Stars
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…
Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
High-Resolution 3D Human Digitization from A Single Image.
Sharp Monocular View Synthesis in Less Than a Second
Stable Diffusion built-in to Blender
fast-stable-diffusion + DreamBooth
OpenMMLab Pose Estimation Toolbox and Benchmark.
Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"
Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network (ECCV 2018)
[ICLR 2024 Oral] Generative Gaussian Splatting for Efficient 3D Content Creation
The official PyTorch implementation of the paper "Human Motion Diffusion Model"
Outpainting with Stable Diffusion on an infinite canvas
An API standard for multi-agent reinforcement learning environments, with popular reference environments and related utilities
Official implementation of CVPR2020 paper "VIBE: Video Inference for Human Body Pose and Shape Estimation"
3D高斯论文，持续更新，欢迎交流讨论。
Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set (CVPRW 2019)
SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM (CVPR 2024)
DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.
Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set (CVPRW 2019). A PyTorch implementation.
[CVPR'22] ICON: Implicit Clothed humans Obtained from Normals
Monocular, One-stage, Regression of Multiple 3D People and their 3D positions & trajectories in camera & global coordinates. ROMP[ICCV21], BEV[CVPR22], TRACE[CVPR2023]
NVIDIA Kaolin Wisp is a PyTorch library powered by NVIDIA Kaolin Core to work with neural fields (including NeRFs, NGLOD, instant-ngp and VQAD).
This is an official implementation of our CVPR 2020 paper "HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation" (https://arxiv.org/abs/1908.10357)
[CVPR 2024 Highlight] PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics
A PyTorch port of the Neural 3D Mesh Renderer