Stars
SceneCompleter: Dense 3D Scene Completion for Generative Novel View Synthesis
[ICCV 25]SpectralAR: Spectral Autoregressive Visual Generation
[ECCV-2024] LN3Diff creates high-quality 3D object mesh from text within 8 V100-SECONDS.
StreamSplat: Towards Online Dynamic 3D Reconstruction from Uncalibrated Video Streams
Official implementation of MAGREF: Masked Guidance for Any-Reference Video Generation
Code release for paper "Test-Time Training Done Right"
Codes of MVSFormer++: Revealing the Devil in Transformer’s Details for Multi-View Stereo (ICLR2024)
[TPAMI 2025 & CVPR 2023] IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matching
An unofficial implementation of DreamScene360.
🚀 [ICLR 2025] Pytorch implementation of 'Fast Feedforward 3D Gaussian Splatting Compression'
🌍 WorldGen - Generate Any 3D Scene in Seconds
MAGI-1: Autoregressive Video Generation at Scale
Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos
Pytorch implementation for the paper titled "SimpleAR: Pushing the Frontier of Autoregressive Visual Generation"
MineWorld: A Real-time interactive world model on Minecraft
[ICCV 2025] Official repo for "GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation"
open-sourced video dataset with dynamic scenes and camera movements annotation
[ICML 2025] Gaussian Mixture Flow Matching Models (GMFlow)
[ICCV 2025] Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction
[CVPR 2025 Highlight] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos
[CVPR 2025] Official code for the paper "SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis"
[ICLR 2025 Oral] Official code for "LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias"
[ICCV 2025] Aether: Geometric-Aware Unified World Modeling
Building Open-Ended Embodied Agents with Internet-Scale Knowledge
Official implementation for WorldScore: A Unified Evaluation Benchmark for World Generation