Stars
Official repo for paper "Echo-Infinity: Learnable Evolving Memory for Real-Time Infinite Video Generation"
The official implementation of ICCV'25 paper "FlashDepth: Real-time Streaming Video Depth Estimation at 2K Resolution"
[CVPR 2025 Best Paper Nomination] FoundationStereo: Zero-Shot Stereo Matching
A Triton Kernel for incorporating Bi-Directionality in Mamba2
[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model
Code Implementation of EfficientVMamba
[CVPR 2025 Highlight] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos
Mamba in Vision: A Comprehensive Survey of Techniques and Applications
🚀 Efficient implementations for emerging model architectures
A linear estimator on top of clip to predict the aesthetic quality of pictures
[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation
Coder for "On the Continuity of Rotation Representations"
A unified framework for 3D content generation.
Refine high-quality datasets and visual AI models
NeRF (Neural Radiance Fields) and NeRF in the Wild using pytorch-lightning
Zero-1-to-3: Zero-shot One Image to 3D Object (ICCV 2023)
A TensorFlow implementation of the Differentiable Neural Computer.
Generate 3D objects conditioned on text or images
Code for the paper "Planning with Diffusion for Flexible Behavior Synthesis"
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
Elucidating the Design Space of Diffusion-Based Generative Models (EDM)
The source code for the blog post The 37 Implementation Details of Proximal Policy Optimization