quality maps by design. Rather than learning “what is degradation" from human-annotated labels, EFIQA learns “what should be there" by leveraging anatomical priors. For fundus photography, we instantiate this as a two-stage approach, by first training an unsupervised anomaly detector via masked anatomical inpainting to identify regions of missing vasculature, and then distilling this prior knowledge into a shallow adapter mapping features of a frozen foundation model to precise quality maps. External-
dataset evaluation demonstrates that this label-free approach with minimal adaptation achieves better performance and explainability compared with supervised methods across
benchmarks with different quality criteria, highlighting its potential for real-world applications.
Read the full abstract ▾
All authors Pengwei Wang, José Morano, Qian Wan, Hrvoje Bogunović
Computer Vision
Geometry-Preserving in 3D Gaussian Splatting for LiDAR-Camera Extrinsic Calibration
Kyoleen Kwak, Daeho Kim, Jeong Woon Lee et al. (+1 more)
Accurate
LiDAR-camera calibration is essential for robust multi-modal perception. Targetless approaches avoid manual setup but remain limited by the scarcity of discriminative cross-modal features. Recent methods address this by reconstructing the scene within a differentiable model, enabling extrinsic optimization through dense photometric supervision. Among these, 3D Gaussian Splatting (3DGS) has been widely adopted as a
geometric proxy that bridges
LiDAR and camera within a single differentiable framework. However, since 3DGS was originally designed for novel view synthesis, existing methods tend to prioritize rendering quality, causing the proxy geometry to drift from the true
LiDAR structure. We propose a framework that preserves the metric geometry of the Gaussian proxy by aggregating multi-view
LiDAR observations for dense depth supervision and blocking photometric gradients from updating the Gaussian spatial parameters. We validate our method on public driving
datasets, where it consistently outperforms existing targetless methods in calibration accuracy.
Read the full abstract ▾
All authors Kyoleen Kwak, Daeho Kim, Jeong Woon Lee, Hyoseok Hwang
Computer Vision
WeGenBench: A Multidimensional Diagnostic Benchmark towards Text-to-Image Model Optimization
Qian Liang, Xiaomin Li, Ying Zhang et al. (+6 more)
Recent text-to-image generation models have demonstrated remarkable capabilities in synthesizing highly realistic images from text inputs alone. Although existing
benchmarks can evaluate the generation capabilities of various models to some extent, they struggle to comprehensively and accurately measure performance across multiple dimensions, often failing to reveal the inherent deficiencies of models in specific categories. To address these limitations, we propose WeGenBench, a novel
benchmark designed for the comprehensive, multi-perspective evaluation of text-to-image generation capabilities. Our
benchmark comprises a total of 4,000 test
prompts across two primary categories, meticulously balanced between Chinese and English to evaluate bilingual and cross-cultural generation capabilities. Beyond macroscopic scene classification, we annotate each
prompt with multi-dimensional tags tailored to the distinct content and challenges of each
language, thereby refining the generation tasks into more specific sub-categories. Through a cross-dimensional evaluation mechanism leveraging both scene classifications and multi-dimensional tags, WeGenBench can precisely pinpoint model shortcomings in specific generation categories. Furthermore, to measure generation quality more accurately, we design and validate several novel evaluation metrics by integrating
Vision-
Language Models (VLMs), which assess model performance on domain-specific tasks from three core aspects. Crucially, our approach yields both the assessment outcomes and the detailed
reasoning trajectories, facilitating a rigorous verification of the accuracy and soundness of the evaluation results. Finally, we conduct systematic benchmarking on current state-of-the-art methods and provide an in-depth analysis of the limitations present in existing models.
