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/wangyueft/detr3d

공식 코드

DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries

https://github.com/wangzcbruce/dhd

공식 코드

Drones Help Drones: A Collaborative Framework for Multi-Drone Object Trajectory Prediction and Beyond

https://github.com/wb014/FreeGS

공식 코드

Bootstraping Clustering of Gaussians for View-consistent 3D Scene Understanding

https://github.com/weiguangzhao/PBNet

공식 코드

Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization

https://github.com/weijiemax/lssinst

공식 코드

LSSInst: Improving Geometric Modeling in LSS-Based BEV Perception with Instance Representation

https://github.com/weiyangdaren/streamdsgn-pytorch

공식 코드

Real-time Stereo-based 3D Object Detection for Streaming Perception

https://github.com/weiyithu/FGR

공식 코드

FGR: Frustum-Aware Geometric Reasoning for Weakly Supervised 3D Vehicle Detection

https://github.com/weiyithu/lidar-distillation

공식 코드

LiDAR Distillation: Bridging the Beam-Induced Domain Gap for 3D Object Detection

https://github.com/weiyithu/surroundocc

공식 코드

SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving

https://github.com/whxuuuu/vision-communication-dataset

공식 코드

Computer Vision Aided mmWave Beam Alignment in V2X Communications

https://github.com/woodwindhu/dts

공식 코드

Density-Insensitive Unsupervised Domain Adaption on 3D Object Detection

https://github.com/woxihuanjiangguo/bevnext

공식 코드

BEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detection

https://github.com/wyf-accept/backtoreality

공식 코드

Back to Reality: Weakly-supervised 3D Object Detection with Shape-guided Label Enhancement

https://github.com/wzzheng/hass

공식 코드

Hardness-Aware Scene Synthesis for Semi-Supervised 3D Object Detection

https://github.com/xaviergrool/fgfusion

공식 코드

FGFusion: Fine-Grained Lidar-Camera Fusion for 3D Object Detection

https://github.com/xharlie/btcdet

공식 코드

Behind the Curtain: Learning Occluded Shapes for 3D Object Detection

https://github.com/xiangxu-0103/lima

공식 코드

Beyond One Shot, Beyond One Perspective: Cross-View and Long-Horizon Distillation for Better LiDAR Representations

https://github.com/xiaoaoran/polarmix

공식 코드

PolarMix: A General Data Augmentation Technique for LiDAR Point Clouds

https://github.com/xiaohao-xu/unified-pretrain-ad

공식 코드

Learning Shared RGB-D Fields: Unified Self-supervised Pre-training for Label-efficient LiDAR-Camera 3D Perception

https://github.com/xiaohaoChen/rrc_detection

공식 코드

Accurate Single Stage Detector Using Recurrent Rolling Convolution

https://github.com/xiaohulugo/ScAR-Scaling-Adversarial-Robustness-for-LiDAR-Object-Detection

공식 코드

ScAR: Scaling Adversarial Robustness for LiDAR Object Detection

https://github.com/xiaohulugo/scar-iros2023

공식 코드

ScAR: Scaling Adversarial Robustness for LiDAR Object Detection

https://github.com/xinge008/Cylinder3D

공식 코드

Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentation

https://github.com/xinge008/SSN

공식 코드

SSN: Shape Signature Networks for Multi-class Object Detection from Point Clouds

https://github.com/xingyizhou/CenterNet

공식 코드

Objects as Points

https://github.com/xingyu-group/3d-density-resampling-sdg

공식 코드

Domain Generalization of 3D Object Detection by Density-Resampling

https://github.com/xinshuoweng/mono3D_PLiDAR

공식 코드

Monocular 3D Object Detection with Pseudo-LiDAR Point Cloud

https://github.com/xinzhuma/3dodi-survey

공식 코드

3D Object Detection from Images for Autonomous Driving: A Survey

https://github.com/xinzhuma/monodle

공식 코드

Delving into Localization Errors for Monocular 3D Object Detection

https://github.com/xjtlu-cvlab/3drom

공식 코드

3D Random Occlusion and Multi-Layer Projection for Deep Multi-Camera Pedestrian Localization

https://github.com/xjtu-haolin/point_assisted_sample_selection

공식 코드

Leveraging Anchor-based LiDAR 3D Object Detection via Point Assisted Sample Selection

https://github.com/xmuqimingxia/dota

공식 코드

Learning to Detect Objects from Multi-Agent LiDAR Scans without Manual Labels

https://github.com/xmuqimingxia/sp3d

공식 코드

SP3D: Boosting Sparsely-Supervised 3D Object Detection via Accurate Cross-Modal Semantic Prompts

https://github.com/xuxw98/backtoreality

공식 코드

Back to Reality: Weakly-supervised 3D Object Detection with Shape-guided Label Enhancement

https://github.com/xuxw98/dspdet3d

공식 코드

3D Small Object Detection with Dynamic Spatial Pruning

https://github.com/xuyangbai/transfusion

공식 코드

TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers

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