Depth Estimation on NYU-Depth V2

34개 결과 · ⬇ CSV · JSON

RMS

Rank	Model	RMS	RMSE	mAP	Paper	Code	Year
21	Semantic-aware NN	0.30	–	–	3D Ken Burns Effect from a Single Image	sniklaus/3d-ken-burns · ipeter50/ken-burns-effect · agmm/colab-3d-ken-burns · +1	2019
22	SwinV2-B 1K-MIM	0.304	–	–	Revealing the Dark Secrets of Masked Image Modeling	SwinTransformer/MIM-Depth-Estimation	2022
23	P3Depth	0.356	–	–	P3Depth: Monocular Depth Estimation with a Piecewise Planarity Prior	syscv/p3depth	2022
24	AdaBins	0.364	–	–	AdaBins: Depth Estimation using Adaptive Bins	shariqfarooq123/AdaBins · martius-lab/beta-nll · dylanauty/mde-biological-vision-systems · +8	2020
25	TransDepth (AGD+ ViT)	0.365	–	–	Transformer-Based Attention Networks for Continuous Pixel-Wise Prediction	ygjwd12345/TransDepth	2021
26	BTS	0.407	–	–	From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation	cleinc/bts · cogaplex-bts/bts · ShuweiShao/NDDepth · +11	2019
27	VNL	0.416	–	–	Enforcing geometric constraints of virtual normal for depth prediction	aim-uofa/AdelaiDepth · aim-uofa/depth · YvanYin/VNL_Monocular_Depth_Prediction	2019
28	Optimized, freeform	0.4325	–	–	Deep Optics for Monocular Depth Estimation and 3D Object Detection		2019
29	Freeform	0.433	–	–	Deep Optics for Monocular Depth Estimation and 3D Object Detection		2019
30	DORN	0.509	–	–	Deep Ordinal Regression Network for Monocular Depth Estimation	hufu6371/DORN · dontLoveBugs/DORN_pytorch · sjsu-smart-lab/Self-supervised-Monocular-Trained-Depth-Estimation-using-Self-attention-and-Discrete-Disparity-Volum · +2	2018
31	MS-CRF	0.586	–	–	Multi-Scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimation	danxuhk/ContinuousCRF-CNN · xuyingyue/DeepUnifiedCRF_iccv19	2017
32	PAD-Net	0.792	–	–	PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing		2018
33	Defocus/DepthNet (Normalized)	–	0.013	–	Focus on defocus: bridging the synthetic to real domain gap for depth estimation	dvl-tum/defocus-net	2020
34	A2J	–	–	8.61	A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Image	zhangboshen/A2J · bo-zhang-cs/CACNet-Pytorch	2019