sirakzg

kornia

Geometric Computer Vision Library for Spatial AI

IC-Light

More relighting!

CLIPasso

faceID_beta

An implementation of iPhone X's FaceID using face embeddings and siamese networks on RGBD images.

vtracer

Raster to Vector Graphics Converter

facexformer

Official implementation of FaceXFormer: A Unified Transformer for Facial Analysis

transformer_latent_diffusion

Text to Image Latent Diffusion using a Transformer core

SUPIR

SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild

FADING

pybraw

Python bindings for the Blackmagic RAW SDK.

RubiksNet

Official repo for ECCV 2020 paper - RubiksNet: Learnable 3D-Shift for Efficient Video Action Recognition

live_sketch

scenic

Scenic: A Jax Library for Computer Vision Research and Beyond

consistencydecoder

Consistency Distilled Diff VAE

Instant-angelo

Instant-angelo: Build high-fidelity Digital Twin within 20 Minutes!

NodeGraphQt

Node graph framework that can be re-implemented into applications that supports PySide2

pytorch-msssim

Fast and differentiable MS-SSIM and SSIM for pytorch.

Stable-Diffusion-WebUI-TensorRT

TensorRT Extension for Stable Diffusion Web UI

Re-ReND

Re-ReND: Real-time Rendering of NeRFs across Devices

fill

Generative fill in 3D.

Face-Super-Resolution

Face super resolution based on ESRGAN

Matte-Anything

[Image and Vision Computing] Interactive Natural Image Matting with Segment Anything Models

ViTMatte

[Information Fusion] Boosting Image Matting with Pretrained Plain Vision Transformers

ZoeDepth

Metric depth estimation from a single image

nanoGPT

The simplest, fastest repository for training/finetuning medium-sized GPTs.

tiny-cuda-nn

Lightning fast C++/CUDA neural network framework

CodeM

gaussian-splatting

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

gigagan-pytorch

Implementation of GigaGAN, new SOTA GAN out of Adobe. Culmination of nearly a decade of research into GANs

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.