Monocular Depth Estimation on KITTI Eigen split

158개 결과 · ⬇ CSV · JSON

absolute relative error 낮을수록 좋음

Rank	Model	absolute relative error	RMSE	Sq Rel	RMSE log	Delta < 1.25	Delta < 1.25^2	Delta < 1.25^3	Square relative error (SqRel)	Extra Training Data	Paper	Code	Year
1	SPIDepth	0.029	1.394	0.069	0.048	0.99	0.999	1.000	–	✓	SPIdepth: Strengthened Pose Information for Self-supervised Monocular Depth Estimation	Lavreniuk/SPIdepth	2024
2	UniK3D (FT, metric)	0.037	1.68	–	0.060	0.990	0.998	0.999	–		UniK3D: Universal Camera Monocular 3D Estimation	lpiccinelli-eth/UniK3D	2025
2	UniDepthV2 (FT, metric)	0.037	1.71	–	0.061	0.989	0.998	0.999	–	✓	UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler	lpiccinelli-eth/unidepth	2025
4	Metric3Dv2 (g2, FT, 80m, flip_aug_test)	0.039	1.766	–	0.060	0.989	0.998	1.000	–	✓	Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation	yvanyin/metric3d	2024
5	LightedDepth (Video Method)	0.041	1.748	0.107	0.059	0.989	0.998	0.999	–		LightedDepth: Video Depth Estimation in Light of Limited Inference View Angles	shngjz/lighteddepth	2023
5	FutureDepth	0.041	1.856	0.117	0.066	0.984	0.998	1.000	0.117		FutureDepth: Learning to Predict the Future Improves Video Depth Estimation		2024
7	UniDepth (Zero-shot)	0.042	1.75	–	0.064	0.986	0.998	0.999	–	✓	UniDepth: Universal Monocular Metric Depth Estimation	lpiccinelli-eth/unidepth · henry123-boy/SpaTracker · ibaiGorordo/ONNX-Unidepth-Monocular-Metric-Depth-Estimation	2024
8	SQLdepth (ConvNeXt-L)	0.043	1.698	0.105	0.064	0.983	0.998	0.999	–		SQLdepth: Generalizable Self-Supervised Fine-Structured Monocular Depth Estimation	hisfog/SfMNeXt-Impl	2023
9	AFNet	0.044	1.712	0.132	0.069	0.980	0.997	0.999	–		Adaptive Fusion of Single-View and Multi-View Depth for Autonomous Driving	junda24/afnet	2024
10	Depth Anything	0.046	1.896	0.121	0.069	0.982	0.998	1.000	–	✓	Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data	LiheYoung/Depth-Anything · spacewalk01/depth-anything-tensorrt · fabio-sim/Depth-Anything-ONNX · +4	2024
11	MetaPrompt-SD	0.047	1.928	0.125	0.071	0.981	0.998	1.000	–	✓	Harnessing Diffusion Models for Visual Perception with Meta Prompts	fudan-zvg/meta-prompts	2023
12	ECoDepth	0.048	1.966	0.139	0.074	0.979	0.998	1.000	–		ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation	aradhye2002/ecodepth	2024
12	ScaleDepth-K	0.048	1.987	0.136	0.073	0.98	0.998	1.000	–		ScaleDepth: Decomposing Metric Depth Estimation into Scale Prediction and Relative Depth Estimation	RuijieZhu94/mmdepth	2024
12	EVP	0.048	2.015	0.136	0.073	0.980	0.998	1.000	–		EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment	lavreniuk/evp	2023
12	GEDepth	0.048	2.044	0.142	0.076	0.9763	0.9972	0.9993	–		GEDepth: Ground Embedding for Monocular Depth Estimation	qcraftai/gedepth · yangyucheng000/Paper-3	2023
16	MAMo	0.049	1.984	0.13	0.072	0.977	0.998	0.9995	–		MAMo: Leveraging Memory and Attention for Monocular Video Depth Estimation		2023
17	SwinV2-L 1K-MIM	0.050	1.966	0.139	0.075	0.977	0.998	1.000	–		Revealing the Dark Secrets of Masked Image Modeling	SwinTransformer/MIM-Depth-Estimation	2022
17	IEBins	0.050	2.011	0.142	0.075	0.978	0.998	0.999	–		IEBins: Iterative Elastic Bins for Monocular Depth Estimation	shuweishao/iebins	2023
17	NDDepth	0.050	2.025	0.141	0.075	0.978	0.998	0.999	–		NDDepth: Normal-Distance Assisted Monocular Depth Estimation	ShuweiShao/NDDepth	2023
17	URCDC-Depth	0.050	2.032	0.142	0.076	0.977	0.997	0.999	–		URCDC-Depth: Uncertainty Rectified Cross-Distillation with CutFlip for Monocular Depth Estimation	shuweishao/urcdc-depth	2023