Papers with Code · CC BY-SA 4.0

KITTI Eigen split unsupervised

아카이브 평가 55건 · 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 0.071 RMSE 3.662 Sq Rel 0.531 RMSE log 0.153 Delta < 1.25 0.94 Delta < 1.25^2 0.973 Delta < 1.25^3 0.985 Resolution 1024x320 Mono X Test frames 1	SPIdepth: Strengthened Pose Information for Self-supervised Monocular Depth Estimation 2024-04-18	코드 1
PlaneDepth (S + 1280x384)	absolute relative error 0.084 RMSE 3.981 Sq Rel 0.549 RMSE log 0.169 Delta < 1.25 0.911 Delta < 1.25^2 0.968 Delta < 1.25^3 0.984 Resolution 1280x384 Mono X	PlaneDepth: Self-supervised Depth Estimation via Orthogonal Planes 2022-10-04	코드 1
ProDepth	absolute relative error 0.086 RMSE 4.139 Sq Rel 0.629 RMSE log 0.166 Delta < 1.25 0.918 Delta < 1.25^2 0.969 Delta < 1.25^3 0.984 Resolution 640x192 Mono O Test frames 2(-1,0)	ProDepth: Boosting Self-Supervised Multi-Frame Monocular Depth with Probabilistic Fusion 2024-07-12	코드 1
Jasmine	absolute relative error 0.09 RMSE 3.944 Sq Rel 0.581 RMSE log 0.161 Delta < 1.25 0.919 Delta < 1.25^2 0.972 Delta < 1.25^3 0.986 Resolution 1024x320 Mono O	Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimation 2025-03-20	연결 없음
SCIPaD	absolute relative error 0.090 RMSE 4.056 Sq Rel 0.650 RMSE log 0.166 Delta < 1.25 0.918 Delta < 1.25^2 0.970 Delta < 1.25^3 0.985 Resolution 640x192	SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learning 2024-07-07	코드 1
DCPI-Depth (M+1024x320)	absolute relative error 0.090 RMSE 4.113 Sq Rel 0.655 RMSE log 0.167 Delta < 1.25 0.914 Delta < 1.25^2 0.969 Delta < 1.25^3 0.985 Mono O	DCPI-Depth: Explicitly Infusing Dense Correspondence Prior to Unsupervised Monocular Depth Estimation 2024-05-27	연결 없음
EPCDepth(S+1024x320)	absolute relative error 0.091 RMSE 4.207 Sq Rel 0.646 RMSE log 0.176 Delta < 1.25 0.901 Delta < 1.25^2 0.966 Delta < 1.25^3 0.983 Resolution 1024x320 Mono X	Excavating the Potential Capacity of Self-Supervised Monocular Depth Estimation 2021-09-26	코드 1
Manydepth2(M+640x192)	absolute relative error 0.091 RMSE 4.232 Sq Rel 0.649 RMSE log 0.170 Delta < 1.25 0.909 Delta < 1.25^2 0.968 Delta < 1.25^3 0.984 Resolution 640x192 Mono O	Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic Scenes 2023-12-23	코드 1
NimbleD-LiteMono-8M	absolute relative error 0.092 RMSE 4.194 Sq Rel 0.646 RMSE log 0.165 Delta < 1.25 0.910 Delta < 1.25^2 0.970 Delta < 1.25^3 0.986 Resolution 640x192 Mono O	NimbleD: Enhancing Self-supervised Monocular Depth Estimation with Pseudo-labels and Large-scale Video Pre-training 2024-08-26	코드 1
MonoViT(MS+1024x320)	absolute relative error 0.093 RMSE 4.202 Sq Rel 0.671 RMSE log 0.169 Delta < 1.25 0.912 Delta < 1.25^2 0.969 Delta < 1.25^3 0.985 Resolution 1024x320 Mono X	MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformer 2022-08-06	코드 1
Manydepth2-NF(M+640x192)	absolute relative error 0.094 RMSE 4.246 Sq Rel 0.676 RMSE log 0.170 Delta < 1.25 0.909 Delta < 1.25^2 0.968 Delta < 1.25^3 0.985 Resolution 640x192 Mono O	Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic Scenes 2023-12-23	코드 1
DIFFNet (MS+1024x320)	absolute relative error 0.094 RMSE 4.250 Sq Rel 0.678 RMSE log 0.172 Delta < 1.25 0.911 Delta < 1.25^2 0.968 Delta < 1.25^3 0.984 Mono X	Self-Supervised Monocular Depth Estimation with Internal Feature Fusion 2021-10-18	코드 1
DCPI-Depth (M+640x192)	absolute relative error 0.095 RMSE 4.274 Sq Rel 0.662 RMSE log 0.170 Delta < 1.25 0.902 Delta < 1.25^2 0.967 Delta < 1.25^3 0.985	DCPI-Depth: Explicitly Infusing Dense Correspondence Prior to Unsupervised Monocular Depth Estimation 2024-05-27	연결 없음
TransDSSL	absolute relative error 0.095 RMSE 4.321 Sq Rel 0.711 RMSE log 0.172 Delta < 1.25 0.906 Delta < 1.25^2 0.967 Delta < 1.25^3 0.984 Mono O	TransDSSL: Transformer based Depth Estimation via Self-Supervised Learning 2022-08-05	코드 1
DS-Depth	absolute relative error 0.095 RMSE 4.329 Sq Rel 0.698 RMSE log 0.173 Delta < 1.25 0.905 Delta < 1.25^2 0.966 Delta < 1.25^3 0.984	DS-Depth: Dynamic and Static Depth Estimation via a Fusion Cost Volume 2023-08-14	코드 1