Read the full abstract ▾
All authors Qian Liang, Xiaomin Li, Ying Zhang, Jia Xu, Lihao Ni, Hongrui Li, Jingjing Li, Jing Lyu, Chen Li
Computer Vision
Stitching and dimensionality effects on large artificially generated volume datasets
Lucas von Chamier, Jan Philipp Albrecht and Dagmar Kainmüller
Generating large images via deep learning requires patching input data to accommodate hardware
memory limitations, then assembling output patches, a process that can introduce stitching artifacts when neighboring patches do not align at borders. While these artifacts are known to affect
segmentation tasks, their impact on generative models for style-transfer remains poorly understood. We investigated three stitching approaches and two patch dimensionalities (2D vs 3D) using cycleGAN models trained on cryo-electron microscopy
datasets. We evaluated both perceptual quality and performance on downstream mitochondria
segmentation. Our key findings reveal that: (1) FID scores fail to detect subtle stitching artifacts that significantly impact downstream
segmentation performance, (2) 3D models with artifact-free stitching marginally outperform 2D models on downstream tasks, though the improvement barely justifies the computational cost, and (3) 2D models train more stably due to larger batch sizes. Additionally, we demonstrate that ensembling predictions from three orthogonal directions can improve low-quality volumes but provides no benefit for high-quality outputs. These results demonstrate that maximizing generative model performance on large scientific
datasets requires careful consideration and mitigation of stitching artifacts, and that perceptual metrics alone are insufficient for evaluating domain adaptation quality in biomedical imaging.
Read the full abstract ▾
Computer Vision
MakeupMirror: Improving Facial Attribute Preservation in Diffusion Models for Makeup Transfer
Nefeli Andreou, Angel Martínez-González, Sabine Sternig et al. (+3 more)
Makeup transfer models enable fun augmented reality (AR) experiences as well as virtual try-on (VTO) for online makeup shopping. While recent state-of-the-art
diffusion based solutions such as Stable-Makeup dramatically improve the accuracy and realism of makeup transfer, they still face limitations in identity and skin color preservation, making production-level VTO for makeup shopping unrealistic. In this work, we propose MakeupMirror, a
diffusion-based approach to makeup transfer that makes significant progress towards preserving facial features and skin tone. We introduce several technical innovations over Stable-Makeup: (1) integration of facial geometry conditioning with ControlNets to maintain facial fidelity; (2) region-specific makeup transfer control to enable precise makeup application across facial regions such as skin, eyes and lips; (3) skin tone-based makeup transfer modulation that prevent skin tone alteration in cross-subject transfer scenarios; and (4) integration of a Levenberg-Marquardt Langevin sampler to speed up inference while maintaining generation quality. Our experiments on CPM-Real, Makeup Wild, and (herein newly collected, more diverse) MakeupSelfies
datasets show that MakeupMirror improves relative facial recognition similarity by +60%, reduces relative skin tone difference by -50% over Stable-Makeup, with a latency of 0.7s, while achieving expert acceptance rate of 94% across core facial identity preservation criteria.
Read the full abstract ▾
All authors Nefeli Andreou, Angel Martínez-González, Sabine Sternig, Matthieu Guillaumin, Epameinondas Antonakos, Michael Opitz
Computer Vision
EventVLA: Event-Driven Visual Evidence Memory for Long-Horizon Vision-Language-Action Policies
Ganlin Yang, Zhangzheng Tu, Yuqiang Yang et al. (+10 more)
Memory remains a critical bottleneck for long-horizon robotic manipulation, as standard
Vision-
Language-Action (VLA) policies often fail when task-relevant cues become occluded or unobservable over time. While existing
memory-augmented methods utilize historical context, they either suffer from severe information bottlenecks, incur high latency via decoupled dual systems, or rely on unselective buffers that accumulate massive visual redundancies. To address these limitations, we introduce EventVLA, an end-to-end framework founded on the concept of sparse visual evidence
memory that comprises two core components: foundational visual anchors to retain initial and short-term contexts, and a dynamic Keyframe Evidence
Memory (KEM) module. Specifically, KEM directly predicts future keyframe probabilities from the VLA's latent
embeddings to autonomously capture and store sparse, task-critical visual events. This foresight-driven mechanism empowers the policy to dynamically evaluate the future causal utility of current observations, preserving transient visual evidence before it becomes unobservable. Furthermore, we propose RoboTwin-MeM, a diagnostic
benchmark specifically designed to evaluate non-Markovian manipulation tasks with interactive visual evidence. Extensive evaluations show that across 17
memory-requiring simulation tasks and 4 real-world bimanual tasks, EventVLA achieves an average success rate improvement of +40% over state-of-the-art
memory-augmented VLAs.
