AI Paper Atlas

Research map / 3D vision / Depth and stereo

Mono-ViFI: A Unified Learning Framework for Self-supervised Single- and Multi-frame Monocular Depth Estimation

Jinfeng Liu, Lingtong Kong, Bo Li, Zerong Wang, Hong Gu, Jinwei Chen

ECCV 2024 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth · 23 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add temporal augmentation (VFI-synthesized virtual views) (ablation)Monodepth2 single-frame · CityscapesAbs Rel: 0.129 -> 0.119Improved
add scale-aware depth consistency on top of spatial augmentation (ablation)Monodepth2 single-frame · CityscapesAbs Rel: 0.122 -> 0.116Improved
add standard view depth consistency (ablation)Monodepth2 single-frame · CityscapesAbs Rel: 0.129 -> 0.117Improved
add motion-aware feature alignment instead of direct feature fusion (ablation)multi-frame fusion · CityscapesAbs Rel: 0.120 -> 0.114Improved
add occlusion-alleviated feature fusion (ablation)multi-frame fusion · CityscapesAbs Rel: 0.114 -> 0.111Improved
combine all components (SA, TA, SVDC, SADC) with fusion (ablation)multi-frame model · CityscapesAbs Rel: 0.111 -> 0.107Improved
swap VFI network among IFRNet, RIFE, AMT (ablation)Mono-ViFI multi-frame · KITTIAbs Rel: 0.099 / 0.100 / 0.099No clear effect
remove Fourier positional encoding of optical flow (ablation)multi-frame fusion · KITTI and Cityscapesdepth metricsHurt
share both encoder and decoder between single- and multi-frame models (ablation)Mono-ViFI · KITTI and Cityscapesdepth metricsHurt
fully separate single- and multi-frame models instead of sharing the encoder (ablation)Mono-ViFI · KITTI and Cityscapesdepth metricsNo clear effect
use large IFRNet in training, small in evaluation (ablation)Mono-ViFI multi-frame · KITTIdepth metricsNo clear effect
apply Mono-ViFI to Monodepth2 ResNet18 single-frame inferenceMonodepth2 · KITTI raw GTAbs Rel: 0.115 -> 0.105Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy