Skip to content
@THU-SI

THU-SI Group

Tsinghua Spatial Intelligence & Vision Group

Pinned Loading

  1. Spatial-MLLM Spatial-MLLM Public

    [NeurIPS 2025] Official implementation of Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence

    Python 446 17

  2. ReconX ReconX Public

    [TIP 2026] ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model

    709 24

  3. Video-T1 Video-T1 Public

    [ICCV 2025] Video-T1: Test-Time Scaling for Video Generation

    Python 307 16

  4. LangScene-X LangScene-X Public

    [ICCV 2025] LangScene-X: Reconstruct Generalizable 3D Language-Embedded Scenes with TriMap Video Diffusion

    Python 297 21

  5. VideoScene VideoScene Public

    [CVPR 2025 Highlight] VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step

    Python 348 9

  6. Physics3D Physics3D Public

    Official implementation of Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusion

    Python 227 13

Repositories

Showing 10 of 11 repositories
  • Spatial-TTT Public

    Official Implementation of Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training

    THU-SI/Spatial-TTT’s past year of commit activity
    Python 20 Apache-2.0 0 0 0 Updated Mar 12, 2026
  • Video-T1 Public

    [ICCV 2025] Video-T1: Test-Time Scaling for Video Generation

    THU-SI/Video-T1’s past year of commit activity
    Python 307 MIT 16 4 0 Updated Mar 7, 2026
  • CFG-Ctrl Public

    [CVPR 2026] CFG-Ctrl: Control-Based Classifier-Free Diffusion Guidance

    THU-SI/CFG-Ctrl’s past year of commit activity
    Python 34 Apache-2.0 2 2 0 Updated Mar 4, 2026
  • Spatial-MLLM Public

    [NeurIPS 2025] Official implementation of Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence

    THU-SI/Spatial-MLLM’s past year of commit activity
    Python 446 MIT 17 5 0 Updated Feb 5, 2026
  • LangScene-X Public

    [ICCV 2025] LangScene-X: Reconstruct Generalizable 3D Language-Embedded Scenes with TriMap Video Diffusion

    THU-SI/LangScene-X’s past year of commit activity
    Python 297 MIT 21 5 0 Updated Jul 15, 2025
  • VideoScene Public

    [CVPR 2025 Highlight] VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step

    THU-SI/VideoScene’s past year of commit activity
    Python 348 MIT 9 6 0 Updated Jul 4, 2025
  • ReconX Public

    [TIP 2026] ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model

    THU-SI/ReconX’s past year of commit activity
    709 MIT 24 4 0 Updated Nov 9, 2024
  • Semantic-Ray Public

    [CVPR 2023] Semantic Ray: Learning a Generalizable Semantic Field with Cross-Reprojection Attention

    THU-SI/Semantic-Ray’s past year of commit activity
    Python 82 MIT 2 3 0 Updated Jul 28, 2024
  • Physics3D Public

    Official implementation of Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusion

    THU-SI/Physics3D’s past year of commit activity
    Python 227 MIT 13 3 0 Updated Jun 12, 2024
  • Sherpa3D Public

    [CVPR 2024] Sherpa3D: Boosting High-Fidelity Text-to-3D Generation via Coarse 3D Prior

    THU-SI/Sherpa3D’s past year of commit activity
    Python 180 MIT 6 6 0 Updated May 22, 2024
View all repositories

Top languages

Loading…