AI Paper Atlas

Research map / 3D vision / Depth and stereo

A Study on the Generality of Neural Network Structures for Monocular Depth Estimation

Jinwoo Bae, Kyumin Hwang, Sunghoon Im

TPAMI 2023 · 3D vision › Depth and stereo · approach: Dense depth prediction and completion · 27 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 ACM and FFD together (ablation)MonoFormer baseline · KITTI Eigen testAbs Rel: 0.113 -> 0.104Improved
add ACM only (ablation)MonoFormer baseline · KITTI Eigen testAbs Rel: 0.113 -> 0.113No clear effect
add FFD only (ablation)MonoFormer baseline · KITTI Eigen testAbs Rel: 0.113 -> 0.112Improved
use 4 transformer layers instead of 2 (ablation)MonoFormer · KITTI Eigen testAbs Rel: 0.148 -> 0.104Improved
use 4 transformer layers instead of 5 (ablation)MonoFormer · KITTI Eigen testAbs Rel: 0.111 -> 0.104Improved
use 4 transformer layers instead of 3 (ablation)MonoFormer · KITTI Eigen testAbs Rel: 0.112 -> 0.104Improved
replace CNN-Transformer encoder with ConvNeXt (ablation)MonoFormer · KITTI Eigen testAbs Rel: 0.104 -> 0.111Hurt
replace CNN-Transformer encoder with SLaK (ablation)MonoFormer · KITTI Eigen testAbs Rel: 0.104 -> 0.117Hurt
replace CNN-Transformer encoder with Twins (ablation)MonoFormer · KITTI Eigen testAbs Rel: 0.104 -> 0.125Hurt
replace CNN-Transformer encoder with plain ViT (ablation)MonoFormer · KITTI Eigen testAbs Rel: 0.104 -> 0.118Hurt
use ground-truth depth supervision instead of self-supervisiondepth networks · KITTI Eigen testAbs Rel: 0.104 -> 0.052Improved
use ConvNeXt (macro design mimicking attention) instead of other CNN encodersself-supervised MDE · out-of-distribution and texture-shifted datasetsgeneralizationImproved

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