binianzjl

ultralytics

NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite

DiffusionDet

[ICCV2023 Best Paper Finalist] PyTorch implementation of DiffusionDet (https://arxiv.org/abs/2211.09788)

rethinking-network-pruning

Rethinking the Value of Network Pruning (Pytorch) (ICLR 2019)

BEVDet

Official code base of the BEVDet series .

DBFace

DBFace is a real-time, single-stage detector for face detection, with faster speed and higher accuracy

ViT-Adapter

[ICLR 2023 Spotlight] Vision Transformer Adapter for Dense Predictions

TPVFormer

[CVPR 2023] An academic alternative to Tesla's occupancy network for autonomous driving.

BEVFusion

Offical PyTorch implementation of "BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework"

Ultra-Fast-Lane-Detection-v2

Ultra Fast Deep Lane Detection With Hybrid Anchor Driven Ordinal Classification (TPAMI 2022)

CenterFusion

CenterFusion: Center-based Radar and Camera Fusion for 3D Object Detection

aanet

[CVPR'20] AANet: Adaptive Aggregation Network for Efficient Stereo Matching

simple_bev

A Simple Baseline for BEV Perception

MOTRv2

[CVPR2023] MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors

Zero-DCE_extension

Sparsebit

A model compression and acceleration toolbox based on pytorch.

litepose

[CVPR'22] Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation

ST3D

(CVPR 2021 & T-PAMI 2022) ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection & ST3D++: Denoised Self-training for Unsupervised Domain Adaptation on 3D Object Detection

futr3d

Code for paper: FUTR3D: a unified sensor fusion framework for 3d detection

BEVStereo

Official code for BEVStereo

TJ4DRadSet

TJ4DRadSet: A 4D Radar Dataset for Autonomous Driving

UVTR

Unifying Voxel-based Representation with Transformer for 3D Object Detection (NeurIPS 2022)

RMNet

RM Operation can equivalently convert ResNet to VGG, which is better for pruning; and can help RepVGG perform better when the depth is large.

MotionNet

CVPR 2020, "MotionNet: Joint Perception and Motion Prediction for Autonomous Driving Based on Bird's Eye View Maps"

YOLO-FaceV2

YOLO-FaceV2: A Scale and Occlusion Aware Face Detector

simtrack

Exploring Simple 3D Multi-Object Tracking for Autonomous Driving (ICCV 2021)

AutoAlignV2

[ECCV2022, IJCAI2022] AutoAlignV2: Deformable Feature Aggregation for Dynamic Multi-Modal 3D Object Detection

RDIoU

"Rethinking IoU-based Optimization for Single-stage 3D Object Detection", ECCV2022 accept!

CMKD

Cross-Modality Knowledge Distillation Network for Monocular 3D Object Detection (ECCV 2022 Oral)

Balanced-Contrastive-Learning

Code Release for “Balanced Contrastive Learning for Long-Tailed Visual Recognition”

MonoDistill