AI Paper Atlas

Research map / 3D vision / Depth and stereo

M^2Depth: Self-supervised Two-Frame Multi-camera Metric Depth Estimation

Yingshuang Zou, Yikang Ding, Xi Qiu, Haoqian Wang, Haotian Zhang

ECCV 2024 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth

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 spatial cost volume to mono prior (ablation)M2Depth · DDADAbs. Rel.: 0.216 -> 0.212Improved
add temporal cost volume on top of spatial volume (ablation)M2Depth · DDADAbs. Rel.: 0.212 -> 0.197Improved
add spatial-temporal fusion (STF) module (ablation)M2Depth · DDADAbs. Rel.: 0.197 -> 0.194Improved
add depth edge loss (ablation)M2Depth · DDADAbs. Rel.: 0.194 -> 0.192Improved
add multi-grained feature fusion (SAM features) in mono prior (ablation)M2Depth · DDADAbs. Rel.: 0.192 -> 0.188Improved
use SAM features in both MFF and depth decoding (ablation)M2Depth · DDADAbs. Rel.: 0.188 -> 0.183Improved
MFF attention fusion instead of simple addition (VFF) (ablation)M2Depth · DDADAbs. Rel.: 0.185 -> 0.183Improved
SAM context features instead of FPN context features in decoder (ablation)M2Depth · DDADAbs. Rel.: 0.196 -> 0.191Improved
predict front-camera pose instead of concatenating all views (ablation)M2Depth · DDADAbs. Rel.: 0.189 -> 0.183Improved
adaptive depth sampling around mono prior vs fixed range (ablation)M2Depth · DDADAbs. Rel.: 0.195 -> 0.183Improved
increase depth bins from 16 to 32 (ablation)M2Depth · DDADAbs. Rel.: 0.194 -> 0.200No clear effect
increase input frames from two to three or four (ablation)M2Depth · DDADAbs. Rel.: 0.183 -> 0.185 (3 frames), 0.186 (4 frames)Hurt

Later papers that compared with this method

3 later accepted papers report M2Depth as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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