mint-lab /3dv_tutorial
3D视觉邀请:适合每个人的收件箱
CMake1826
visual-geometry 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
3D视觉邀请:适合每个人的收件箱
[CVPR 2026] Visual Geometry Transformer for Autonomous Driving
Official implementation of the paper "VGGT-Diff: Visual Geometry Meets Diffusion for Sparse-View Novel View Synthesis."
[ECCV 2026] OVGGT is a training-free framework enabling streaming 3D reconstruction from arbitrarily long video with constant memory.
Accelerate sparse-view novel view synthesis by integrating VGGT geometry priors with diffusion models for faster, higher-quality 3D scene generation.
SenseNova-Vision: unified multimodal generation for computer vision with text, image, and mixed outputs.
GeoVehicle3D: vision-centric 3D vehicle-center estimation from image geometry