Read the full abstract ▾
All authors Ganlin Yang, Zhangzheng Tu, Yuqiang Yang, Sitong Mao, Junyi Dong, Tianxing Chen, Jiaqi Peng, Jing Xiong, Jiafei Cao, Jifeng Dai, Wengang Zhou, Yao Mu, Tai Wang
Computer Vision
Holo-World: Unified Camera, Object and Weather Control for Video World Model
Xiangchen Yin, Wenzhang Sun, Jiahui Yuan et al. (+6 more)
Video world models are moving toward preserving an observed world under controllable camera and object motion while allowing its environmental state to change. Yet these controls remain isolated, and weather generation typically relies on a source
video or reconstructed scene that already specifies future structure. We study a first-frame-anchored source-to-state setting, where the model starts from a single image and follows explicit camera and object controls and an optional weather instruction, then generates a
video that either preserves the source world or transfers it to a target weather state. To address these challenges, we first build HoloStateData, a state
video dataset that turns diverse
videos into unified control samples for camera, object, and weather supervision. Second, we introduce Holo-World, a unified controllable
video world model that jointly controls the scene from a single image. Its Unified Scene Adapter factorizes world preservation and weather transfer into distinct parameter subspaces, using rendered background, geometry buffers, and object controls to maintain controlled scene structure while modeling weather-dependent appearance and particle effects. Additionally, Scene-Weather Decomposed CFG guides scene and weather residuals separately, strengthening target weather effects without over-amplifying the full condition. Quantitative and qualitative experiments demonstrate that Holo-World maintains precise camera and object controls with consistent scene structure while transferring scenes into diverse target weather states, outperforming
video-to-
video weather editing baselines on weather-state generation. Our project page is available at https://xiangchenyin.github.io/Holo-World/.
Read the full abstract ▾
All authors Xiangchen Yin, Wenzhang Sun, Jiahui Yuan, Zijie Liu, Yinda Chen, Wei Li, Dachun Kai, Chunfeng Wang, Xiaoyan Sun
Computer Vision
The Hidden Evolution of Disguised Visual Context inside the VLM
Wish Suharitdamrong, Tony Alex, Xiatian Zhu et al. (+2 more)
Visual
tokens enter Large
Language Models (LLMs) as raw, foreign signals. How they are transformed into meaningful representations and interact with the
language space depends entirely on the integration architecture. Whether by treating visual
tokens as in-context
prompts within the input sequence or injecting them directly into the LLM's intermediate layers. A controlled comparison and understanding of how these architectural choices affect visual information and its internal transformation to integrate with the LLM remains underexplored. We provide a fair comparison by evaluating in-context and layer-wise injection VLM integration paradigms under identical training conditions across single image, multi-image, and
video benchmarks. In doing so, we uncover a hidden
evolution where visual
tokens enter the LLM as disguised visual context, raw representations lacking linguistic structure, but are progressively reshaped depending on the integration paradigm, each capturing fundamentally different frequency characteristics of the visual signal. We show that this
evolution inside the LLM determines what visual features the VLM can utilize effectively, how visual representations align with the
language space, and ultimately how each paradigm performs across different tasks. We further demonstrate that
attention allocation alone is insufficient, and that performance is driven by the quality of visual representations at each layer.
