VGGT-X: When VGGT Meets Dense Novel View Synthesis

RapidAVA: All-vs-all overlap detection in HiFi reads

[ICLR 2026] Mono4DGS-HDR: High Dynamic Range 4D Gaussian Splatting from Alternating-exposure Monocular Videos

[NeurIPS'25] HyRF: Hybrid Radiance Fields for Efficient and High-quality Novel View Synthesis

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch and FLAX.

[CVPR2025] Prometheus: 3D-Aware Latent Diffusion Models for Feed-Forward Text-to-3D Scene Generation

[NeurIPS 2024] MVInpainter: Learning Multi-View Consistent Inpainting to Bridge 2D and 3D Editing

Unofficial implementation of RealFill

ICML2025, I Think, Therefore I Diffuse: Enabling Multimodal In-Context Reasoning in Diffusion Models

A generative world for general-purpose robotics & embodied AI learning.

Source code of 'PolarRec: Improving Radio Interferometric Data Reconstruction Using Polar Coordinates', CVPR'24 accepted. By Ruoqi Wang, Zhuoyang Chen, Jiayi Zhu, Qiong Luo, Feng Wang

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

The repository for CVPR 2022 Paper "Neural 3D Video Synthesis"

[CVPR 2022] "MonoScene: Monocular 3D Semantic Scene Completion": 3D Semantic Occupancy Prediction from a single image

[ICCV 2023] OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception

[ICCV 2023] SurroundOcc: Multi-camera 3D Occupancy Prediction for Autonomous Driving

[ICCV 2023] OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction

Official implementation for paper: InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Prior