SoftVC VITS Singing Voice Conversion

Using Low-rank adaptation to quickly fine-tune diffusion models.

A General NeRF Acceleration Toolbox in PyTorch.

This is the Unity package for COLIBRI VR, the Core Open Lab on Image-Based Rendering Innovation for Virtual Reality.

Lecture notes, projects and other materials for Course 'CS219 Advanced Programming' at Southern University of Science and Technology.

BoxMOT: Pluggable python and c++ SOTA multi-object tracking modules with support for axis-aligned and oriented bounding boxes

Comparison of IQA models in Perceptual Optimization

PyTorch3D is FAIR's library of reusable components for deep learning with 3D data

[NeurIPS‘2021] "TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up", Yifan Jiang, Shiyu Chang, Zhangyang Wang

API to support AIST++ Dataset: https://google.github.io/aistplusplus_dataset

Surround360 is Facebook's open source hardware and software for capturing stereoscopic 3D 360 video for VR. The repo contains hardware designs, as well as software for camera control and rendering.

Code for tutorial on how to use Eigen's LM optimization

Liquid Warping GAN with Attention: A Unified Framework for Human Image Synthesis

NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

A high performance and generic framework for distributed DNN training

[ICLR-2020] Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification.

A Trimap-Free Portrait Matting Solution in Real Time [AAAI 2022]

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

Fully textured and animatable human body mesh reconstruction from a single image

improves over nerf in 360 capture of unbounded scenes

ECCV18 Workshops - Enhanced SRGAN. Champion PIRM Challenge on Perceptual Super-Resolution. The training codes are in BasicSR.

Bringing Old Photo Back to Life (CVPR 2020 oral)

Volumetric Human Teleportation (SIGGRAPH 2020 Real-Time Live) Monocular Real-Time Volumetric Performance Capture(ECCV 2020)

Deep 3D Portrait from a Single Image

[ECCV2020] a toolbox of light-reid learning for faster inference, speed both feature extraction and retrieval stages up to >30x

A PyTorch implementation of "ContourNet: Taking a Further Step toward Accurate Arbitrary-shaped Scene Text Detection" (CVPR2020)

Official pytorch Code for CVPR2019 paper "Fast Human Pose Estimation" https://arxiv.org/abs/1811.05419

Algorithm to texture 3D reconstructions from multi-view stereo images