Read the full abstract ▾
All authors Wish Suharitdamrong, Tony Alex, Xiatian Zhu, Muhammad Awais, Sara Atito
Computer Vision
Variable-Length Tokenization via Learnable Global Merging for Diffusion Transformers
Dong Hoon Lee and Seunghoon Hong
Latent
Diffusion Models (LDMs) have become dominant in visual synthesis, but their quality-compute trade-off is largely constrained by the tokenizer's fixed compression ratio. Variable-length tokenizers (VLTs) promise adaptive compression by varying
token counts, allowing
diffusion models to flexibly balance quality and compute. However, conventional VLTs modulate length by truncating ordered
token sequences, which makes
token semantics depend on
token position and breaks representational
alignment across lengths. This leads to a cross-length shift in the latent distribution that hinders a single variable-length
diffusion model from operating effectively. To address this, we propose a novel variable-length tokenizer that modulates length by merging
tokens. We show that encouraging similar
tokens to merge enables direct cross-length representation
alignment when the
diffusion transformer operates according to the merging pattern. Since conventional merging methods are data-dependent, making the merging pattern inaccessible during generation, we introduce learnable global merging, which is data-independent, to ensure compatibility with
diffusion transformers. On ImageNet 256$\times$256 generation, our merging-based variable-length tokenizer integrated with a
diffusion transformer achieves a superior gFID-compute trade-off compared to prior VLT methods. Code is available at [this https URL](https://github.com/movinghoon/lgm)
Read the full abstract ▾
Computer Vision
Fanfu Xue, En Yu, Yantian Shen et al. (+5 more)
UAV Vision-
Language Navigation (
UAV-VLN) is typically formulated as a holistic search-and-reach problem, where long-range target discovery and final target approach are optimized and evaluated jointly. This formulation makes it difficult to assess a critical capability of aerial
embodied agents, namely whether a
UAV can accurately ground a visible target and translate
vision-
language evidence into precise 3D motion once the target enters its field of view. To address this limitation, we introduce
UAV-VLN-FOV, a target-visible
navigation task that isolates the see-and-reach stage and enables a more diagnostic evaluation of terminal reaching ability. We further propose 3DG-VLN, a
vision-
language waypoint prediction framework guided by dynamic 3D direction cues to enhance fine-grained visual grounding and spatial direction
alignment for precise target reaching. Specifically, 3DG-VLN adaptively processes high-resolution front-view and downward-view observations to preserve fine-grained visual and
geometric details for target grounding. It also updates the target-relative direction online during closed-loop
navigation, allowing the
agent to maintain spatial
alignment with the target and reduce accumulated direction drift. To support this task, we construct a dedicated high-resolution
benchmark which contains 2,717 trajectories with target-oriented high-level instructions, high-resolution front-view and downward-view
egocentric observations, and continuous 3D waypoint annotations. Experiments show that 3DG-VLN outperforms competitive
UAV-VLN baselines, achieving a 13.82% improvement in success rate. Real-world trials further demonstrate the potential of 3DG-VLN for practical see-and-reach
navigation. The source code and
benchmark are available at https://github.com/xuefanfu/3DG-VLN.
Read the full abstract ▾
All authors Fanfu Xue, En Yu, Yantian Shen, Zhikun Hu, Hongjun Wang, Yang Yang, Xindi Wang, Jiande Sun
Computer Vision
FUSE: Frequency-domain Unification and Spectral Energy Alignment for Multi-modal Object Re-Identification
Xuanhao Qi, Tom H. Luan, Yukang Zhang et al. (+4 more)
Despite significant progress in multi-modal Re-Identification (ReID), existing methods tend to emphasize low-frequency cues. Consequently, they focus on attributes such as color, illumination, and coarse appearance, while overlooking mid and high-frequency structures that encode
geometric, textural, and identity-discriminative details. This imbalance leads to incomplete spectral representations and unstable cross-modal
alignment. To overcome these limitations, we introduce FUSE, a frequency-domain framework that reformulates multi-modal ReID as a two-stage process of spectral disentanglement and energy
alignment. The proposed Spectral Decomposition Module (SDM) adaptively partitions features into low, mid, and high-frequency subspaces, enabling hierarchical spectral modeling. The Cross-Modal
Alignment Module (CAM) further enforces energy
alignment and subspace complementarity across modalities via frequency-consistency regularization. In addition, FUSE incorporates learnable frequency modulation to enhance robustness under varying illumination and heterogeneous sensor conditions. Extensive experiments on RGBNT201, RGBNT100, and MSVR310 show that FUSE achieves 9.1% mAP and 9.5% Rank-1 improvements, establishing an interpretable frequency-domain paradigm for multi-modal representation learning.
