yanweifu

yanweifu.github.io

deeplearning-models

A collection of various deep learning architectures, models, and tips

DeepLearning

深度学习入门教程&&优秀文章&&Deep Learning Tutorial

RLBench

A large-scale benchmark and learning environment.

awesome-action-recognition

A curated list of action recognition and related area resources

ComputerVisionDatasets

DROID-SLAM

neural_renderer

Code for the paper "Neural 3D Mesh Renderer" by H. Kato, Y. Ushiku, and T. Harada.

SoftRas

Project page of paper "Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning"

awesome-3d-human

cvpr2020-videomodeling-deployment

Materials for demonstrating video model deployment

DessiLBI

dynamicfusion

Implementation of Newcombe et al. CVPR 2015 DynamicFusion paper

ElasticFusion

Real-time dense visual SLAM system

engshell

An English-language shell for any OS, powered by LLMs

Fast-Quadric-Mesh-Simplification

Mesh triangle reduction using quadrics

GraphCMR

Repository for the paper "Convolutional Mesh Regression for Single-Image Human Shape Reconstruction"

improved-aesthetic-predictor

CLIP+MLP Aesthetic Score Predictor

insightface

Face Recognition Project on MXNet

Kintinuous

Real-time large scale dense visual SLAM system

mediapipe

MediaPipe is a cross-platform framework for building multimodal applied machine learning pipelines

metaseq

Repo for external large-scale work

MixHop-and-N-GCN

An implementation of "MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing" (ICML 2019).

mm-cot

Official implementation for "Multimodal Chain-of-Thought Reasoning in Language Models" (stay tuned and more will be updated)

point2mesh

Reconstruct Watertight Meshes from Point Clouds [SIGGRAPH 2020]

Qix

Machine Learning、Deep Learning、PostgreSQL、Distributed System、Node.Js、Golang

Scene-Text-Recognition

splitnet-wrn

Code for ICML 2017 paper, SplitNet: Learning to Semantically Split Deep Networks for Parameter Reduction and Model Parallelization

unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

vrn

:man: Code for "Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression"