peterzhousz Goto Github PK
Name: PeterZhouSZ
Type: User
Name: PeterZhouSZ
Type: User
Learning Unsupervised Multi-View Stereopsis via Robust Photometric Consistency
Unwind: Interactive Fish Straightening
Official code repository for the paper "Unite the People – Closing the Loop Between 3D and 2D Human Representations".
[CVPR2021 Oral] UP-DETR: Unsupervised Pre-training for Object Detection with Transformers
A Blender add-on to import, edit and export 3D city models encoded in CityJSON v.1.0 format preserving geometries, attributes and semantics
PyTorch implementation of paper "UprightNet: Geometry-Aware Camera Orientation Estimation from Single Images", ICCV 2019
Upright orientation of 3D shapes with convolutional networks
What is Learned in Deep Uncalibrated Photometric Stereo? (ECCV 2020)
Towards Ultra-Resolution Neural Style Transfer via Thumbnail Instance Normalization
MSc Graduation Thesis: Height Inference for All USA Building Footprints in the Absence of Height Data
C++ implementation of USYMLQ/USYMQR algorithms for solving unsymmetric linear systems
Source code of disparity estimation module for "UWStereoNet: Unsupervised Learning for Depth Estimation and Color Correction of Underwater Stereo Imagery"
PyTorch implementation of the Value Iteration Networks (VIN) (NIPS '16 best paper)
A video processing framework with simplicity in mind
Implementation of the paper "Variance-Aware Multiple Importance Sampling" for bidirectional path tracing in PBRT.
Code for the computing beads in a slice with varying width for minimizing underfill
Implementation of the paper "Variance-Aware Path Guiding" (SIGGRAPH 2020)
This is a team project implementing a scientific paper called "Variational Shape Approximation" by David Cohen-Steiner, Pierre Alliez and Mathieu Desbrun, published in ACM SIGGRAPH 2004.
Codebase for "Variational Surface Cutting" by Sharp & Crane, SIGGRAPH 2018
VariTex: Variational Neural Face Textures, ICCV 2021.
Code for the paper Learning Visible Connectivity Dynamics for Cloth Smoothing
Code for SIGGRAPH Asia 2016 Workshop Oral Paper: A Virtual Reality Platform for Dynamic Human-Scene Interaction
Learning latent representations of registered meshes is useful for many 3D tasks. Techniques have recently shifted to neural mesh autoencoders. Although they demonstrate higher precision than traditional methods, they remain unable to capture fine-grained deformations. Furthermore, these methods can only be applied to a template-specific surface mesh, and is not applicable to more general meshes, like tetrahedrons and non-manifold meshes. While more general graph convolution methods can be employed, they lack performance in reconstruction precision and require higher memory usage. In this paper, we propose a non-template-specific fully convolutional mesh autoencoder for arbitrary registered mesh data. It is enabled by our novel convolution and (un)pooling operators learned with globally shared weights and locally varying coefficients which can efficiently capture the spatially varying contents presented by irregular mesh connections. Our model outperforms state-of-the-art methods on reconstruction accuracy. In addition, the latent codes of our network are fully localized thanks to the fully convolutional structure, and thus have much higher interpolation capability than many traditional 3D mesh generation models.
Code for the Scene Graph Generation part of CVPR 2019 oral paper: "Learning to Compose Dynamic Tree Structures for Visual Contexts"
Code for the Visual Question Answering (VQA) part of CVPR 2019 oral paper: "Learning to Compose Dynamic Tree Structures for Visual Contexts"
Implementation of "Voting for Distortion Points in Geometric Processing"
Repository for the paper "Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images"
Lifting Vectorial Variational Problems: A Natural Formulation based on Discrete Exterior Calculus and Geometric Measure Theory, CVPR 2019
Semantic Segmentation for Line Drawing Vectorization Using Neural Networks
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.