AI Paper Atlas

Research map / 3D vision / Depth and stereo

R-MSFM: Recurrent Multi-Scale Feature Modulation for Monocular Depth Estimating

Zhongkai Zhou, Xinnan Fan, Pengfei Shi, Yuanxue Xin

ICCV 2021 · 3D vision › Depth and stereo · approach: Dense depth prediction and completion · 189 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 MSFM module at decoder beginning to the shared decoder (ablation)R-MSFM3-A · KITTI Eigen splitAbs Rel: 0.120 -> 0.114Improved
add MSFM module after third decoder conv layer (ablation)R-MSFM3-A · KITTI Eigen splitAbs Rel: 0.120 -> 0.118Improved
add a second MSFM module at both positions (ablation)R-MSFM3-C · KITTI Eigen splitAbs Rel: 0.114 -> 0.115No clear effect
replace Monodepth2 U-Net decoder with parameter-shared iterative decoder and truncated encoder (ablation)Monodepth2 · KITTI Eigen splitparameters: 14.3M -> 2.9MImproved
increase iterative updates from 1 to 3 (ablation)R-MSFM3 (1024x320) · KITTI Eigen splitAbs Rel: 0.137 -> 0.112Improved
increase iterative updates from 1 to 6 (ablation)R-MSFM6 (1024x320) · KITTI Eigen splitAbs Rel: 0.141 -> 0.108Improved
increase updates from 5 to 6 (ablation)R-MSFM6 (1024x320) · KITTI Eigen splitAbs Rel: 0.108 -> 0.108No clear effect
extend three updates to six updates (ablation)R-MSFM3-C · KITTI Eigen splitAbs Rel: 0.114 -> 0.112Improved
use ImageNet pretrained encoder (ablation)R-MSFM6 · KITTI Eigen splitAbs Rel: 0.126 -> 0.112Improved
increase input resolution from 640x192 to 1024x320R-MSFM6 · KITTI Eigen splitRMSE: 4.704 -> 4.470Improved
add stereo supervision (MS vs M)R-MSFM6 · KITTI Eigen splitAbs Rel: 0.112 -> 0.111No clear effect
R-MSFM6 versus Monodepth2 in parameters and RMSER-MSFM6 (1024x320) · KITTI Eigen splitRMSE: 4.701 -> 4.470Improved

Later papers that compared with this method

1 later accepted paper reports R-MSFM6 as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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