Skip to content
@zju3dv

ZJU3DV

ZJU3DV is a research group affliated with the State Key Lab of CAD&CG, Zhejiang University. We focus on the research of 3D computer vision, SLAM and AR.

Popular repositories Loading

  1. EasyMocap EasyMocap Public

    Make human motion capture easier.

    Python 4.9k 572

  2. LoFTR LoFTR Public

    Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021, T-PAMI 2022

    Jupyter Notebook 3k 419

  3. NeuralRecon NeuralRecon Public

    Code for "NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video", CVPR 2021 oral

    Python 2.3k 311

  4. GVHMR GVHMR Public

    Code for "GVHMR: World-Grounded Human Motion Recovery via Gravity-View Coordinates", Siggraph Asia 2024, TPAMI 2026

    Jupyter Notebook 2.1k 256

  5. 4K4D 4K4D Public

    [CVPR 2024] 4K4D: Real-Time 4D View Synthesis at 4K Resolution

    Python 1.8k 77

  6. EasyVolcap EasyVolcap Public

    [SIGGRAPH Asia 2023 (Technical Communications)] EasyVolcap: Accelerating Neural Volumetric Video Research

    Python 1.6k 101

Repositories

Showing 10 of 135 repositories
  • InfiniSplat Public

    InfiniSplat v1 & v2: Feed-Forward 3D Gaussian Reconstruction

    zju3dv/InfiniSplat's past year of commit activity
    Python 458 26 0 0 Updated Oct 17, 2026
  • zju3dv/zju3dv.github.io's past year of commit activity
    HTML 93 14 3 0 Updated Oct 16, 2026
  • SuperNav Public

    An Agentic Navigation System for Any Task in Any Scene

    zju3dv/SuperNav's past year of commit activity
    Python 186 5 2 0 Updated Oct 14, 2026
  • habitat-gs Public

    [ECCV 2026] Habitat-GS: A High-Fidelity Navigation Simulator with Dynamic Gaussian Splatting

    zju3dv/habitat-gs's past year of commit activity
    C++ 324 17 0 0 Updated Oct 13, 2026
  • PointSplat Public

    [ECCV 2026] PointSplat: Compact Gaussian Splatting via Human-Centric Prediction

    zju3dv/PointSplat's past year of commit activity
    Python 71 4 0 0 Updated Oct 12, 2026
  • INTACT-JEPA Public

    INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models.

    zju3dv/INTACT-JEPA's past year of commit activity
    Python 216 MIT 15 0 0 Updated Oct 10, 2026
  • ENeRF Public

    SIGGRAPH Asia 2022: Code for "Efficient Neural Radiance Fields for Interactive Free-viewpoint Video"

    zju3dv/ENeRF's past year of commit activity
    Python 441 27 13 0 Updated Oct 9, 2026
  • MeGAS Public

    [ECCV 2026] MeGAS: Thermomechanical Dynamic Gaussian Splatting for Thermophysical Scene Editing

    zju3dv/MeGAS's past year of commit activity
    HTML 17 0 0 0 Updated Oct 8, 2026
  • UniVerse Public

    [ICCV 2025] UniVerse: Unleashing the Scene Prior of Video Diffusion Models for Robust Radiance Field Reconstruction

    zju3dv/UniVerse's past year of commit activity
    Python 27 0 1 0 Updated Oct 6, 2026
  • geometry-as-address Public

    [ARXIV 2026] Geometry as Address: Routing Attention to Visual Memory for Long-Horizon Camera-Controlled Video Generation

    zju3dv/geometry-as-address's past year of commit activity
    43 1 1 0 Updated Sep 29, 2026