vggt 开源项目推荐（73 个）

MIT-SPARK /VGGT-SLAM

VPGT-SLAM：在SL（4）管汇上优化的密集色RB SLAM

OpenDCAI /OpenWorldLib

高级世界模型统一代码库。

reality-opened /openreality

Open Reality: phone video to AI-queryable 3D scenes. MCP tools for Claude/Codex/Cursor (npm openreality-mcp), the self-hostable broker, and the VGGT-SLAM library, in one repo. BSD-2-Clause.

TencentARC /Track4World

[ECCV 2026] Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels

Linketic /VGGT-X

VGGT-X: When VGGT Meets Dense Novel View Synthesis

3D-Vision-World /All-3R-SLAM-in-this-Repo

This is a list of relevant papers for 3D Geometric Foundation Models and Applications.

jaskirat1616 /Splatline

使用高斯飞溅后台（VGPT、LongSplat、DepthSplat、SHARP、TripoSplat）、重新运行和SuperSplat编辑器将2D视频和照片转换为交互式3D场景。

chenkangjie1123 /VGGT-Diff

Official implementation of the paper "VGGT-Diff: Visual Geometry Meets Diffusion for Sparse-View Novel View Synthesis."

jmanhype /vggt-mps

VGGT 3D 视觉代理，针对苹果硅芯片优化，配备金属性能着色器

LSXI7 /Wat3R

[ECCV 2026 Oral] Wat3R: Underwater 3D Geometry Learning without Annotations

yassa9 /dvlt.cu

Suckless no dependencies CUDA/C++ port of NVIDIA's DVLT, feed it images, get a 3D point cloud + camera poses. NO python. One fast 5MB binary.

yejun688 /CVPR_2025_Oral_Paper_List

😎 A curated list of CVPR 2025 Oral paper. Total 96

yester31 /Monocular_Depth_Estimation_TRT

Optimizing Monocular Depth Estimation with TensorRT: Model Conversion, Inference Acceleration, and 3D Reconstruction

jashshah999 /vggt-factor-refinement

Factor graph refinement of VGGT feed-forward 3D reconstruction

vLAR-group /RayletDF

🔥RayletDF in PyTorch (ICCV 2025 Highlight)

jashshah999 /recon3d

One-command 3D reconstruction from video. No COLMAP needed.

andvg3 /eVGGT

[IROS 2026] Code for "eVGGT: An Efficient Geometry-Aware Vision Encoder for Visuomotor Policies"

CMLab-Korea /Self-Geometry

Official repository of Self-Geometry

Brack-Wang /finetune_omega

Omega-Forge: unofficial code to finetune or train VGGT-Omega (VGGT-Ω) on your own dataset, for use while official training code is not yet available. Additionally includes a standalone zero-GPU 3D reconstruction visualizer.

Hasasasaki /photo-to-mesh

Turn photos of an object into a clean, scaled 3D mesh. Interactive GUI on Hunyuan3D (single + multi-view 2mv), SAM 3 masking, VGGT/2DGS reconstruction.