AI Paper Atlas

Research map / 3D vision / Depth and stereo

Scal3R: Learning Efficient Multi-Relative Pose Query for Scalable Online 3D Reconstruction

Chin-Yang Lin, Yang-Che Sun, Cheng Sun, Fu-En Yang, Min-Hung Chen, Yen-Yu Lin, Wei-Chen Chiu, Yu-Lun Liu

ECCV 2026 · 3D vision › Depth and stereo · approach: Feed-forward 3D reconstruction · 0 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
replace global first-frame pose regression with multi-reference relative pose querying plus PGOCUT3R · KITTIATE avg: 207.2 -> 69.7Improved
add multi-reference training (3 references) versus no reference supervision (ablation)Scal3R (CUT3R) · vKITTIATE: 33.318 -> 5.632Improved
use multiple references instead of a single reference during training (ablation)Scal3R (CUT3R) · vKITTIATE: 15.764 -> 5.632Improved
add keyframe selection (ablation)Scal3R (CUT3R) · vKITTIATE: 38.258 -> 5.632Improved
add online pose-graph optimization (ablation)Scal3R (CUT3R) · vKITTIATE: 20.089 -> 5.632Improved
increase inference references from 4 to 12 (ablation)Scal3R (CUT3R) · vKITTIATE: 15.748 -> 5.632Improved
increase inference references from 12 to 24 (beyond training count) (ablation)Scal3R (CUT3R) · vKITTIATE: 5.63 -> 12.16Hurt
add loop closure (ablation)Scal3R (CUT3R) · KITTIATE avg: 143.45 -> 75.01Improved
use asymmetric instead of symmetric (VPT) attention injection (ablation)Scal3R (CUT3R) · vKITTIATE: 57.78 -> 5.63Improved
use asymmetric instead of symmetric attention injection (ablation)Scal3R (CUT3R) · Sintel / ScanNet (indoor)ATE: Sintel 0.154 vs 0.168; ScanNet 0.083 vs 0.092Mixed
add TTT3R on top of Scal3R posesScal3R · KITTIATE: 69.73 -> 62.05Improved
remove Sim(3) scale alignment at evaluation (ablation)Scal3R (CUT3R) · KITTIATE: 69.73 -> 88.66Hurt

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