Stars
A Unified Framework for Real-Time Rendering on the Web
Code for "Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans" CVPR 2021 best paper candidate
This repo is the homepage of Mathematical-Experiment courses, which is used to store and display related courseware, homework instructions and code frameworks.
This repository contains the links of code for partial papers.
【Code of CVPR 2022 paper】Neural Points: Point Cloud Representation with Neural Fields for Arbitrary Upsampling
【NeurIPS 2022 Spotlight】Neural Surface Reconstruction of Dynamic Scenes with Monocular RGB-D Camera
Training and Evaluation Code for "Mixture of Volumetric Primitives for Efficient Neural Rendering"
[SIGGRAPH Asia 2022] IDE-3D: Interactive Disentangled Editing For High-Resolution 3D-aware Portrait Synthesis
NVIDIA Kaolin Wisp is a PyTorch library powered by NVIDIA Kaolin Core to work with neural fields (including NeRFs, NGLOD, instant-ngp and VQAD).
This is a repository for the CG (Computer Graphics) messages transported from Twitter.
This repository contains a pytorch implementation of "StereoPIFu: Depth Aware Clothed Human Digitization via Stereo Vision".
Source code for the paper "Disentangled Human Body Embedding Based on Deep Hierarchical Neural Network" (TVCG2020).
This repository contains a PyTorch implementation of "AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis".
Implementation for paper "Disentangled Representation Learning for 3D Face Shape" CVPR 2019
The source code for paper "Landmark Detection and 3D Face Reconstruction for Caricature using a Nonlinear Parametric Model".
🌱 [CVPR'18] Alive Caricature from 2D to 3D. This repository contains some caricature-related data.
This repository contains the 3D face reconstruction results from a single image.
This repository contains the dataset including the pair of 2D face image and its corresponding 3D face geometry model.
Source code for the paper "Lightweight Photometric Stereo for Facial Details Recovery" (CVPR2020).
Source code for the paper "Quasi-Newton Solver for Robust Non-Rigid Registration" (CVPR2020 Oral).
【Code of CVPR2021 paper】Recurrent Multi-view Alignment Network for Unsupervised Surface Registration (CVPR 2021)
[CVPR'20] AANet: Adaptive Aggregation Network for Efficient Stereo Matching
[IJCAI 2019] Region Deformer Networks for Unsupervised Depth Estimation from Unconstrained Monocular Videos