扩散模型技术跨界3D交互，让机器人理解开放世界物体操作方式，知识泛化能力大升级。
arXiv:2508.01651v2 Announce Type: replace Abstract: 3D affordance grounding aims to understand how diverse objects can be manipulated, making it a cor…
无需训练即可抗噪的3D结构先验，为体素逆问题提供全新几何约束，值得关注。
arXiv:2603.02149v2 Announce Type: replace Abstract: Volume denoising is a foundational problem in computational imaging, as many 3D imaging inverse pr…
计算机视觉库重磅升级，全新DNN引擎原生支持大模型，性能与易用性全面提升。
IT之家 6 月 6 日消息，OpenCV 团队本周正式发布了 OpenCV 5。 据介绍，二十多年来，OpenCV 一直是计算机视觉研究、机器人技术、嵌入式视觉、AI 应用、工业检测、AR / VR、医学成像以及无数生产系统的基础。如今，该库在 GitHub 上拥有超过 86,000 颗 star…
这篇论文提出一种失败感知的bootstrap方法，解决动态点云理解中的关键难点，为3D视觉研究带来新思路。
arXiv:2602.03890v2 Announce Type: replace Abstract: Point clouds provide a compact and expressive representation of 3D objects, and have recently been…
双路径几何感知机制提升MLLM空间理解，为具身智能与3D视觉任务提供新范式。
arXiv:2605.25334v1 Announce Type: new Abstract: Spatial understanding of the physical world from 2D visual inputs hinges on two complementary forms of…
用可微分渲染技术从单张声纳图像重建海底三维地形，开创水下视觉新范式
arXiv:2605.24195v1 Announce Type: cross Abstract: Sonar is often the only modality suitable for high-resolution imaging underwater due to light attenu…