-
Facebook
- Bay Area
- https://www.linkedin.com/in/liyingcmu/
Stars
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
Virtual whiteboard for sketching hand-drawn like diagrams
Deformable DETR: Deformable Transformers for End-to-End Object Detection.
End-to-End Object Detection with Transformers
[ECCV 2024] EgoPoseFormer: A Simple Baseline for Stereo Egocentric 3D Human Pose Estimation
DeepSeek LLM: Let there be answers
A python code of digital image processing video series on my YouTube channel
Emote Portrait Alive: Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions
[IJCV] FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention
Nodes related to video workflows
Examples of ComfyUI workflows
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
EILeV: Eliciting In-Context Learning in Vision-Language Models for Videos Through Curated Data Distributional Properties
A unified framework for 3D content generation.
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
COLMAP - Structure-from-Motion and Multi-View Stereo
A curated list of awesome neural radiance fields papers
State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.
Lightweight Multi-View 3D Pose Estimation through Camera-Disentangled Representation - Tensorflow
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
A toolbox for skeleton-based action recognition.
The Replica Dataset v1 as published in https://arxiv.org/abs/1906.05797 .
A short, reasonnably simple, fast, and robust function to determine if a set of points are inside a 3d mesh