Read the full abstract ▾
All authors Xuanhao Qi, Tom H. Luan, Yukang Zhang, Jinkai Zheng, Zhou Su, Shuwei Li, Lei Tan
Computer Vision
PU-UNet: Stable Multiplicative Interactions for Medical Image Segmentation
Ziyuan Li, Osamah Sufyan, Uwe Jaekel et al. (+1 more)
Many dense prediction networks rely on additive feature transformations and model higher-order feature interactions only implicitly. Product units provide an explicit mechanism for multiplicative feature modeling, but their logarithmic–exponential formulation can cause numerical instability, which has limited their use in deep dense prediction networks. In this work, we propose Product-Unit U-Net (PU-UNet), a residual U-Net that integrates stable product-unit residual blocks into rich low-resolution stages for medical image
segmentation. The proposed formulation combines smooth positivity mapping with log-domain clipping, enabling stable multiplicative feature learning with negligible computational overhead. On ISIC 2018, Kvasir-SEG, and BUSI, PU-UNet achieves Dice scores of 0.942, 0.959, and up to 0.925, respectively. Compared with a matched Residual U-Net baseline, PU-UNet consistently improves Dice and IoU while keeping parameters, FLOPs, and inference latency nearly unchanged, and reduces the image-level false-positive rate on normal BUSI cases from 0.077 to zero. Ablation studies suggest that the gains are associated with product-unit interactions, are strongest under low-resolution placement, and benefit from the proposed stabilization design. These results suggest that stable product-unit residual learning can be an effective way to enhance U-Net-style
segmentation networks with explicit multiplicative interactions.
Read the full abstract ▾
All authors Ziyuan Li, Osamah Sufyan, Uwe Jaekel, Babette Dellen
Computer Vision
ReA-OVCD: Training-Free Open-Vocabulary Change Detection via Semantic-Spatial Reliability Assessment
Hongming Zhu, Huaji Chen, Bowen Du et al. (+2 more)
Unlike traditional remote sensing change detection that relies on predefined categories, Open-Vocabulary Change Detection (OVCD) identifies land cover changes flexibly using arbitrary text
prompts. However, most existing OVCD methods rely on instance-level matching for stable correspondence but may overlook fine-grained variations (e.g., partial building extensions). Dense pixel-level comparison is more flexible, yet direct semantic comparison often produces unreliable candidate changes due to semantic ambiguity and spatial inconsistency. To this end, we propose ReA-OVCD, an efficient training-free framework that revisits pixel-level OVCD from a reliability assessment perspective. It first derives candidate change regions from pixel-wise semantic discrepancies to retain flexible localization. Instead of directly trusting these candidates, ReA-OVCD applies a two-stage semantic-spatial reliability assessment. The semantic stage evaluates whether a label discrepancy is supported by meaningful distributional and response-level changes, while the spatial stage validates whether a candidate region contains stable interior evidence rather than only boundary-induced responses. Extensive experiments across LEVIR-CD, WHU-CD, DSIFN, and SECOND show that the proposed framework improves the reliability of pixel-level OVCD and consistently outperforms state-of-the-art approaches, achieving $\mathrm{F}_{1}^{C}$ improvements of 3.54% to 8.45% while maintaining superior computational efficiency. The code is available at \href{https://github.com/Funny0101/ReA-OVCD}{https://github.com/Funny0101/ReA-OVCD}.
Read the full abstract ▾
All authors Hongming Zhu, Huaji Chen, Bowen Du, Sicong Liu, Qin Liu
Computer Vision
QG-MIL: A Gated Transformer Aggregator for Domain-Agnostic Multiple Instance Learning in Medical Imaging
Luca Zedda, Davide Antonio Mura, Cecilia Di Ruberto et al. (+4 more)
Attention-based Multiple Instance Learning aggregators in medical imaging are prone to
attention concentration, producing overconfident and unstable predictions. We introduce QG-MIL, a gated
transformer aggregator that addresses this through four synergistic architectural components: RMSNorm-based pre-normalization, per-head QK normalization, fine-grained
attention output gating, and SwiGLU-style feed-forward modules. Together, these design choices stabilize training and distribute
attention more uniformly across instances without auxiliary losses, masking, or multi-stage regularization. We evaluate QG-MIL across six
benchmarks spanning whole-slide pathology and
cell-level hematology, covering two fundamentally different MIL scales. The best-performing QG-MIL variants outperform leading baselines on all six
benchmarks, with an average improvement of +6.1 mean macro F1 points.
