cs.CV · 2026-06-24 · No. 33
Computer Vision and Pattern Recognition, 2026-06-24.
24 new papers in cs.CV. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
24 entries-
01
FLUX3D: High-Fidelity 3D Gaussian Generation with Diffusion-Aligned Sparse Representation
Haorui Ji, Weizhe Liu, Hongdong Li, Hengkai Guo
cs.CV · cs.AI
Sparse voxel representation has emerged as a scalable foundation for image-to-3D Gaussian Splatting (3DGS) generation, yet current methods struggle to preserve high-frequency visual details of input images due to two structural bottlenecks. First, they adopt discriminative 2D features optimized for semantic abstraction to construct sparse voxel latents, which suppress reconstructive cues and induce a representation bottleneck. Second, in the...
-
02
IV-CoT: Implicit Visual Chain-of-Thought for Structure-Aware Text-to-Image Generation
Zixuan Li, Haokun Lin, Yicheng Xiao, Zhiwei Li, Xinyang Song, Zelong Zheng, Yong He, Heng Yao, Ke Ding, Chao Yu,...
cs.CV · cs.AI
Unified multi-modal large language models (MLLMs) have achieved strong text-to-image generation quality, but still struggle with structure-aware prompt following, where object counts, spatial relations, attribute bindings, and coarse layouts must be preserved. We attribute this limitation in part to the entanglement of structural planning and appearance rendering within a single conditioning stream. To address this issue, we propose Implicit...
-
03
OrbitForge: Text-to-3D Scene Generation via Reconstruction-Anchored Video Synthesis
Chenrui Fan, Paolo Favaro
cs.CV · cs.AI
Generic text-to-video models can be used as rich open-world scene priors. Despite the high quality of today's generated videos, they do not directly yield reliable 3D assets: camera motion is difficult to control, view coverage is partial, and frames often contain inconsistencies across time. We introduce OrbitForge, an adapter built from frozen video priors and per-prompt Gaussian Splatting reconstruction optimization that converts a single...
-
04
EG-VQA: Benchmarking Verifiable Video Question Answering with Grounded Temporal Evidence
Linpeng Huang, Weixing Chen, Zexin Chen, Yang Liu, Liang Lin
cs.CV · cs.AI
Recent advances in Video Large Language Models (Video-LLMs) have yielded promising performance on video question answering (VideoQA). Nevertheless, existing benchmarks are predominantly evaluated through answer correctness, while the grounding of predictions in relevant video evidence remains largely unexamined. This disconnect between answer generation and evidence understanding motivates the construction of the Evidence-Grounded Video...
-
05
UniDrive: A Unified Vision-Language and Grounding Framework for Interpretable Risk Understanding in Autonomous Driving
Xiaowei Gao, Pengxiang Li, Yitai Cheng, Ruihan Xu, James Haworth, Stephen Law, Yun Ye
cs.CV · cs.AI
Recent multimodal large language models (MLLMs) have shown strong potential for autonomous driving scene understanding, yet existing methods still face a fundamental trade-off between temporal reasoning and spatial precision. Models that rely on single-frame or low-resolution inputs often miss small, distant, or partially occluded hazards, while language-centric driving models frequently provide limited grounded evidence for their...
-
06
Evaluating the Interpretability of Sparse Autoencoders with Concept Annotations
Jonas Klotz, Cassio F. Dantas, Pallavi Jain, Diego Marcos, Begüm Demir
cs.CV · cs.AI
Sparse autoencoders (SAEs) are increasingly used to extract interpretable concepts from vision and vision language models, yet existing evaluation methods largely rely on proxy metrics or qualitative inspection rather than measuring semantic correspondence. We present a human-grounded evaluation framework that quantifies alignment between SAE latents and human-annotated concepts, without requiring user studies, and validate this matching...
-
07
EERLoss: A Novel Loss Function for Training Deep Biometric Models. A Case Study in Keystroke Dynamics
Nahuel Gonzalez, Marta Robledo-Moreno, Ivan DeAndres-Tame, Ruben Vera-Rodriguez, Ruben Tolosana
cs.CV · cs.LG
Deep learning approaches to biometric verification are commonly trained by optimizing indirect objectives, creating a misalignment between the optimization process and the primary evaluation metric, typically the Equal Error Rate (EER). This paper introduces EERLoss: a subdifferentiable, arbitrarily accurate approximation to EER for training deep biometric models. Furthermore, this framework has the potential to be adapted to optimize any...
-
08
RetiSEM: Generalising Causal Models for Fragmented Biomedical Data
Inam Ullah, Imran Razzak, Shoaib Jameel
cs.CV · cs.AI · stat.ME
Learning causal models from fragmented biomedical data is challenging because clinical, molecular, and imaging variables are often incomplete or not jointly observed. We propose RetiSEM, a domain-constrained structural equation modelling (SEM) framework for causal graph recovery and mediation analysis under limited multimodal resources. This proposed work organises variables into biologically informed blocks, applies forbidden-edge...
