Repositories list

• Spatial-TTT

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

  vlmspatial-reasoningtest-time-training+ 2

  vlmspatial-reasoningtest-time-trainingmllmspatial-intelligence

  Python

  •

  Apache License 2.0

  •44 forks•181181 stars•55 issues•00 pull requests•Updated Mar 13, 2026Mar 13, 2026

• Video-T1

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

  videovideo-generationaigc+ 2

  videovideo-generationaigcchain-of-thoughttest-time-scaling

  Python

  •

  MIT License

  •1717 forks•311311 stars•44 issues•00 pull requests•Updated Mar 7, 2026Mar 7, 2026

• CFG-Ctrl

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

  Python

  •

  Apache License 2.0

  •22 forks•3636 stars•22 issues•00 pull requests•Updated Mar 4, 2026Mar 4, 2026

• Spatial-MLLM

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

  multimodalaigcllm+ 2

  multimodalaigcllmmultimodal-large-language-modelsspatial-intelligence

  Python

  •

  MIT License

  •1717 forks•462462 stars•66 issues•00 pull requests•Updated Feb 5, 2026Feb 5, 2026

• LangScene-X

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

  3d-reconstructiondiffusionvideo-generation+ 1

  3d-reconstructiondiffusionvideo-generationunified-model

  Python

  •

  MIT License

  •2222 forks•302302 stars•66 issues•11 pull request•Updated Jul 15, 2025Jul 15, 2025

• VideoScene

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

  video3d-reconstructionvideo-generation

  video3d-reconstructionvideo-generation

  Python

  •

  MIT License

  •1010 forks•352352 stars•66 issues•00 pull requests•Updated Jul 4, 2025Jul 4, 2025

• DreamCinema

  Public
  DreamCinema: Cinematic Transfer with Free Camera and 3D Character

  3d-graphicsagic

  3d-graphicsagic

  MIT License

  •22 forks•9595 stars•33 issues•00 pull requests•Updated Jun 13, 2025Jun 13, 2025

• ReconX

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

  3d-reconstructionvideo-diffusion-model

  3d-reconstructionvideo-diffusion-model

  MIT License

  •2525 forks•708708 stars•44 issues•00 pull requests•Updated Nov 9, 2024Nov 9, 2024

• Semantic-Ray

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

  computer-visioncomputer-graphicsnerf

  computer-visioncomputer-graphicsnerf

  Python

  •

  MIT License

  •33 forks•8282 stars•33 issues•00 pull requests•Updated Jul 28, 2024Jul 28, 2024

• Physics3D

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

  physics-simulation4d3d-aigc

  physics-simulation4d3d-aigc

  Python

  •

  MIT License

  •1414 forks•231231 stars•44 issues•00 pull requests•Updated Jun 12, 2024Jun 12, 2024

• Sherpa3D

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

  text-to-3d3d-aigc

  text-to-3d3d-aigc

  Python

  •

  MIT License

  •77 forks•182182 stars•77 issues•00 pull requests•Updated May 22, 2024May 22, 2024

• Make-Your-3D

  Public
  [ECCV 2024] Make-Your-3D: Fast and Consistent Subject-Driven 3D Content Generation

  3d-aigc

  3d-aigc

  MIT License

  •88 forks•128128 stars•22 issues•00 pull requests•Updated Mar 15, 2024Mar 15, 2024