CVPR 2024 Papers Autonomous Driving

[ICCV 2023] SurroundOcc: Multi-camera 3D Occupancy Prediction for Autonomous Driving

[ICCV 2023] OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction

[CVPR 2023 Best Paper Award] Planning-oriented Autonomous Driving

Target Inner-Geometry Learning for BEV 3D Object Detection

[ECCV 2022 oral] Monocular 3D Object Detection with Depth from Motion

[ICCV21 & WACV23] Monocular 3D Object Detection for Automonous Driving

Count the MACs / FLOPs of your PyTorch model.

OpenMMLab Model Deployment Framework

OpenMMLab YOLO series toolbox and benchmark. Implemented RTMDet, RTMDet-Rotated,YOLOv5, YOLOv6, YOLOv7, YOLOv8,YOLOX, PPYOLOE, etc.

DCNv2 supports decent pytorch such as torch 1.5+ (now 1.8+)

Deformable Convolutional Networks v2 with Pytorch

The repository containing tools and information about the WoodScape dataset.

[ECCV 2022] Lidar Point Cloud Guided Monocular 3D Object Detection.

Categorical Depth Distribution Network for Monocular 3D Object Detection (CVPR 2021 Oral)

Official code for BEVDepth.

Awesome Monocular 3D detection

Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

Official code base of the BEVDet series .

Released code for Objects are Different: Flexible Monocular 3D Object Detection, CVPR21

implementation of paper - You Only Learn One Representation: Unified Network for Multiple Tasks (https://arxiv.org/abs/2105.04206)

OpenMMLab's next-generation platform for general 3D object detection.

[ECCV2022] PETR: Position Embedding Transformation for Multi-View 3D Object Detection & [ICCV2023] PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images

[ICRA'23] BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

Deformable DETR: Deformable Transformers for End-to-End Object Detection.

[ECCV 2022] This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.