-
09
video-SALMONN-R$^3$: Learning to ReWatch, ReAsk, and ReAnswer for Efficient Video Understanding
Yixuan Li, Guangzhi Sun, Yudong Yang, Wei Li, Zejun MA, Chao Zhang
cs.CV · cs.AI · cs.SD
Video large language models (LLMs) are often constrained by computation and memory budgets, leading them to use reduced frame rates and spatial resolutions, which may cause them to miss critical information for question answering (QA). A practical and efficient solution is a two-stage paradigm: first perform coarse video understanding to localize relevant segments, and then re-watch these segments at higher temporal or spatial fidelity. In...
-
10
MedPCFM: Improving Medical Point Cloud Completion by Integrating Point Transformers and Flow Matching
Kamil Kwarciak, Marek Wodzinski
cs.CV · cs.AI · cs.LG
Medical point cloud completion is important for anatomical reconstruction and downstream clinical workflows, yet generative modeling in this setting remains insufficiently studied. We investigate completion through continuous-time generative modeling and introduce PCFM, a PTv3-backed flow matching approach for medical point cloud completion. We evaluate on SkullFix and SkullBreak, and additionally on the more recent Mandibular Defect dataset....
-
11
Transformation Behavior of Images in Latent Space
Christian Zöllner, Mozzam Motiwala, Aysel Ahadova, Gerrit Anders, Robert Hüneburg, Jacob Nattermann, Matthias Kloor
cs.CV · cs.AI
Training of neural networks for histopathology classification tasks typically relies on data encoding into latent space, which reduces complexity and improves performance. There are several encoder networks available, either pretrained on general image datasets such as ImageNET, or specifically on histopathological images. Training of encoder networks should be adapted to downstream tasks, allowing encoding of biologic/diagnostic content...
-
12
Structural Kolmogorov-Arnold Convolutions: Learnable Function on the Values or the Filter Shape as Parameter-Efficient Alternative to Per-Edge Convolutional KANs
Stefano Mereu, Oleksandr Kuznetsov, Gabriele Marchello, Alessandro Galdelli, Emanuele Frontoni, Adriano Mancini,...
cs.CV · cs.AI
Convolutional Kolmogorov--Arnold Networks (KANs) replace the fixed weights of a convolutional kernel with learnable univariate functions. The dominant formulation attaches one such function to every kernel entry and lets it act on pixel values, expressive but parameter-heavy and prone to overfitting. We argue that the learnable functions are better placed in the \emph{structure} of the convolution than on each edge, and we organise the design...
-
13
Open-Vocabulary BEV Segmentation with 3D-Aware Geometric Constraints
Hojun Choi, Seulbin Hwang, Dae Jung Kim, Kisung Kim, Hyunjung Shim, Jinhan Lee
cs.CV · cs.LG
Bird's-eye view (BEV) perception fuses multi-camera images into a unified top-down representation for autonomous driving. Despite recent progress, state-of-the-art methods remain confined to closed-set scenarios, making them vulnerable to unpredictable real-world environments. In this work, we introduce open-vocabulary BEV segmentation (OVBS), which leverages vision-language models (VLMs) to recognize categories beyond the training set while...
-
14
MotifGen: Spatiotemporal interpolation of misaligned satellite images via multi-source generative modeling, in an application to tropical cyclones
Clément Dauvilliers, Claire Monteleoni
cs.CV · cs.LG
Microwave satellite imagery plays a crucial role in monitoring tropical cyclone precipitation and intensity worldwide, but suffers from long revisit times, potentially missing rapid storm evolution phases. While this raises the need for an interpolation method, it is made challenging by the high level of heterogeneity of microwave data coming from different instruments. In this work, we introduce the first generative model that can be applied...
-
15
Social Structure Matters in 3D Human-Human Interaction Generation
Zhongju Wang, Beier Wang, Yatao Bian, Pichao Wang, Zhi Wang, Daoyi Dong, Hongdong Li, Huadong Mo, Zhenhong Sun
cs.CV · cs.AI
Although text-to-motion generation has achieved strong progress in synthesizing realistic single-person motions from language, extending it to text-driven 3D human-human interaction (HHI) remains non-trivial, as HHI requires modeling the underlying \textbf{social structure} that governs phase progression, actor roles, and inter-actor coordination. In this paper, we formulate HHI generation as a social structure modeling and grounding problem:...
-
16
Inclusive Interactive Collisions for Multi-View Consistent Compositional 3D Generation
Chang Liu, Mingwen Shao, Xiang Lv, Xinyuan Chen, Lingzhuang Meng, Qiao Zhang, Zhengyi Gong, Jinghao Hu
cs.CV · cs.AI
Recent breakthroughs in 3D generation have advanced notably with the development of text-to-image diffusion model. However, existing methods remain two practical challenges: (1) They primarily generate single 3D object, but struggle to generate multi-object compositional 3D assets due to the lack of the modeling for Gaussian primitives in reasonable interactions. (2) They often suffer from cross-view inconsistency during 3D optimization, as...
