Monocular Depth Estimation On Kitti Eigen

Métriques

absolute relative error

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	absolute relative error	Paper Title	Repository
CC	0.140	Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation
AFNet	0.044	Adaptive Fusion of Single-View and Multi-View Depth for Autonomous Driving
SIGNet	0.133	SIGNet: Semantic Instance Aided Unsupervised 3D Geometry Perception
PrimeDepth	0.079	PrimeDepth: Efficient Monocular Depth Estimation with a Stable Diffusion Preimage
DPT-Hybrid	0.062	Vision Transformers for Dense Prediction
VNL	0.072	Enforcing geometric constraints of virtual normal for depth prediction
UniK3D (FT, metric)	0.037	UniK3D: Universal Camera Monocular 3D Estimation
DINOv2 (ViT-g/14 frozen, w/ DPT decoder)	0.0652	DINOv2: Learning Robust Visual Features without Supervision
MAMo	0.049	MAMo: Leveraging Memory and Attention for Monocular Video Depth Estimation	-
D-Net	0.056	D-Net: A Generalised and Optimised Deep Network for Monocular Depth Estimation	-
ECoDepth	0.048	ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation
EVP	0.048	EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment
GLPDepth	0.057	Global-Local Path Networks for Monocular Depth Estimation with Vertical CutDepth
ScaleDepth-K	0.048	ScaleDepth: Decomposing Metric Depth Estimation into Scale Prediction and Relative Depth Estimation
3Net	0.126	Learning monocular depth estimation with unsupervised trinocular assumptions
DiPE	0.112	DiPE: Deeper into Photometric Errors for Unsupervised Learning of Depth and Ego-motion from Monocular Videos
AdaBins	0.058	AdaBins: Depth Estimation using Adaptive Bins
GASDA	0.149	Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimation
Marigold	0.099	Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation
Manydepth2	0.091	Manydepth2: Motion-Aware Self-Supervised Monocular Depth Estimation in Dynamic Scenes

0 of 79 row(s) selected.