[ICLR 2026] Official Implementation for Paper "Joint Optimization for 4D Human-Scene Reconstruction in the Wild"

[IJCV 2024] InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions

A simple and fast GUI tool to visualize and compare the SMPL sequences and scenes in real-time.

A Blender add-on for importing a sequence of OBJ meshes as frames

[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.

VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models

Materials for the Hugging Face Diffusion Models Course

Perception toolkit for sim2real training and validation in Unity

《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。

Implementation of depth camera in Unity

Code for our ICCV 2021 paper "Mitigating Intensity Bias in Shadow Detection via Feature Decomposition and Reweighting"

Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).

Detecting SP (sun position) in outdoor 360 panorama. (image based estimation, approximation. Solar Position Algorithm)

Semantic segmentation of outdoor panoramic images using UNet-stdconv and UNet-equiconv. CVRG-Pano: semantically annotated outdoor panoramic image dataset.

A re-implemented project of "Deep Outdoor Illumination Estimation [Hold-Geoffroy et al. CVPR 2017]"

[AAAI 2022] The first dataset on foreground object shadow generation for image composition in real-world scenes. The code used in our paper "Shadow Generation for Composite Image in Real-world Scen…

Official implementation for "Blended Latent Diffusion" [SIGGRAPH 2023]

An open source lane detection toolbox based on PyTorch, including SCNN, RESA, UFLD, LaneATT, CondLane, etc.

Monocular Depth Estimation Toolbox based on MMSegmentation.

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

A library to generate LaTeX expression from Python code.

[CVPR'21] Projecting Your View Attentively: Monocular Road Scene Layout Estimation via Cross-view Transformation

Official code for the Paper "Goal-driven Self-Attentive Recurrent Networks for Trajectory Prediction", CVPRW 2022

[ECCV2022] Official implementation of the paper "View Vertically: A Hierarchical Network for Trajectory Prediction via Fourier Spectrums"

A Grounded Simulation Testing Framework for Evaluating Social Navigation: https://arxiv.org/abs/2103.00047

A PyTorch implementation of NeRF (Neural Radiance Fields) that reproduces the results.

scikit-fmm is a Python extension module which implements the fast marching method.