← Monocular Depth Estimation

Papers with Code · CC BY-SA 4.0

KITTI Eigen split

아카이브 평가 79건 · 마지막 적재/변경 2026-10-30

원본 데이터셋 링크 1

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
DeepLabV3+ (F10)	absolute relative error 0.110	Single Image Depth Estimation Trained via Depth from Defocus Cues 2020-01-14	코드 1
DiPE	absolute relative error 0.112	DiPE: Deeper into Photometric Errors for Unsupervised Learning of Depth and Ego-motion from Monocular Videos 2020-03-03	코드 1
DNet	absolute relative error 0.113 RMSE 4.812 RMSE log 0.191 Delta < 1.25 0.877 Delta < 1.25^2 0.960 Delta < 1.25^3 0.981	Toward Hierarchical Self-Supervised Monocular Absolute Depth Estimation for Autonomous Driving Applications 2020-04-12	코드 1
LSIM	absolute relative error 0.113	Learn Stereo, Infer Mono: Siamese Networks for Self-Supervised, Monocular, Depth Estimation 2019-05-01	코드 1
SC-Depth (ResNet 50)	absolute relative error 0.114 RMSE 4.706 RMSE log 0.191 Delta < 1.25 0.873 Delta < 1.25^2 0.960 Delta < 1.25^3 0.982	Unsupervised Scale-consistent Depth Learning from Video 2021-05-25	코드 1 · 코드 2
SemanticAware	absolute relative error 0.118	Towards Scene Understanding: Unsupervised Monocular Depth Estimation With Semantic-Aware Representation 2019-06-01	연결 없음
SC-Depth (ResNet18)	absolute relative error 0.119 RMSE 4.950 RMSE log 0.197 Delta < 1.25 0.863 Delta < 1.25^2 0.957 Delta < 1.25^3 0.981	Unsupervised Scale-consistent Depth Learning from Video 2021-05-25	코드 1 · 코드 2
PackNet-SfM	absolute relative error 0.12	3D Packing for Self-Supervised Monocular Depth Estimation 2019-05-06	코드 1 · 코드 2 · 코드 3 · 코드 4
3Net	absolute relative error 0.126	Learning monocular depth estimation with unsupervised trinocular assumptions 2018-08-05	코드 1
SC-SfMLearner_CS+K	absolute relative error 0.128	Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video 2019-08-28	코드 1 · 코드 2
SelfDepthNorm	absolute relative error 0.133	Self-supervised Learning for Single View Depth and Surface Normal Estimation 2019-03-01	연결 없음
SIGNet	absolute relative error 0.133	SIGNet: Semantic Instance Aided Unsupervised 3D Geometry Perception 2018-12-13	코드 1 · 코드 2
struct2depth	absolute relative error 0.135	Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos 2018-11-15	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9 · 코드 10 · 코드 11
SC-SfMLearner	absolute relative error 0.137	Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video 2019-08-28	코드 1 · 코드 2
CC	absolute relative error 0.140	Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation 2018-05-24	코드 1
SIW	absolute relative error 0.14	Scaling up Multi-domain Semantic Segmentation with Sentence Embeddings 2022-02-04	연결 없음
LeReS	absolute relative error 0.149 Delta < 1.25 0.784	Learning to Recover 3D Scene Shape from a Single Image 2020-12-17	코드 1
GASDA	absolute relative error 0.149	Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimation 2019-04-03	코드 1
VDA	absolute relative error 0.193	Veritatem Dies Aperit- Temporally Consistent Depth Prediction Enabled by a Multi-Task Geometric and Semantic Scene Understanding Approach 2019-03-26	코드 1