Stars
[CVPR'25] MonoSplat: Generalizable 3D Gaussian Splatting from Monocular Depth Foundation Models
[CVPR 2025] Official code of "PanDA: Towards Panoramic Depth Anything with Unlabeled Panoramas and Mobius Spatial Augmentation"
Official PyTorch implementation of our paper "Spherical Vision Transformer for 360° Video Saliency Prediction" (BMVC 2023)
[CVPR 2025 Best Paper Award Candidate] VGGT: Visual Geometry Grounded Transformer
The repo for "Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator"
Rasterize with the least efforts for researchers.
Depth Any Video with Scalable Synthetic Data (ICLR 2025)
A fast poisson image editing implementation that can utilize multi-core CPU or GPU to handle a high-resolution image input.
Poisson blending of images
[CVPR 2025 Highlight] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos
PyTorch implementation of "From Sparse to Soft Mixtures of Experts"
[ICLR 2025] MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts
[ACL 2024] Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models
[ICLR 2025] Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models
This is the official code release for our work, Denoising Vision Transformers.
这是一个segformer-pytorch的源码，可以用于训练自己的模型。
[ECCV 2024, Oral] DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors
A generative world for general-purpose robotics & embodied AI learning.
[TPAMI 2025] UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation
Lifting ControlNet for Generalized Depth Conditioning
[CVPR'25 Highlight] You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale
Official code of "Imagine360: Immersive 360 Video Generation from Perspective Anchor"
DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion
Official implementation of "ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis"
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"