Calculate the day of reaching LeetCode points

Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.

[ECCV 2024] Towards Stable 3D Object Detection

HEDNet (NeurIPS 2023) & SAFDNet (CVPR 2024 Oral)

[CVPR'24 Oral] Official repository of Point Transformer V3 (PTv3)

GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimation [IJCV2023]

PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Clouds (CVPR 2023)

[ICCV 2023] DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Clouds

Amnezia VPN Client (Desktop+Mobile)

[NeurIPS 2024] Official code of ”LION: Linear Group RNN for 3D Object Detection in Point Clouds“

Pointcept: Perceive the world with sparse points, a codebase for point cloud perception research. Latest works: Sonata (CVPR'25 Highlight), PTv3 (CVPR'24 Oral)

YaFSDP: Yet another Fully Sharded Data Parallel

Refine high-quality datasets and visual AI models

FastPillars: A Deployment-friendly Pillar-based 3D Detector

Read and write PCL .pcd files in python

LiSnowNet: Real-time Snow Removal for LiDAR Point Cloud

VINS-Fusion based visual-inertial SLAM with tightly-coupled wheel odometry for outdoor delivery robot

2D road segmentation using lidar data during training

Curated list of interactive ML demos

A project demonstrating Lidar related AI solutions, including three GPU accelerated Lidar/camera DL networks (PointPillars, CenterPoint, BEVFusion) and the related libs (cuPCL, 3D SparseConvolution…

Python partial re-implementation of accumuLaser in python from the KITTI360 devkits to recover label of individual pointclouds from aggregated pointclouds.

TensorRT Plugin of corresponding PyTorch Scatter operators.

This is a tensorflow-based rotation detection benchmark, also called AlphaRotate.

[CVPR2023] Official Implementation of "DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets"

RIFE, Real-Time Intermediate Flow Estimation for Video Frame Interpolation implemented with ncnn library

SparseTIR: Sparse Tensor Compiler for Deep Learning

Neural Network Compression Framework for enhanced OpenVINO™ inference

A project demonstrating how to use CUDA-PointPillars to deal with cloud points data from lidar.

An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.