3D Object Detection On Scannetv2

Métriques

mAP@0.25

mAP@0.5

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	mAP@0.25	mAP@0.5	Paper Title	Repository
BFL	74.6	65.3	-	-
TR3D	72.9	59.3	TR3D: Towards Real-Time Indoor 3D Object Detection
RBGNet	70.6	55.2	RBGNet: Ray-based Grouping for 3D Object Detection
HGNet	61.3	34.4	A Hierarchical Graph Network for 3D Object Detection on Point Clouds	-
PBNet	69.3	60.1	Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization
V-DETR	77.8	65.9	V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection
Point-GCC+TR3D	73.1	59.6	Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast
BRNet	66.1	50.9	Back-tracing Representative Points for Voting-based 3D Object Detection in Point Clouds
SoftGroup	71.6	59.4	SoftGroup for 3D Instance Segmentation on Point Clouds
GSDN	62.8	34.8	Generative Sparse Detection Networks for 3D Single-shot Object Detection
SPGroup3D	74.3	59.6	SPGroup3D: Superpoint Grouping Network for Indoor 3D Object Detection
H3DNet	67.2	48.1	H3DNet: 3D Object Detection Using Hybrid Geometric Primitives
ImGeoNet (RGB only)	54.8	28.4	ImGeoNet: Image-induced Geometry-aware Voxel Representation for Multi-view 3D Object Detection
VoteNet	58.6	33.5	Deep Hough Voting for 3D Object Detection in Point Clouds
GroupFree3D	69.1	52.8	Group-Free 3D Object Detection via Transformers
Swin3D-L+CAGroup3D	76.4	63.2	Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding
OneFormer3D	76.9	65.3	OneFormer3D: One Transformer for Unified Point Cloud Segmentation
TokenFusion	70.8	54.2	Multimodal Token Fusion for Vision Transformers
UniDet3D	77.5	66.1	UniDet3D: Multi-dataset Indoor 3D Object Detection
DEST (based on V-DETR) (TTA)	78.8	67.9	-	-

0 of 33 row(s) selected.