ProDepth(M+640x192)	absolute relative error 0.095 RMSE 4.345 Sq Rel 0.693 RMSE log 0.172 Delta < 1.25 0.902 Delta < 1.25^2 0.967 Delta < 1.25^3 0.985 Resolution 640x192 Mono O	ProDepth: Boosting Self-Supervised Multi-Frame Monocular Depth with Probabilistic Fusion 2024-07-12	코드 1
CADepth-Net (MS+1024x320)	absolute relative error 0.096 RMSE 4.264 Sq Rel 0.694 RMSE log 0.173	Channel-Wise Attention-Based Network for Self-Supervised Monocular Depth Estimation 2021-12-24	코드 1
NimbleD-LiteMono	absolute relative error 0.096 RMSE 4.304 Sq Rel 0.684 RMSE log 0.171 Delta < 1.25 0.903 Delta < 1.25^2 0.969 Delta < 1.25^3 0.986 Resolution 640x192 Mono O	NimbleD: Enhancing Self-supervised Monocular Depth Estimation with Pseudo-labels and Large-scale Video Pre-training 2024-08-26	코드 1
Nimbled-SwiftDepth	absolute relative error 0.096 RMSE 4.333 Sq Rel 0.697 RMSE log 0.171 Delta < 1.25 0.905 Delta < 1.25^2 0.969 Delta < 1.25^3 0.986 Resolution 640x192 Mono O	NimbleD: Enhancing Self-supervised Monocular Depth Estimation with Pseudo-labels and Large-scale Video Pre-training 2024-08-26	코드 1
DynamicDepth (M+640x192)	absolute relative error 0.096 RMSE 4.458 Sq Rel 0.720 RMSE log 0.175 Delta < 1.25 0.897 Delta < 1.25^2 0.964 Delta < 1.25^3 0.984 Mono X	Disentangling Object Motion and Occlusion for Unsupervised Multi-frame Monocular Depth 2022-03-29	코드 1
Nimbled-MD2-R50	absolute relative error 0.097 RMSE 4.377 Sq Rel 0.721 RMSE log 0.172 Delta < 1.25 0.904 Delta < 1.25^2 0.968 Delta < 1.25^3 0.985 Resolution 640x192 Mono O	NimbleD: Enhancing Self-supervised Monocular Depth Estimation with Pseudo-labels and Large-scale Video Pre-training 2024-08-26	코드 1
SCIPaD(M+640x192)	absolute relative error 0.098 RMSE 4.391 Sq Rel 0.732 RMSE log 0.175 Delta < 1.25 0.897 Delta < 1.25^2 0.964 Delta < 1.25^3 0.983 Resolution 640x192 Mono O	SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learning 2024-07-07	코드 1
Nimbled-SwiftDepth-S	absolute relative error 0.098 RMSE 4.401 Sq Rel 0.733 RMSE log 0.174 Delta < 1.25 0.901 Delta < 1.25^2 0.968 Delta < 1.25^3 0.985 Resolution 640x192 Mono O	NimbleD: Enhancing Self-supervised Monocular Depth Estimation with Pseudo-labels and Large-scale Video Pre-training 2024-08-26	코드 1
CREMono(M + 1024x320 + Res50)	absolute relative error 0.099 RMSE 4.165 Sq Rel 0.624 RMSE log 0.171 Delta < 1.25 0.902 Delta < 1.25^2 0.969 Delta < 1.25^3 0.986	Towards Comprehensive Representation Enhancement in Semantics-guided Self-supervised Monocular Depth Estimation 2022-10-23	연결 없음
NimbleD-LiteMono-S	absolute relative error 0.099 RMSE 4.370 Sq Rel 0.709 RMSE log 0.172 Delta < 1.25 0.898 Delta < 1.25^2 0.967 Delta < 1.25^3 0.986 Resolution 640x192 Mono O	NimbleD: Enhancing Self-supervised Monocular Depth Estimation with Pseudo-labels and Large-scale Video Pre-training 2024-08-26	코드 1
FeatDepth-MS	absolute relative error 0.099 RMSE 4.427 Sq Rel 0.697 RMSE log 0.184 Delta < 1.25 0.889 Delta < 1.25^2 0.963 Delta < 1.25^3 0.982	Feature-metric Loss for Self-supervised Learning of Depth and Egomotion 2020-07-21	코드 1
VTDepthB2 (stereo supervision)	absolute relative error 0.099 RMSE 4.439 Sq Rel 0.743 RMSE log 0.178 Delta < 1.25 0.904 Delta < 1.25^2 0.965 Delta < 1.25^3 0.983	Exploring Efficiency of Vision Transformers for Self-Supervised Monocular Depth Estimation 2022-12-27	코드 1
EPCDepth(S+640x192)	absolute relative error 0.099 RMSE 4.490 Sq Rel 0.754 RMSE log 0.183 Delta < 1.25 0.888 Delta < 1.25^2 0.963 Delta < 1.25^3 0.982	Excavating the Potential Capacity of Self-Supervised Monocular Depth Estimation 2021-09-26	코드 1
Nimbled-MD2-R18	absolute relative error 0.100 RMSE 4.440 Sq Rel 0.739 RMSE log 0.175 Delta < 1.25 0.898 Delta < 1.25^2 0.967 Delta < 1.25^3 0.985 Resolution 640x192 Mono O	NimbleD: Enhancing Self-supervised Monocular Depth Estimation with Pseudo-labels and Large-scale Video Pre-training 2024-08-26	코드 1
MonoDEVSNet	absolute relative error 0.101 RMSE 4.413 Sq Rel 0.703 Delta < 1.25 0.882 Delta < 1.25^2 0.962	Monocular Depth Estimation through Virtual-world Supervision and Real-world SfM Self-Supervision 2021-03-22	코드 1