sj-li

3D-Machine-Learning

A resource repository for 3D machine learning

action-sets

Code for the paper Action Sets: Weakly Supervised Action Segmentation without Ordering Constraints

AdelaiDet

AdelaiDet is an open source toolbox for multiple instance-level detection and recognition tasks.

DP_GAN

Dual Pyramid Generative Adversarial Networks for Semantic Image Synthesis (BMVC2022)

homepage_old

Shijie Li's Homepage

MINet

Multi-scale Interaction for Real-time LiDAR Data Segmentation on an Embedded Platform (RA-L)

MS-TCN2

MS-TCN++: Multi-Stage Temporal Convolutional Network for Action Segmentation (TPAMI 2020)

PR-GCN

Pose Refinement Graph Convolutional Network for Skeleton-based Action Recognition(RA-L with ICRA 2021)

StereoNet

StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth prediction model in pytorch. ECCV2018

UnpNet

Rethinking 3-D LiDAR Point Cloud Segmentation(IEEE TNNLS)

sj-li/MS-TCN2

MS-TCN++: Multi-Stage Temporal Convolutional Network for Action Segmentation (TPAMI 2020)

sj-li/DP_GAN

Dual Pyramid Generative Adversarial Networks for Semantic Image Synthesis (BMVC2022)

sj-li/MINet

Multi-scale Interaction for Real-time LiDAR Data Segmentation on an Embedded Platform (RA-L)

sj-li/PR-GCN

Pose Refinement Graph Convolutional Network for Skeleton-based Action Recognition(RA-L with ICRA 2021)

sj-li/UnpNet

Rethinking 3-D LiDAR Point Cloud Segmentation(IEEE TNNLS)

sj-li/AdelaiDet

AdelaiDet is an open source toolbox for multiple instance-level detection and recognition tasks.

sj-li/Cylinder3D

Rank 1st in the leaderboard of SemanticKITTI semantic segmentation (Nov. 2020) :fire::fire:

sj-li/DACS

Code from the paper "DACS: Domain Adaptation via Cross-domain Mixed Sampling"

sj-li/DPT

Dense Prediction Transformers

sj-li/e3d

Efficient Methods for 3D Deep Learning

sj-li/ESANet

ESANet: Efficient RGB-D Semantic Segmentation for Indoor Scene Analysis

sj-li/inception-score-pytorch

Inception Score for GANs in Pytorch

sj-li/NeuralRecon

Code for "NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video", CVPR 2021 oral

sj-li/OASIS

Official implementation of the paper "You Only Need Adversarial Supervision for Semantic Image Synthesis" (ICLR 2021)

sj-li/point-transformer-pytorch

Implementation of the Point Transformer layer, in Pytorch

sj-li/pytorch-fid

Compute FID scores with PyTorch.

sj-li/pytorch3d

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

sj-li/RandLA-Net

🔥RandLA-Net in Tensorflow (CVPR 2020, Oral)

sj-li/ResNeSt

ResNeSt: Split-Attention Networks

sj-li/SalsaNext

Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving

sj-li/Scene-LSTM

Data and Code for "Scene-LSTM: A model for human trajectory prediction" (ISVC 2019)

sj-li/semantic-kitti-api-1

SemanticKITTI API for visualizing dataset, processing data, and evaluating results.

sj-li/sj-li.github.io

sj-li/SMIS

Semantically Multi-modal Image Synthesis(CVPR 2020)

sj-li/stable-dreamfusion

A pytorch implementation of text-to-3D dreamfusion, powered by stable diffusion.

sj-li/SwinIR

SwinIR: Image Restoration Using Swin Transformer

sj-li/transfuser

[CVPR'21] Multi-Modal Fusion Transformer for End-to-End Autonomous Driving

sj-li/TSIT

[ECCV 2020 Spotlight] A Simple and Versatile Framework for Image-to-Image Translation

sj-li/Unsupervised-Domain-Adaptation-with-Differential-Treatment

Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentation (CVPR 2020)

sj-li/vovnet-detectron2

VoVNet backbone networks for detectron2, in CVPR 2020