AI Paper Atlas

Research map / 3D vision / Depth and stereo

Easi3R: Estimating Disentangled Motion from DUSt3R Without Training

Xingyu Chen, Yue Chen, Yuliang Xiu, Andreas Geiger, Anpei Chen

ICCV 2025 · 3D vision › Depth and stereo · approach: Feed-forward 3D reconstruction · 76 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 A_ref mean attention map to segmentation (ablation)Easi3R segmentation · DAVIS-16 (w/o SAM2, DUSt3R backbone)JM: 53.1 -> 33.3 when removedImproved
add A_src mean attention map (ablation)Easi3R segmentation · DAVIS-16 (w/o SAM2, DUSt3R backbone)JM: 53.1 -> 45.1 when removedImproved
add A_src std attention map (ablation)Easi3R segmentation · DAVIS-16 (w/o SAM2, DUSt3R backbone)JM: 53.1 -> 42.3 when removedImproved
add A_ref std attention map (ablation)Easi3R segmentation · DAVIS-16 (w/o SAM2, DUSt3R backbone)JM: 53.1 -> 47.7 when removedImproved
add cross-frame feature clustering (ablation)Easi3R segmentation · DAVIS-16 (w/o SAM2, DUSt3R backbone)JM: 53.1 -> 40.0 when removedImproved
use window size 3 instead of 5 (ablation)Easi3R (MonST3R backbone) · DAVIS-16 (w/ SAM2)JM: 70.7 -> 76.0Improved
use window size 7 instead of 5 (ablation)Easi3R (MonST3R backbone) · DAVIS-16 (w/ SAM2)JM: 70.7 -> 66.9Hurt
use 16 clusters instead of 64 (ablation)Easi3R (MonST3R backbone) · DAVIS-16 (w/ SAM2)JM: 70.7 -> 67.4Hurt
use 32 clusters instead of 64 (ablation)Easi3R (MonST3R backbone) · DAVIS-16 (w/ SAM2)JM: 70.7 -> 71.6Improved
use fixed threshold 0.5 instead of Otsu (ablation)Easi3R (MonST3R backbone) · DAVIS-16 (w/ SAM2)JM: 70.7 -> 61.6Hurt
use fixed threshold 0.7 instead of Otsu (ablation)Easi3R (MonST3R backbone) · DAVIS-16 (w/ SAM2)JM: 70.7 -> 70.2No clear effect
re-weight only the reference decoder instead of both branches (ablation)Easi3R (DUSt3R backbone) · DyCheck poseATE: 0.030 -> 0.029Improved

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