HyperAI초신경

홈 뉴스 최신 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

3D Object Detection From Monocular Images On 7

평가 지표

AP25

AP50

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	AP25	AP50	Paper Title	Repository
MonoDETR	27.13	0.79	MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection
MonoDLE	28.99	0.85	Delving into Localization Errors for Monocular 3D Object Detection
VoteNet	30.61	3.40	Deep Hough Voting for 3D Object Detection in Point Clouds
SeaBird + Image2Maps	35.04	3.14	SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objects
MonoDTR	39.76	3.02	MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer
SeaBird + PanopticBEV	37.12	4.64	SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objects
Cube R-CNN	15.57	0.80	Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild
GrooMeD-NMS	16.12	0.17	GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection
BoxNet	23.59	4.08	Deep Hough Voting for 3D Object Detection in Point Clouds
GUPNet	27.25	0.87	Geometry Uncertainty Projection Network for Monocular 3D Object Detection
DEVIANT	26.96	0.88	DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection

0 of 11 row(s) selected.