AI Paper Atlas

Research map / 3D vision / Depth and stereo

BLASt3R: Bundle Adjustment of Any Image Set with Multi-View Matching and Monocular priors

Vincent Leroy, Philippe Weinzaepfel, Lojze Zust, Yohann Cabon, Jerome Revaud

ECCV 2026 · 3D vision › Depth and stereo · approach: Feed-forward 3D reconstruction · 1 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 multiple corrective depth channels (nz=16 instead of nz=1) (ablation)BLASt3R · Monocular depth, 10-dataset averageRel: 8.65 -> 4.87Improved
add multiple corrective depth channels (nz=16 instead of nz=1) (ablation)BLASt3R · Monocular depth, 10-dataset averagedelta1: 90.3 -> 96.2Improved
add multiple depth channels (nz=1 -> full) (ablation)BLASt3R · ETH3D dense reconstructionAccuracy mean: 0.104 -> 0.069Improved
add multiple depth channels (nz=1 -> full) (ablation)BLASt3R · 7-Scenes dense reconstructionAccuracy mean: 0.029 -> 0.021Improved
add multiple depth channels (nz=1 -> full) (ablation)BLASt3R · ETH3D dense reconstructionNormal consistency mean: 0.835 -> 0.881Improved
add multiple depth channels (nz=1 -> full) (ablation)BLASt3R · ETH3D dense reconstructionCompleteness mean: 0.045 -> 0.055Hurt
use depth-regularized BA instead of COLMAP BA (ablation)BLASt3R · Co3Dv2 (10 frames)mAA@30: 86.3 -> 88.2Improved
use depth-regularized BA instead of COLMAP BA (ablation)BLASt3R · RealEstate10K (10 frames)mAA@30: 80.2 -> 85.2Improved
use depth-regularized BA instead of COLMAP BA (ablation)BLASt3R · ETH3D-MVSmAA@30: 98.8 -> 98.5Hurt
use depth-regularized BA instead of COLMAP BA (ablation)BLASt3R · Tanks&Temples (full sequences)mAA@30: 78.5 -> 74.1Hurt
use calibrated intrinsics instead of uncalibratedBLASt3R · TUM-RGBD fr1ATE RMSE (cm), avg: 3.0 -> 2.5Improved
disable focal optimization in initial BA iterationsBLASt3R · RealEstate10K (10 frames)mAA@30: 85.2 -> 88.0Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 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