Papers with Code · CC BY-SA 4.0

KITTI Eigen split

아카이브 평가 79건 · 마지막 적재/변경 2026-10-30

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
SPIDepth	absolute relative error 0.029 RMSE 1.394 Sq Rel 0.069 RMSE log 0.048 Delta < 1.25 0.99 Delta < 1.25^2 0.999 Delta < 1.25^3 1.000	SPIdepth: Strengthened Pose Information for Self-supervised Monocular Depth Estimation 2024-04-18	코드 1
UniK3D (FT, metric)	absolute relative error 0.037 RMSE 1.68 RMSE log 0.060 Delta < 1.25 0.990 Delta < 1.25^2 0.998 Delta < 1.25^3 0.999	UniK3D: Universal Camera Monocular 3D Estimation 2025-03-20	코드 1
UniDepthV2 (FT, metric)	absolute relative error 0.037 RMSE 1.71 RMSE log 0.061 Delta < 1.25 0.989 Delta < 1.25^2 0.998 Delta < 1.25^3 0.999	UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler 2025-02-27	코드 1
Metric3Dv2 (g2, FT, 80m, flip_aug_test)	absolute relative error 0.039 RMSE 1.766 RMSE log 0.060 Delta < 1.25 0.989 Delta < 1.25^2 0.998 Delta < 1.25^3 1.000	Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation 2024-03-22	코드 1
LightedDepth (Video Method)	absolute relative error 0.041 RMSE 1.748 Sq Rel 0.107 RMSE log 0.059 Delta < 1.25 0.989 Delta < 1.25^2 0.998 Delta < 1.25^3 0.999	LightedDepth: Video Depth Estimation in Light of Limited Inference View Angles 2023-01-01	코드 1
FutureDepth	absolute relative error 0.041 RMSE 1.856 Sq Rel 0.117 RMSE log 0.066 Delta < 1.25 0.984 Delta < 1.25^2 0.998 Delta < 1.25^3 1.000 Square relative error (SqRel) 0.117	FutureDepth: Learning to Predict the Future Improves Video Depth Estimation 2024-03-19	연결 없음
UniDepth (Zero-shot)	absolute relative error 0.042 RMSE 1.75 RMSE log 0.064 Delta < 1.25 0.986 Delta < 1.25^2 0.998 Delta < 1.25^3 0.999	UniDepth: Universal Monocular Metric Depth Estimation 2024-03-27	코드 1 · 코드 2 · 코드 3
SQLdepth (ConvNeXt-L)	absolute relative error 0.043 RMSE 1.698 Sq Rel 0.105 RMSE log 0.064 Delta < 1.25 0.983 Delta < 1.25^2 0.998 Delta < 1.25^3 0.999	SQLdepth: Generalizable Self-Supervised Fine-Structured Monocular Depth Estimation 2023-09-01	코드 1
AFNet	absolute relative error 0.044 RMSE 1.712 Sq Rel 0.132 RMSE log 0.069 Delta < 1.25 0.980 Delta < 1.25^2 0.997 Delta < 1.25^3 0.999	Adaptive Fusion of Single-View and Multi-View Depth for Autonomous Driving 2024-03-12	코드 1
Depth Anything	absolute relative error 0.046 RMSE 1.896 Sq Rel 0.121 RMSE log 0.069 Delta < 1.25 0.982 Delta < 1.25^2 0.998 Delta < 1.25^3 1.000	Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data 2024-01-19	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7
MetaPrompt-SD	absolute relative error 0.047 RMSE 1.928 Sq Rel 0.125 RMSE log 0.071 Delta < 1.25 0.981 Delta < 1.25^2 0.998 Delta < 1.25^3 1.000	Harnessing Diffusion Models for Visual Perception with Meta Prompts 2023-12-22	코드 1
ECoDepth	absolute relative error 0.048 RMSE 1.966 Sq Rel 0.139 RMSE log 0.074 Delta < 1.25 0.979 Delta < 1.25^2 0.998 Delta < 1.25^3 1.000	ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation 2024-03-27	코드 1
ScaleDepth-K	absolute relative error 0.048 RMSE 1.987 Sq Rel 0.136 RMSE log 0.073 Delta < 1.25 0.98 Delta < 1.25^2 0.998 Delta < 1.25^3 1.000	ScaleDepth: Decomposing Metric Depth Estimation into Scale Prediction and Relative Depth Estimation 2024-07-11	코드 1
EVP	absolute relative error 0.048 RMSE 2.015 Sq Rel 0.136 RMSE log 0.073 Delta < 1.25 0.980 Delta < 1.25^2 0.998 Delta < 1.25^3 1.000	EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment 2023-12-13	코드 1
