AI Paper Atlas

Research map / 3D vision / Depth and stereo

EGformer: Equirectangular Geometry-biased Transformer for 360 Depth Estimation

Ilwi Yun, Chanyong Shin, Hyunku Lee, Hyuk-Jae Lee, Chae Eun Rhee

ICCV 2023 · 3D vision › Depth and stereo · approach: Depth from light field and defocus · 46 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
use EGformer instead of Panoformer360 depth estimation · Structured3D testAbs.rel: 0.0394 -> 0.0342Improved
use EGformer instead of Panoformer360 depth estimation · Pano3D testAbs.rel: 0.0699 -> 0.0660Improved
mix Panoformer-style and EH(V)-MSA blocks (MMEE-EEMM) instead of EH(V)-MSA only (ablation)EGformer · Structured3D testAbs.rel: 0.0375 -> 0.0342Improved
use horizontal-only attention instead of combined EH(V)-MSA (ablation)EGformer · Structured3D testAbs.rel: 0.0375 -> 0.0421Hurt
add Das (distance-aware score) (ablation)EGformer · Structured3D testAbs.rel: 0.0360 -> 0.0342Improved
add EaAR (ablation)EGformer · Structured3D testAbs.rel: 0.0363 -> 0.0342Improved
add ERPE, Das and EaAR over softmax attention with LePE (ablation)EGformer · Pano3D testAbs.rel: 0.0700 -> 0.0660Improved
use EH(V)-MSA instead of CSwin-style softmax+LePE attention in EEEE-E-EEEE (ablation)EGformer · Structured3D testAbs.rel: 0.0399 -> 0.0375Improved
set geometry bias level rho to 0.1 instead of 0.03 or 0.3 (ablation)EGformer · Structured3D (trained on S3D only)Abs.rel: 0.0347 / 0.0352 -> 0.0338Improved

Later papers that compared with this method

1 later accepted paper reports EGFormer as a baseline in their results tables; 1 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 2 of 2 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