-
17
Co-occurring associated retained concepts in Diffusion Unlearning
Miso Kim, Georu Lee, Yunji Kim, Hoki Kim, Jinseong Park, Woojin Lee
cs.CV · cs.AI · cs.CL
Unlearning has emerged as a key technique to mitigate harmful content generation in diffusion models. However, existing methods often remove not only the target concept, but also benign co-occurring concepts. As illustrated in Fig.1, unlearning nudity can unintentionally suppress the concept of person, preventing a model from generating images with person. We define these undesirably suppressed co-occurring concepts that must be preserved...
-
18
Deep Learning Approaches for 3D Medical Scene Completion: From Geometric Modeling to Generative Paradigms
Afifa Khaled, Said Jadid Abdulkadir, Majdy Mohamed Eltayeb Eltahir
cs.CV · cs.AI
Three-dimensional scene completion has evolved as a major problem in computer vision and robotics, and its applications are diverse, including autonomous navigation and augmented reality. In this study, a systematic review has been conducted to compile the research contributions made in the last ten years, i.e., 2016 to 2026, which has revolutionized the field from the voxel semantic completion paradigm represented by SSCNet to the latest...
-
19
Zero-Shot Test-Time Canonicalization using Out-of-Distribution Scoring
Dominik Lindner, Johann Schmidt, Tom Siegl, Martin Becker, Sebastian Stober
cs.CV · cs.AI
Pretrained vision models often misclassify inputs that are rotated, scaled, or sheared, even though these affine transformations leave the object class unchanged. Robustness is usually restored either by building equivariance into the architecture or by retraining with augmentation, both of which require changing or retraining the model. Test-time canonicalization instead leaves the classifier untouched. It undoes the transformation of each...
-
20
Autonomous Video Generation with Counterfactual Controllability for Self-Evolving World Models
Xin Wang, Wenxuan Liu, Tongtong Feng, Wenwu Zhu
cs.CV · cs.LG
Existing literature claims that video generation essentially is world modelling. On the one hand, the claim is productive because it pushes generative AI beyond static images and toward temporally extended physical scenes. On the other hand, this claim dangerously relies on the belief that scaling visual prediction alone will automatically yield physical agents. We prefer a more accurate statement: video generation models learn a partial,...
-
21
A Benchmark for Hallucination Detection in VLMs for Gastrointestinal Endoscopy
Aminu Lawal, Niyoj Oli, Sachin Acharya, Prashnna Gyawali, Maria Carmen Romano, Binod Bhattarai
cs.CV · cs.AI
Vision-language models (VLMs) are prone to hallucination, which remains a major barrier to their safe deployment in clinical practice. To date, most hallucination detection methods have been evaluated on radiology benchmarks such as MIMIC-CXR and VQA-RAD, while gastrointestinal (GI) endoscopy remains largely underexplored. In this paper, we benchmark nine hallucination detection methods on the Gut-VLM dataset, a GI diagnostic Visual Question...
-
22
DramaDirector: Geometry-Guided Short Drama Generation
Hengji Zhou, Sijie Liu, Jianrun Chen, Xingchen Zou, Lianghao Xia, Liqiang Nie
cs.CV · cs.AI
Short dramas, with their rapid shot rhythms, dialogue-driven focus shifts, and demanding cinematographic grounding, pose challenges that prompt-level or text-only video generation pipelines struggle to meet. We study plot-to-short-drama generation, where a global plot and local context are transformed into visually grounded multi-shot videos. We propose DramaDirector, a geometry-grounded framework that lets the planner borrow cinematographic...
-
23
Beyond Bayer: Task-Optimal Sensor Co-Design for Robust Autonomous-Driving Segmentation
Reeshad Khan, John Gauch
cs.CV · cs.AI
Robust perception underpins autonomous driving, and most recent progress comes from scaling the model-larger backbones, foundation models, and cooperative multi-agent fusion. We pursue a complementary, upstream question: what should the camera itself measure? Using a differentiable RAW-to-task pipeline, we decompose which sensor degrees of freedom benefit dense prediction. Learning the spectral colour-filter-array (CFA) weights is the...
-
24
End-to-End Radar and Communication Modulation Recognition with Neuromorphic Computing
Xiaohu Li, Chongxiao Qu, Caiyong Lin, Chenxiao Dou, Wei Hua
cs.CV · cs.AI
Although deep learning-based methods can achieve high accuracy in automatic modulation recognition (AMR) tasks, their high computational cost makes it difficult to strike a balance between accuracy and power consumption, thereby limiting their application on resource-constrained platforms. Neuromorphic architectures that perform spike-driven inference with modest energy budgets have recently been explored for vision and timeseries tasks....
This edition is part of The Daily Abstract — cs.CV archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.