Stars
Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepowe…
The context API to search, scrape, and interact with the web at scale. 🔥
Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"
An open source implementation of CLIP.
Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
Official code release for CVPR 2022 paper gDNA: Towards Generative Detailed Neural Avatars
This repository contains a pytorch implementation of "SelfRecon: Self Reconstruction Your Digital Avatar from Monocular Video (CVPR 2022, Oral)".
Code for the paper Learned Vertex Descent: A New Direction for 3D Human Model Fitting (ECCV 2022)
Adversarial Parametric Pose Prior
HumanNeRF turns a monocular video of moving people into a 360 free-viewpoint video.
A library for differentiable nonlinear optimization
Google Research
VPoser: Variational Human Pose Prior
High-quality implementations of standard and SOTA methods on a variety of tasks.
Reference models and tools for Cloud TPUs.
Back to the Feature: Learning Robust Camera Localization from Pixels to Pose (CVPR 2021)
A simple HTML visualization tool for computer vision research 🛠️
A general and flexible factor graph non-linear least square optimization framework
GTSAM is a library of C++ classes that implement smoothing and mapping (SAM) in robotics and vision, using factor graphs and Bayes networks as the underlying computing paradigm rather than sparse m…
Public code for "Data-Efficient Decentralized Visual SLAM"
Image augmentation for machine learning experiments.
Deep Nets for object detection wrapped in ROS
Scripts showing how to work with the SceneNetRGBD dataset
The most cited deep learning papers
3DMatch - a 3D ConvNet-based local geometric descriptor for aligning 3D meshes and point clouds.
Source code for paper: Learning to Track at 100 FPS with Deep Regression Networks, Held, et al. ECCV 2016