cs.CV · 2026-05-27 · No. 10

Computer Vision and Pattern Recognition, 2026-05-27.

14 new papers in cs.CV. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

14 entries
  1. 01

    LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding

    Shihao Wang, Shilong Liu, Yuanguo Kuang, Xinyu Wei, Yangzhou Liu, Zhiqi Li, Yunze Man, Guo Chen, Andrew Tao, Guilin...

    cs.CV · cs.AI · cs.LG · cs.RO

    Vision-language models (VLMs) commonly formulate visual grounding and detection as a coordinate-token generation problem, serializing each 2D box into multiple 1D tokens that are learned and decoded largely independently. This token-by-token decoding mismatches the coupled structure of box geometry and creates a practical inference bottleneck due to strictly sequential generation. We introduce LocateAnything, a unified generative grounding...

    arxiv.org/abs/2605.27365 · PDF

  2. 02

    When Eyes Betray AI: Social Gaze Consistency as a Semantic Cue for AI-Generated Image Detection

    Kim Jihyeon, Sohee Kim, Soosan Lee, Souhwan Jung, James Matthew Rehg, Hyesong Choi

    cs.CV · cs.AI

    Recent generative models have largely closed the gap on low-level artifacts - pixel fingerprints, frequency anomalies, upsampling traces - particularly in person-centric and partial-edit settings where the manipulated region is small and surrounded by photometrically authentic content. We introduce Social Gaze Consistency, a high-level semantic cue defined as the mutual coherence of gaze direction, head-eye alignment, and pupil placement...

    arxiv.org/abs/2605.27348 · PDF

  3. 03

    Towards Controllable Image Generation through Representation-Conditioned Diffusion Models

    Nithesh Chandher Karthikeyan, Jonas Unger, Gabriel Eilertsen

    cs.CV · cs.LG

    Diffusion models have emerged as powerful tools for high-quality image generation and editing, but guiding these models to produce specific outputs remains a challenge. Conventional approaches rely on conditioning mechanisms, such as text prompts or semantic maps, which require extensively annotated datasets. In this preliminary work, we explore diffusion models conditioned on representations from a pre-trained self-supervised model. The...

    arxiv.org/abs/2605.27343 · PDF

  4. 04

    Generative Animations: A Multi-Model Pipeline for Prompt-Driven Motion Synthesis

    Mannat Khurana, Sanyam Jain, Rishav Agarwal

    cs.CV · cs.AI

    Animation elevates digital documents into immersive experiences, yet creating custom motion paths remains cumbersome, requiring designers to manually select presets, plot Bézier points, and configure timing properties. We introduce Generative Animations, a system that transforms natural language prompts into production-ready animations. By chaining Large Language Models (LLMs) for semantic parsing with the Segment Anything Model (SAM) for...

    arxiv.org/abs/2605.27203 · PDF

  5. 05

    FoundObj: Self-supervised Foundation Models as Rewards for Label-free 3D Object Segmentation

    Zihui Zhang, Zhixuan Sun, Yafei Yang, Jinxi Li, Jiahao Chen, Bo Yang

    cs.CV · cs.AI · cs.LG · cs.RO

    We address the challenging task of 3D object segmentation in complex scene point clouds without relying on any scene-level human annotations during training. Existing methods are typically constrained to identifying simple objects, primarily due to insufficient object priors in the learning process. In this paper, we present FoundObj, a novel framework featuring a superpoint-based object discovery agent that incrementally merges suitable...

    arxiv.org/abs/2605.27178 · PDF

  6. 06

    Semantic Robustness Probing via Inpainting: An Interactive Tool for Safety-Critical Object Detection

    Nico Steckhan, Krutarth Prajapati, Weija Shao, Silvia Vock

    cs.CV · cs.AI

    Testing object detectors in safety-critical domains requires semantically meaningful probes beyond pixel-level corruptions. We present SemProbe, a tool for semantic robustness probing: users upload deployment images, create masks manually or automatically, select operational design domain-derived factors (or custom prompts), and run diffusion-based controlled inpainting. The system supports batch jobs, parallel seed/workflow variations, and...

    arxiv.org/abs/2605.27155 · PDF

  7. 07

    Is an Image Also Worth 16x16=256 Superpixels? A Framework for Attentional Image Classification

    Pedro Henrique da Costa Avelar, Anderson R. Tavares, Luís C. Lamb

    cs.CV · cs.LG

    Superpixel-based image classification has traditionally leveraged graph neural networks (GNNs) for processing irregular image representations. Recent advances in computer vision, driven by Vision Transformers (ViTs), have introduced new paradigms in self-attentional models, surpassing convolutional neural networks (CNNs) in various tasks. However, a synergistic connection between GNNs, superpixels, and transformers remains unexplored. In this...

