Pinned Repositories
2D-3D-Object-Detection
Related Paper and Code for 2D or 3D Object Detection
CUDA-PointPillars
A project demonstrating how to use CUDA-PointPillars to deal with cloud points data from lidar.
End-to-end-Autonomous-Driving
All you need for End-to-end Autonomous Driving
frustum-pointnets-view-results
PG-RCNN
Implementation of "PG-RCNN: Semantic Surface Point Generation for 3D Object Detection" (ICCV 2023)
SA-BEV
SEU-SRTP--3d-
SEU srtp项目——基于双目相机和激光雷达实现3d物体的定位与识别
Simple-Kitti-Visualization
Simple and easy to follow point cloud and bounding box visualizations for kitti data. The only dependencies are OpenCV and Numpy. Create re-projections onto images and 3 different views of a point-cloud with a black background (birds eye view, first person view, third person view).
TokenFusion
[CVPR 2022] Code release for "Multimodal Token Fusion for Vision Transformers"
WYSIWYD
The official codes implementation for paper "What You See Is What You Detect: Towards better Object Densification in 3D detection"
jlqzzz's Repositories
jlqzzz/End-to-end-Autonomous-Driving
All you need for End-to-end Autonomous Driving
jlqzzz/PG-RCNN
Implementation of "PG-RCNN: Semantic Surface Point Generation for 3D Object Detection" (ICCV 2023)
jlqzzz/SA-BEV
jlqzzz/WYSIWYD
The official codes implementation for paper "What You See Is What You Detect: Towards better Object Densification in 3D detection"
jlqzzz/3D-Box-Segment-Anything
We extend Segment Anything to 3D perception by combining it with VoxelNeXt.
jlqzzz/4d-occ-forecasting
Official code for `Point Cloud Forecasting as a Proxy for 4D Occupancy Forecasting'
jlqzzz/Awesome-Anything
General AI methods for Anything: AnyObject, AnyGeneration, AnyModel, AnyTask, AnyX
jlqzzz/Collaborative_Perception
This repository is a paper digest of recent advances in collaborative / cooperative / multi-agent perception for V2I / V2V / V2X autonomous driving scenario.
jlqzzz/CompletionFormer
[CVPR2023] CompletionFormer: Depth Completion with Convolutions and Vision Transformers
jlqzzz/CVPR2023-UniDistill
CVPR2023 (highlight) - UniDistill: A Universal Cross-Modality Knowledge Distillation Framework for 3D Object Detection in Bird's-Eye View
jlqzzz/DAIR-V2X-Seq
jlqzzz/DBQ-SSD
The official implementation of the paper DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detection (ICLR 2023)
jlqzzz/DeepAccident
Code for the benchmark - DeepAccident: A Motion and Accident Prediction Benchmark for V2X Autonomous Driving.
jlqzzz/DTS
Code for "Density-Insensitive Unsupervised Domain Adaption on 3D Object Detection"
jlqzzz/EFG
An Efficient, Flexible, and General deep learning framework that retains minimal.
jlqzzz/GaussianSplattingViewer
Tiny Gaussian Splatting Viewer
jlqzzz/GMIR
Gradient-based Maximally Interfered Retrieval for Domain Adaptive 3D Object Detection
jlqzzz/Lidar_AI_Solution
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, YUV2RGB, cuOSD,).
jlqzzz/LT3D
Towards Long Tailed 3D Detection. CoRL '22
jlqzzz/MIC
[CVPR23] Official Implementation of MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation
jlqzzz/MS3D
MS3D: Leveraging Multiple Source Detectors for Unsupervised Domain Adaptation in 3D Object Detection
jlqzzz/pointcloud-3d-detector-tensorrt
The first tensorrt implementation for point-based 3d detector, i.e., 3DSSD,SASA,IA-SSD.
jlqzzz/PointClouds_Segmantic_Visualize
jlqzzz/RobDet3D
jlqzzz/Robo3D
Robo3D: Towards Robust and Reliable 3D Perception against Corruptions
jlqzzz/RoboBEV
RoboBEV: Robust Bird's Eye View Detection under Corruptions and Domain Shift
jlqzzz/SegmentAnything3D
SAM-3D: A toolbox transfers 2D SAM segments into 3D scene-level point clouds.
jlqzzz/traffic-behavior-simulation
jlqzzz/ULIP
jlqzzz/UniV2X