扩散模型先验知识赋能人物搜索新范式，精准提升行人重识别效果
arXiv:2510.01841v2 Announce Type: replace Abstract: Person search aims to jointly perform person detection and re-identification by localizing and ide…
提出边缘感知热红外无人机群跟踪方法，融合图谱卷积与注意力机制，突破多目标遮挡和红外模糊难题。
arXiv:2607.12544v1 Announce Type: new Abstract: Thermal infrared (TIR) imaging is essential for UAV swarm operations in visually degraded environments…
新型多模态检索增强框架让大模型精准理解航拍图像细节，解决细粒度视觉推理难题。
arXiv:2604.17889v2 Announce Type: replace Abstract: Despite recent progress in multimodal large language models (MLLMs), reliable visual question answ…
无需额外训练，推理阶段即可实现跨主体的精准运动迁移，为视频生成与动画制作带来简洁高效的解决方案。
arXiv:2607.11644v1 Announce Type: new Abstract: This work explores the motion transfer from one video to another, which is crucial in animation for di…
6D位姿估计新方法，低成本实现工业料箱抓取，效率与精度双重突破。
arXiv:2604.04690v2 Announce Type: replace-cross Abstract: Bin picking in real industrial environments remains challenging due to severe clutter, occlu…
诊断Video-LLM在长视频中跟踪角色的失败，揭示当前最强开源模型未能真正“观看”视频的局限。
arXiv:2607.11078v1 Announce Type: cross Abstract: Can a Video Large Language Model (Video-LLM) follow one person through a long video, keeping track o…
用三角拼图法破解平移平均的鲁棒性难题，为视觉SLAM和3D重建提供全新优化思路。
arXiv:2605.07143v2 Announce Type: replace Abstract: Translation averaging aims to recover camera locations from pairwise relative translation directio…
全新基准测试RVN-Bench，专为反应式视觉导航设计，推动机器人自主导航评估标准化
arXiv:2603.03953v2 Announce Type: replace-cross Abstract: Safe visual navigation is critical for indoor mobile robots operating in cluttered environme…
一篇关于视频问答的创新论文，强调利用证据推理来提升答案的准确性与可解释性。
arXiv:2607.11862v1 Announce Type: cross Abstract: Current Video Large Language Models (Video LLMs) excel in question answering (QA) but largely operat…
商汤开源统一视觉大模型 SenseNova-Vision，全任务能力超越 Vision Banana，视觉理解与生成实现原生统一。
IT之家 7 月 13 日消息，商汤科技今日发布并全面开源 日日新 SenseNova-Vision 理解生成统一视觉大模型 ，这是商汤日日新大模型体系的重要视觉能力升级。 商汤科技表示，行业以往的 " 统一视觉 " 多是把检测、分割、深度预测等多个专家模型打包封装，本质还是割裂的。SenseNov…
从粗到细监督实现高效高分辨率视觉表示，SigLIP-HD在处理多模态大模型时兼顾计算效率与细粒度特征。
arXiv:2607.09488v1 Announce Type: new Abstract: High-quality visual representation is a long-standing pursuit in computer vision. In the context of mu…
免费AI脸型检测器，基于Claude Vision和Vercel无服务器函数，教你用“无聊”的技术栈快速实现面部比例分析。
At Epica Beauty we kept seeing the same question from users: "what face shape do I have?" People were measuring their faces with rulers and comparing …
利用颜色命名规则，解决传统深度图像增强中可解释性差与参数化不足的两大痛点。
arXiv:2607.08185v1 Announce Type: new Abstract: Enhancing images to make them visually appealing is a persistent challenge in computer vision. Many de…
一个视觉音频引擎新工具，已上线Web，轻松打造音画互动体验。
Article URL: https://khn190.github.io/posara/ Comments URL: https://news.ycombinator.com/item?id=48850806 Points: 2 # Comments: 0
IT之家 7 月 10 日消息，据科技媒体 The Verge 前天报道，自动驾驶行业十多年来始终在争论：仅凭摄像头是否能取代人类驾驶员，还是说真正的无人驾驶汽车必须配备毫米波雷达、激光雷达等冗余传感器，才能可靠地感知环境？ 特斯拉已经在纯视觉智驾方案投资数十亿美元，并坚定地在这条路上前进。但与此同…
新研究发现良好初始化就能大幅提升视觉归因的忠实度，搜索式扰动方法成为关键。
arXiv:2607.06726v1 Announce Type: new Abstract: Faithful visual attribution identifies which image regions support a model prediction. Search-based pe…
多模态大模型视觉计数能力新基准，HoloCount全面评测模型在复杂场景下的计数表现，揭示当前MLLMs的瓶颈。
arXiv:2607.06420v1 Announce Type: new Abstract: Visual counting is a fundamental pillar of multimodal intelligence, requiring a seamless integration o…
突破语言束缚，BabyVision让视觉推理不再依赖文字，打造更接近人类婴儿的纯视觉认知能力。
arXiv:2601.06521v2 Announce Type: replace-cross Abstract: While humans develop core visual skills long before acquiring language, contemporary Multimo…
新基准EgoDyn-Bench专测自动驾驶视觉基础模型的自我运动理解能力，诊断漏洞提升安全性。
arXiv:2604.22851v2 Announce Type: replace-cross Abstract: While Vision-Language Models (VLMs) have advanced high-level reasoning in autonomous driving…
多模态大模型LLaVA与联邦学习结合，在保护隐私同时提升模型性能，已被计算机视觉顶会WACV接收。
arXiv:2409.06067v3 Announce Type: replace Abstract: Previous studies on federated learning (FL) often encounter performance degradation due to data he…