AI Paper Atlas

Research map / 3D vision / Depth and stereo

DoubleTake: Geometry Guided Depth Estimation

Mohamed Sayed, Filippo Aleotti, Jamie Watson, Zawar Qureshi, Guillermo Garcia-Hernando, Gabriel Brostow, Sara Vicente, Michael Firman

ECCV 2024 · 3D vision › Depth and stereo · approach: Foundation models for monocular geometry · 7 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 geometry hint and confidence via Hint MLP to SimpleRecon (ablation)SimpleRecon · ScanNetV2 depth (incremental)Abs Diff: .0873 -> .0767Improved
run offline with two passes using first-pass TSDF as hintDoubleTake · ScanNetV2 depthAbs Diff: .0767 -> .0627Improved
provide no hint at test time (ablation)DoubleTake · ScanNetV2 depthAbs Diff: .0873 vs .0870No clear effect
add confidence map to the Hint MLP input (ablation)DoubleTake · ScanNetV2 depth (incremental)Abs Diff: .0863 -> .0767Improved
feed hint into cost volume encoder instead of Hint MLP (ablation)DoubleTake · ScanNetV2 depth (incremental)Abs Diff: .0767 -> .0890Hurt
use forward-warped previous depth as hint instead of TSDF render (ablation)DoubleTake · ScanNetV2 depth (incremental)Abs Diff: .0767 -> .0889Hurt
replace Hint MLP with cost volume modulation or a single shared MLP (ablation)DoubleTake · ScanNetV2 depth (incremental)Abs Diff: .0767 vs .0773No clear effect
use long-term hints from a previous visit (revisit)DoubleTake · 3RScanAbs Diff: .1255 -> .1182Improved
add pose alignment noise in revisit mode (ablation)DoubleTake · 3RScanAbs Diff: .1182 -> .1199No clear effect
naively input a rendered depth of the global mesh into a depth networkdepth estimation network · ScanNetV2depth accuracyNo clear effect
DoubleTake incremental versus SimpleRecon on 7Scenes delta<1.25DoubleTake · 7Scenesdelta < 1.25: 97.33 -> 97.01Hurt

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