karaninder

GFPGAN

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

OpenDevin

🐚 OpenDevin: Code Less, Make More

llama3

The official Meta Llama 3 GitHub site

supervision

We write your reusable computer vision tools. 💜

Bend

A massively parallel, high-level programming language

codellama

Inference code for CodeLlama models

llama-recipes

Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama for WhatsApp & Messenger.

AnimateAnyone

Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation

SpotX

SpotX patcher used for patching the desktop version of Spotify

PhotoMaker

PhotoMaker [CVPR 2024]

EasyMocap

Make human motion capture easier.

T2I-Adapter

T2I-Adapter

InstantMesh

InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models

LoFTR

Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021, T-PAMI 2022

SpotX-Bash

SpotX Mac and Linux adblocker for the Spotify desktop client, in Bash

4DGaussians

[CVPR 2024] 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering

NeuralRecon

Code for "NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video", CVPR 2021 oral

4K4D

[CVPR 2024] 4K4D: Real-Time 4D View Synthesis at 4K Resolution

rtx-remix

Combined repo for the RTX-Remix runtime

MotionCtrl

Official Code for MotionCtrl [SIGGRAPH 2024]

snake

Code for "Deep Snake for Real-Time Instance Segmentation" CVPR 2020 oral

accelerated_features

Implementation of XFeat (CVPR 2024). Do you need robust and fast local feature extraction? You are in the right place!

OnePose

Code for "OnePose: One-Shot Object Pose Estimation without CAD Models", CVPR 2022

EasyVolcap

[SIGGRAPH Asia 2023 (Technical Communications)] EasyVolcap: Accelerating Neural Volumetric Video Research

EfficientLoFTR

DoRA

[ICML2024 (Oral)] Official PyTorch implementation of DoRA: Weight-Decomposed Low-Rank Adaptation

ScoreHMR

ScoreHMR: Score-Guided Diffusion for 3D Human Recovery (CVPR 2024)

NeuMesh

Code for "MeuMesh: Learning Disentangled Neural Mesh-based Implicit Field for Geometry and Texture Editing", ECCV 2022 Oral

p1

LLM-based code completion engine

Coin3D

[SIGGRAPH 2024] Coin3D: Controllable and Interactive 3D Assets Generation with Proxy-Guided Conditioning