GEDepth	absolute relative error 0.048 RMSE 2.044 Sq Rel 0.142 RMSE log 0.076 Delta < 1.25 0.9763 Delta < 1.25^2 0.9972 Delta < 1.25^3 0.9993	GEDepth: Ground Embedding for Monocular Depth Estimation 2023-09-18	코드 1 · 코드 2
MAMo	absolute relative error 0.049 RMSE 1.984 Sq Rel 0.13 RMSE log 0.072 Delta < 1.25 0.977 Delta < 1.25^2 0.998 Delta < 1.25^3 0.9995	MAMo: Leveraging Memory and Attention for Monocular Video Depth Estimation 2023-07-26	연결 없음
SwinV2-L 1K-MIM	absolute relative error 0.050 RMSE 1.966 Sq Rel 0.139 RMSE log 0.075 Delta < 1.25 0.977 Delta < 1.25^2 0.998 Delta < 1.25^3 1.000	Revealing the Dark Secrets of Masked Image Modeling 2022-05-26	코드 1
IEBins	absolute relative error 0.050 RMSE 2.011 Sq Rel 0.142 RMSE log 0.075 Delta < 1.25 0.978 Delta < 1.25^2 0.998 Delta < 1.25^3 0.999	IEBins: Iterative Elastic Bins for Monocular Depth Estimation 2023-09-25	코드 1
NDDepth	absolute relative error 0.050 RMSE 2.025 Sq Rel 0.141 RMSE log 0.075 Delta < 1.25 0.978 Delta < 1.25^2 0.998 Delta < 1.25^3 0.999	NDDepth: Normal-Distance Assisted Monocular Depth Estimation 2023-09-19	코드 1
URCDC-Depth	absolute relative error 0.050 RMSE 2.032 Sq Rel 0.142 RMSE log 0.076 Delta < 1.25 0.977 Delta < 1.25^2 0.997 Delta < 1.25^3 0.999	URCDC-Depth: Uncertainty Rectified Cross-Distillation with CutFlip for Monocular Depth Estimation 2023-02-16	코드 1
iDisc	absolute relative error 0.050 RMSE 2.067 Sq Rel 0.145 RMSE log 0.077 Delta < 1.25 0.977 Delta < 1.25^2 0.997 Delta < 1.25^3 0.999	iDisc: Internal Discretization for Monocular Depth Estimation 2023-04-13	코드 1 · 코드 2
DDP (Swin-L, step-3)	absolute relative error 0.050 RMSE 2.072 Sq Rel 0.148 RMSE log 0.076 Delta < 1.25 0.975 Delta < 1.25^2 0.997 Delta < 1.25^3 0.999	DDP: Diffusion Model for Dense Visual Prediction 2023-03-30	코드 1
MIM-Swin-V2	absolute relative error 0.0508 RMSE 2.0373 Sq Rel 0.1458 RMSE log 0.077 Delta < 1.25 0.9757 Delta < 1.25^2 0.9974 Delta < 1.25^3 0.9994	Analysis of NaN Divergence in Training Monocular Depth Estimation Model 2023-11-07	연결 없음
PixelFormer	absolute relative error 0.051 RMSE 2.081 Sq Rel 0.149 RMSE log 0.077 Delta < 1.25 0.976 Delta < 1.25^2 0.997 Delta < 1.25^3 0.999	Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention 2022-10-17	코드 1
SwinV2-B 1K-MIM	absolute relative error 0.052 RMSE 2.050 Sq Rel 0.148 RMSE log 0.078 Delta < 1.25 0.976 Delta < 1.25^2 0.998 Delta < 1.25^3 0.999	Revealing the Dark Secrets of Masked Image Modeling 2022-05-26	코드 1
BinsFormer	absolute relative error 0.052 RMSE 2.098 Sq Rel 0.151 RMSE log 0.079 Delta < 1.25 0.974 Delta < 1.25^2 0.997 Delta < 1.25^3 0.999	BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimation 2022-04-03	코드 1 · 코드 2
NeWCRFs	absolute relative error 0.052 RMSE 2.129 Sq Rel 0.155 RMSE log 0.079 Delta < 1.25 0.974 Delta < 1.25^2 0.997 Delta < 1.25^3 0.999	NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation 2022-03-03	코드 1
DepthFormer	absolute relative error 0.052 RMSE 2.143 Sq Rel 0.158 RMSE log 0.079 Delta < 1.25 0.975 Delta < 1.25^2 0.997 Delta < 1.25^3 0.999	DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimation 2022-03-27	코드 1
MonoDELSNet	absolute relative error 0.053 RMSE 2.101 Sq Rel 0.161 RMSE log 0.082 Delta < 1.25 0.969 Delta < 1.25^2 0.996 Delta < 1.25^3 0.999	Monocular Depth Estimation through Virtual-world Supervision and Real-world SfM Self-Supervision 2021-03-22	코드 1
SfM-Revisited	absolute relative error 0.055 RMSE 2.273 Sq Rel 0.224	Deep Two-View Structure-from-Motion Revisited 2021-04-01	코드 1