    arxiv.org/abs/2605.27144 · PDF

  8. 08

    PILOT: A Data-Free Continual Learning Approach for Real-Time Semantic Segmentation via Boundary Guidance

    Yujing Zhou, Prashant Shekhar, Thomas Yang, Yongxin Liu

    cs.CV · cs.LG

    Real-time semantic segmentation models offer an excellent balance between accuracy and inference speed. However, deploying these models in dynamic real world environments often requires the ability to learn novel classes incrementally without retraining on the entire dataset. This capability is known as continual learning. In this regard, the standard fine-tuning methods in deep learning often fail due to catastrophic forgetting, where the...

    arxiv.org/abs/2605.27128 · PDF

  9. 09

    JLT: Clean-Latent Prediction in Latent Diffusion Transformers

    Funing Fu, Tenghui Wang, Junyong Cen, Qichao Zhu, Guanyu Zhou

    cs.CV · cs.LG

    Flow matching with clean-data prediction has shown that regressing the clean point can exploit low-dimensional structure more effectively than predicting an ambient noised quantity. We ask whether this principle remains useful after images are mapped into a learned latent space, where compression has already removed much of the raw pixel variability. We introduce JLT, a 130M latent diffusion Transformer over frozen FLUX.2 VAE codes, and...

    arxiv.org/abs/2605.27102 · PDF

  10. 10

    Black-box Membership Inference Attacks on the Pre-training Data of Image-generation Models

    Tao Qi, Huili Wang, Yuanhong Huang, Wendan Wang, Lianchao Zhao, Jinrui Wang, Zichen Qin, Shangguang Wang, Yongfeng Huang

    cs.CV · cs.AI

    The rapid advancement of diffusion-based image generation models has raised serious concerns regarding potential copyright and privacy infringements involving human-created data. Membership inference attacks (MIAs) have emerged as a promising tool for identifying unauthorized data usage during model training. Existing methods typically assess the ability of model to denoise perturbed suspect images as an indicator of membership status....

    arxiv.org/abs/2605.27020 · PDF

  11. 11

    Timestep-Aware SVDQuant-GPTQ for W4A4 Quantization of Wan2.2-I2V

    Junhao Wu, Dezhong Yao, Hai Jin

    cs.CV · cs.AI

    W4A4 quantization of large video diffusion Transformers offers substantial memory savings but is hindered by two main challenges: sparse large-magnitude activation outliers, and strongly timestep-dependent activation distributions across the multi-step denoising trajectory. These difficulties are compounded by Wan2.2-I2V's two-expert Mixture-of-Experts DiT design, whose high-noise and low-noise experts exhibit distinct quantization...

    arxiv.org/abs/2605.27003 · PDF

  12. 12

    Rotation-Invariant Spherical Watermarking via Third-Order SO(3) Representation Coupling

    Pengzhen Chen, Yanwei Liu, Xiaoyan Gu, Antonios Argyriou, Wu Liu, Weiping Wang

    cs.CV · cs.AI · cs.CR · cs.LG

    Reliable watermarking of panoramic imagery is fundamentally challenged by arbitrary 3D rotations. As panoramas are defined on the sphere, they naturally transform under the action of $SO(3)$, rendering conventional planar representations and augmentation-based robustness strategies inadequate and devoid of theoretical guarantees. To address this, we formulate panoramas as spherical signals and leverage $SO(3)$ representation theory to derive...

    arxiv.org/abs/2605.26702 · PDF

  13. 13

    DynFrame: Adaptive Reasoning-Driven Multimodal Framework with Dynamic Frame Augmentation for Complex Video Understanding

    Peng Zhang, Guanghao Zhang, Wanggui He, Longxiang Zhang, Mushui Liu, Yan Xia, Zhenhao Peng, Weilong Dai, Jinlong...

    cs.CV · cs.AI

    Recent video multimodal large language models (MLLMs) increasingly couple step-by-step reasoning with on-demand visual evidence retrieval, allowing models to revisit relevant video segments during inference. However, two structural gaps remain in existing thinking-with-video systems. (i) Sampling density is not a learnable decision: existing methods may let the model decide where to look, but the per-window frame rate is largely fixed. As a...

    arxiv.org/abs/2605.26680 · PDF

  14. 14

    Respecting Modality Gap in Post-hoc Out-of-distribution Detection with Pre-trained Vision-Language Models

    Yuanwei Hu, Bo Peng, Yadan Luo, Zhen Fang, Ling Chen, Jie Lu

    cs.CV · cs.AI

    Out-of-distribution (OOD) detection has emerged as a popular technique to enhance the reliability of machine learning models by identifying unexpected inputs from unknown classes. Recent progress in pre-trained vision-language models (VLMs) has enabled zero-shot OOD detection without access to in-distribution (ID) training data; in this setting, existing methods commonly treat text embeddings of class names as class prototypes. In this paper,...

    arxiv.org/abs/2605.26661 · PDF

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.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.