前馈式水下3D重建新方法WAT3R，突破水下图像畸变与散射限制，实现快速高精度三维重建。
arXiv:2607.21023v1 Announce Type: new Abstract: Reliable feedforward underwater 3D reconstruction remains challenging due to severe light attenuation …
多智能体协作与前馈架构结合，单目视频秒变3D模型，视觉重建技术新突破
arXiv:2607.15211v1 Announce Type: new Abstract: This paper presents MAGiSt3R, a multi-agent 3D reconstruction framework performing reconstruction and …
李飞飞团队提出Real2Sim方案SimFoundry，串起场景生成、数据生成到策略训练全流程，低成本解决Sim2Real痛点。
一段视频，生成无限训练场景
首个能对长视频序列做实例级3D重建的模型，喂一段视频就能拆出每个物体的三维结构
arXiv:2607.00375v1 Announce Type: new Abstract: We present LIST3R, an instance-aware framework for long-sequence 3D reconstruction inspired by the way…
深度3D重建赋能视频稳定，鲁棒全画幅防抖，视觉算法前沿突破，速看！
arXiv:2603.05851v2 Announce Type: replace Abstract: Video stabilization aims to mitigate camera shake but faces a fundamental trade-off between geomet…
野外场景也能精准生成漫反射纹理，让神经渲染告别光照干扰，效果更真实
arXiv:2606.30677v1 Announce Type: cross Abstract: Classical mesh texturing techniques blend captured multi-view images directly, which inevitably suff…
用AI高保真合成蝴蝶标本新视角，3D重建精度惊艳，昆虫数字化新思路。
arXiv:2606.31679v1 Announce Type: cross Abstract: Mounted butterflies are among the most striking objects in natural history collections. However, the…
开源SfM库，Python+C++实现，重建相机位姿、稀疏点云，支持密集重建与地理参考2D地图
OpenSfM v1.0 is here, and it's a big leap. The original OpenSfM (github.com/mapillary/opensfm), the Structure-from-Motion engine behind OpenDroneMap a…
华为鸿蒙6用户将迎来全局3D空间记忆应用，手机捕捉三维瞬间并直接在图库查看分享。
IT之家 6 月 14 日消息，去年 6 月的华为开发者大会 HDC 2025 上，华为终端 BG 首席执行官何刚宣布，华为、KIRI 将合作首发一款名为“Remy”的 3D 空间记忆 App。目前，该应用已登陆鸿蒙 HarmonyOS NEXT 系统的华为应用市场 App Gallery，并适配了…
用几何感知的高斯面元实现主动式物体3D重建，兼顾效率与精度，为三维视觉研究提供新思路。
arXiv:2601.06997v2 Announce Type: replace-cross Abstract: Autonomous high-fidelity object reconstruction is fundamental for creating digital assets an…
用高斯溅射模型从照片重建虚拟景观，打造全新摄影形式。
As a photographer, I've been experimenting with gaussian splatting as a quasi-photographic artistic medium. After alignment and training (colmap, brus…
SIGGRAPH 2026提出AGILE框架，用智能体生成从视频精准重建手-物体三维交互。
arXiv:2602.04672v4 Announce Type: replace Abstract: Reconstructing dynamic hand-object interactions from monocular videos is critical for dexterous ma…
从野外图像学习语义一致的变形3D表征，革新3D重建技术。
arXiv:2605.27938v1 Announce Type: new Abstract: Learning deformable 3D object models from single-view in-the-wild images has enabled impressive 3D sha…
融合几何感知与表征去噪，提升多视图3D重建鲁棒性，突破噪声干扰瓶颈。
arXiv:2605.26230v1 Announce Type: new Abstract: Multi-view 3D reconstruction has achieved remarkable progress with the advent of feed-forward 3D recon…
物体姿态追踪遇手部遮挡？新方法揭示何时能信任手部线索，助力机器人操作
arXiv:2605.23523v1 Announce Type: new Abstract: Reconstructing the motion of objects from videos is a key component for embodied AI and robot manipula…
一篇关于几何视图扩散模型的论文，提出景观感知方法提升3D场景重建质量，创新融合空间几何与扩散先验。
arXiv:2605.19865v1 Announce Type: new Abstract: Accurate camera viewpoint estimation under sparse-view conditions remains challenging, particularly in…
FactorizedHMR提出混合框架，巧妙区分躯干与四肢的不确定性，显著提升视频人体网格恢复在遮挡场景下的精度。
arXiv:2605.14854v1 Announce Type: cross Abstract: Human Mesh Recovery (HMR) is fundamentally ambiguous: under occlusion or weak depth cues, multiple 3…
类别无关的前馈模型，仅凭稀疏多状态RGB图像快速重建完整3D铰接物体。
arXiv:2512.14671v3 Announce Type: replace Abstract: We introduce ART, Articulated Reconstruction Transformer -- a category-agnostic, feed-forward mode…
CT扫描与3D重建技术助考古学家从庞贝遇难者遗骸中识别出一位罗马医生，揭秘古罗马社会。
New X-rays and CT scans showed small case with locking mechanism containing metal instruments.