PK PyTorchKR Papers
Papers with Code · CC BY-SA 4.0

3D Object Detection

Object Detection › 3D Object Detection 939 평가 기록 93 datasets

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>

개요는 각 항목의 일부입니다. 위 탭에서 전체 기록을 페이지별로 탐색할 수 있습니다.

벤치마크

Papers with Code 아카이브의 데이터셋별 기록 예시입니다. 평가 조건과 지표 방향이 검증되지 않아 순위를 의미하지 않습니다.

Dataset기록된 모델 예시MetricPaperCode
EA-LSS
NDS: 0.78mAP: 0.77mATE: 0.23mASE: 0.21
논문 코드
DEST (based on V-DETR) (TTA)
mAP@0.25: 78.8mAP@0.5: 67.9
논문 코드
Point-GCC+TR3D+FF
mAP@0.25: 69.7mAP@0.5: 54.0
논문 코드
CIE
AP Medium: 20.95
논문 -
TRTConv
AP: 91.90 %
- -
TRTConv
AP: 80.38 %
- -
Far3D
NDS: 68.7Future Frame: false
논문 코드
3D-FCT
AP: 75.86%
논문 -
DSGN++
AP75: 67.37
논문 코드
3D-FCT
AP: 89.15%
논문 -
SA-Det3D
AP: 61.33%
논문 코드
3D-FCT
AP: 58.4%
논문 -

데이터셋

93개
nuScenesScanNetV2SUN-RGBD valKITTI Cars ModerateKITTI Cars EasyKITTI Cars HardnuScenes Camera OnlyKITTI Cyclists ModerateKITTI Cars ModerateKITTI Cyclists EasyKITTI Cyclists HardKITTI Pedestrians Moderate

논문

라이브러리

Papers with Code 리더보드 row에 연결된 구현 저장소입니다.

github.com/open-mmlab/OpenPCDet 2 논문
github.com/2023-MindSpore-1/ms-code-214/tree/main/frustum-pointnet 1 논문
github.com/2023-MindSpore-4/Code9/tree/main/PointNet2 1 논문
github.com/aaronfriedman6/MV3D_VoxelNet 1 논문
github.com/abdullahozer11/Segmentation-and-Classification-of-Objects-in-Point-Clouds 1 논문
github.com/ahmed-anas/thesis-pointnet 1 논문
github.com/alpemek/ais3d 1 논문
github.com/AlvesRobot/Deep-Learning-on-Point-Cloud-for-3D-Classification-and-Segmentation 1 논문

하위 태스크

M3 Monocular 3D Object Detection 16 데이터셋 · 72 rows MD Multiview Detection 5 데이터셋 · 32 rows 3O 3D Object Detection From Stereo Images 3 데이터셋 · 23 rows R3 Robust 3D Object Detection 2 데이터셋 · 6 rows RB Robust BEV Detection 0 데이터셋 · 0 rows