- ByteDance
- Shenzhen
- https://nicholasli1995.github.io/
- in/shichao-li-63a97415a
Stars
[NeurIPS 2021] Moment-DETR code and QVHighlights dataset
Official project website for the ICRA 2025 paper "Learning better representations for crowded pedestrians in offboard LiDAR-camera 3D tracking-by-detection"
Source code of "Towards Enforcing Social Distancing Regulations with Occlusion-Aware Crowd Detection" presented in International Conference on Control, Automation, Robotics and Vision, 2020
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
A library for differentiable nonlinear optimization
HOTA (and other) evaluation metrics for Multi-Object Tracking (MOT).
Vision-Centric BEV Perception: A Survey
Awesome papers about Multi-Camera 3D Object Detection and Segmentation in Bird's-Eye-View, such as DETR3D, BEVDet, BEVFormer, BEVDepth, UniAD
Perception toolkit for sim2real training and validation in Unity
Predict dense depth maps from sparse and noisy LiDAR frames guided by RGB images. (Ranked 1st place on KITTI) [MVA 2019]
[ NeurIPS2021] This is an official implementation of our paper "HRFormer: High-Resolution Transformer for Dense Prediction".
[T-PAMI 2022] DSGN++: Exploiting Visual-Spatial Relation for Stereo-based 3D Detectors
A 3D vision library from 2D keypoints: monocular and stereo 3D detection for humans, social distancing, and body orientation.
Behind the Curtain: Learning Occluded Shapes for 3D Object Detection
Toolkit for the BOP benchmark, including evaluation scripts and utilities for 6D object pose estimation and related tasks.
This repository contains datasets and baselines for benchmarking Chinese text recognition.
Official implementation of "VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Environment"
Python tools for working with KITTI data.
Awesome work on object 6 DoF pose estimation
[CVPR'22] ICON: Implicit Clothed humans Obtained from Normals
[ICCV21 & WACV23] Monocular 3D Object Detection for Automonous Driving
Code repository for the paper "Tracking People with 3D Representations". NeurIPS 2021
Tooling for the Common Objects In 3D dataset.
Progressive Coordinate Transforms for Monocular 3D Object Detection, NeurIPS 2021
