Papers with Code 아카이브

3D Object Detection

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 5
평가표: 67
보존된 평가 기록: 806

3D Object Detection is a task in computer vision where the goal is to identify and locate objects in a 3D environment based on their shape, location, and orientation. It involves detecting the presence of objects and determining their location in the 3D space in real-time. This task is crucial for applications such as autonomous vehicles, robotics, and augmented reality.

<span style="color:grey; opacity: 0.6">( Image credit: AVOD )</span>

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/tudelft-iv/unibev

공식 코드

UniBEV: Multi-modal 3D Object Detection with Uniform BEV Encoders for Robustness against Missing Sensor Modalities

https://github.com/tum-traffic-dataset/coopdet3d

공식 코드

TUMTraf V2X Cooperative Perception Dataset

https://github.com/tum-traffic-dataset/tum-traffic-dataset-dev-kit

공식 코드

TUMTraf V2X Cooperative Perception Dataset

https://github.com/tumftm/radargnn

공식 코드

RadarGNN: Transformation Invariant Graph Neural Network for Radar-based Perception

https://github.com/tusen-ai/mv2d

공식 코드

Object as Query: Lifting any 2D Object Detector to 3D Detection

https://github.com/tusen-ai/sst

공식 코드

Super Sparse 3D Object Detection

https://github.com/tusimple/centerformer

공식 코드

CenterFormer: Center-based Transformer for 3D Object Detection

https://github.com/tusimple/sst

공식 코드

Embracing Single Stride 3D Object Detector with Sparse Transformer

https://github.com/tydpan/gpc

공식 코드

Pre-Training LiDAR-Based 3D Object Detectors Through Colorization

https://github.com/uber/sbnet

공식 코드

SBNet: Sparse Blocks Network for Fast Inference

https://github.com/ucla-mobility/v2v4real

공식 코드

V2V4Real: A Real-world Large-scale Dataset for Vehicle-to-Vehicle Cooperative Perception

https://github.com/uddd821/hv-bev

공식 코드

HV-BEV: Decoupling Horizontal and Vertical Feature Sampling for Multi-View 3D Object Detection

https://github.com/umd-fire-coml/kitti-orientation-learning

공식 코드

SoK: Vehicle Orientation Representations for Deep Rotation Estimation

https://github.com/ut-amrl/coda-devkit

공식 코드

Towards Robust Robot 3D Perception in Urban Environments: The UT Campus Object Dataset

https://github.com/ut-amrl/coda-models

공식 코드

Towards Robust Robot 3D Perception in Urban Environments: The UT Campus Object Dataset

https://github.com/uulm-mrm/mmood3d

공식 코드

Revisiting Out-of-Distribution Detection in LiDAR-based 3D Object Detection

https://github.com/valeoai/slidr

공식 코드

Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Data

https://github.com/vdigpku/bev-mae

공식 코드

BEV-MAE: Bird's Eye View Masked Autoencoders for Point Cloud Pre-training in Autonomous Driving Scenarios

https://github.com/vdigpku/henet

공식 코드

HENet: Hybrid Encoding for End-to-end Multi-task 3D Perception from Multi-view Cameras

https://github.com/vdigpku/rcbevdet

공식 코드

RCBEVDet: Radar-camera Fusion in Bird's Eye View for 3D Object Detection

https://github.com/vdigpku/teocc

공식 코드

TEOcc: Radar-camera Multi-modal Occupancy Prediction via Temporal Enhancement

https://github.com/velatkilic/LISA

공식 코드

Lidar Light Scattering Augmentation (LISA): Physics-based Simulation of Adverse Weather Conditions for 3D Object Detection

https://github.com/viewformerocc/viewformer-occ

공식 코드

ViewFormer: Exploring Spatiotemporal Modeling for Multi-View 3D Occupancy Perception via View-Guided Transformers

https://github.com/viktorkare/bevf

공식 코드

Towards a Robust Sensor Fusion Step for 3D Object Detection on Corrupted Data

https://github.com/vision-agh/lift

공식 코드

LiFT: Lightweight, FPGA-tailored 3D object detection based on LiDAR data

https://github.com/vision-agh/pointpillars-backbone

공식 코드

PointPillars Backbone Type Selection For Fast and Accurate LiDAR Object Detection

https://github.com/visualaikhu/monowad

공식 코드

MonoWAD: Weather-Adaptive Diffusion Model for Robust Monocular 3D Object Detection

https://github.com/vita-epfl/monoloco

공식 코드

MonoLoco: Monocular 3D Pedestrian Localization and Uncertainty Estimation

https://github.com/vitae-transformer/bevsimdet

공식 코드

SimDistill: Simulated Multi-modal Distillation for BEV 3D Object Detection

https://github.com/vitae-transformer/simdistill

공식 코드

SimDistill: Simulated Multi-modal Distillation for BEV 3D Object Detection

https://github.com/vniclas/lidar_beam_selection

공식 코드

End-To-End Optimization of LiDAR Beam Configuration for 3D Object Detection and Localization

https://github.com/walzimmer/3d-bat

공식 코드

TUMTraf V2X Cooperative Perception Dataset

https://github.com/wangguojun2018/CenterNet3d

공식 코드

CenterNet3D: An Anchor Free Object Detector for Point Cloud

https://github.com/wangguojun2018/MVAF-Net

공식 코드

Multi-View Adaptive Fusion Network for 3D Object Detection

https://github.com/wangsch10/v2x-dgpe

공식 코드

V2X-DGPE: Addressing Domain Gaps and Pose Errors for Robust Collaborative 3D Object Detection

https://github.com/wangys16/ohda

공식 코드

Syn-to-Real Unsupervised Domain Adaptation for Indoor 3D Object Detection

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.