AI Paper Atlas

Research map / 3D vision / Depth and stereo

FrozenRecon: Pose-free 3D Scene Reconstruction with Frozen Depth Models

Guangkai Xu, Wei Yin, Hao Chen, Chunhua Shen, Kai Cheng, Feng Zhao

ICCV 2023 · 3D vision › Depth and stereo · approach: Foundation models for monocular geometry · 13 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 geometric consistency alignment module instead of directly optimizing per-frame depth (ablation)FrozenRecon · NYUF-score: 0.303 -> 0.622Improved
use global plus local scale-shift alignment instead of RCVD deformation map (ablation)FrozenRecon · NYUAbsRel: 0.153 -> 0.092Improved
add photometric constraint (ablation)FrozenRecon · ScanNetF-score: 0.169 -> 0.410Improved
add geometric constraint (ablation)FrozenRecon · ScanNetF-score: 0.323 -> 0.410Improved
add regularization constraint on anchor point weights (ablation)FrozenRecon · ScanNetF-score: 0.254 -> 0.410Improved
add global keyframe stage after local stage (ablation)FrozenRecon · NYUAbsRel: 0.111 -> 0.092Improved
add global keyframe stage after local stage (ablation)FrozenRecon · NYUChamfer C-l1: 0.091 -> 0.099Hurt
replace photometric constraint with optical-flow constraint (ablation)FrozenRecon · NYUF-score: 0.622 vs 0.627No clear effect
use pose-based keyframe sampling instead of flow-guided sampling (ablation)FrozenRecon · NYUF-score: 0.565 -> 0.622Improved
provide GT intrinsics only (ablation)FrozenRecon · NYUF-score: 0.622 -> 0.622No clear effect
provide GT poses (ablation)FrozenRecon · NYUF-score: 0.622 -> 0.662Improved
FrozenRecon vs baselines on outdoor KITTI depthFrozenRecon · KITTIAbsRel: 0.203 vs 0.112 (BoostingDepth-DROID)Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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