Attention overlays and
attention mass analysis confirm more distributed instance weighting. Ablation studies show that while individual components can match the full model on specific
datasets, the QG-MIL design provides the most consistent cross-domain performance and tightest variance when compared to selected baselines. We release a configurable implementation to support reproducibility at: https://github.com/unica-visual-intelligence-lab/QG-MIL
Read the full abstract ▾
All authors Luca Zedda, Davide Antonio Mura, Cecilia Di Ruberto, Maurizio Atzori, Muhammed Furkan Dasdelen, Carsten Marr, Andrea Loddo
Computer Vision · Cross-listed from cs.RO
Tri-Info: Generalizable, Interpretable Failure Prediction for VLA Models via Information Theory
Jinghan Yang, Yunchao Zhang, Wang Yuan et al. (+4 more)
Vision-
Language-Action (VLA) models are increasingly deployed across diverse tasks, yet they remain black boxes whose physical interactions can cause irreversible harm, making generalizable and interpretable failure detection essential. We observe that successful and failed rollouts carry systematically different information-theoretic signatures. Building on this, we formalize VLA control as a closed-loop information pipeline and derive the Triple Information-theoretic (Tri-Info) signals that capture whether actions remain diverse, temporally consistent, and coupled to state transitions. Across six VLA models and three
benchmark environments, Tri-Info matches the strongest baselines in-domain. Moreover, Tri-Info transfers across architectures, environments, and the sim-to-real gap without retraining with labeled data, reaching 70% accuracy on real-world tasks. This establishes Tri-Info as a simple yet powerful method that not only detects failures with strong cross-domain generalization, but also delivers interpretable diagnostics of the underlying failure modes.
Read the full abstract ▾
All authors Jinghan Yang, Yunchao Zhang, Wang Yuan, Haolun Wan, Jiaming Zhang, Zhengyang Hu, Yanchao Yang
Computer Vision
Vision-Reasoning-Guided Occlusion Removal from Light Fields
Mohamed Youssef and Oliver Bimber
Occlusion-robust scene recovery remains a major challenge in computational imaging, particularly where dense vegetation severely limits visibility. We propose a visionreasoning-guided light field occlusion removal framework combining light field integration (LFI) with
vision-
language model (VLM) semantic
reasoning. Multi-view observations are first integrated via LFI to suppress foreground occlusions, producing an initial visibility-enhanced representation, a VLM then acts as a conditional semantic prior to restore degraded structures and fine details. A multi-sample fusion strategy aggregates multiple generated hypotheses to improve consistency and reduce
hallucination. Experimental results on synthetic and real-world
datasets show state-of-the-art performance, achieving the highest average SSIM across four synthetic
benchmark scenes (4-Syn) and strong generalization across structured and unstructured acquisition settings, with applicability to search-and-rescue and exploratory robotic
navigation.
Read the full abstract ▾
Computer Vision
CrossFlow: One-Step Generation Across Latent and Pixel Spaces
Xiyuan Wang, Xiao Zhang, Yang Li et al. (+4 more)
Most
diffusion and flow-matching generators define the prior, probability path, and prediction target in the same representation space. Latent
diffusion improves efficiency by moving this path into an autoencoder latent space, but the final sample is still produced by a separately trained decoder. This separation creates a mismatch: the generator is optimized for latent-space prediction, while final quality depends on how the decoder handles generated latents that may differ from clean encoder outputs. We introduce CrossFlow, a cross-space flow formulation that maps noisy latent inputs directly to pixel-space images. The key technical step is a velocity-free one-step objective: the latent trajectory defines the training path, but the supervised prediction is an image rather than a latent displacement. This lets one model act both as a one-step latent-to-pixel generator and as a decoder replacement for latent
diffusion pipelines. On class-conditional ImageNet-1k at $256\times256$, CrossFlow-XL achieves 1.62 FID with one function evaluation. Ablations show that the latent encoder and pixel-space perceptual and
adversarial losses are important for fidelity. These results indicate that cross-space flow objectives can combine the efficiency of latent representations with direct pixel-space supervision, without requiring a separate decoder at inference.
Read the full abstract ▾
All authors Xiyuan Wang, Xiao Zhang, Yang Li, Ruoxi Jiang, Zhao Zhong, Liefeng Bo, Muhan Zhang