AI Paper Atlas

Research map / 3D vision / Depth and stereo

HAMSt3R: Human-Aware Multi-view Stereo 3D Reconstruction

Sara Rojas, Matthieu Armando, Bernard Ghanem, Philippe Weinzaepfel, Vincent Leroy, Grégory Rogez

ICCV 2025 · 3D vision › Depth and stereo · approach: Feed-forward 3D reconstruction · 6 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 MASt3R encoder with DUNE distilled encoder and add human heads, trained with 50% human dataHAMSt3R · Multi-view depth (5 test sets average)rel: 3.13 -> 4.26Hurt
human-aware training on EgoExo4D camera poseHAMSt3R · EgoExo4D camera poseAE: 11.70 -> 2.85 (vs MASt3R)Improved
train HAMSt3R on top of DUNE for EgoHumans camera poseHAMSt3R · EgoHumans camera poseAE: 3.51 -> 10.24 (DUNE vs HAMSt3R)Hurt
evaluate on large open scenes versus small environments (ablation)HAMSt3R · EgoHumansAE: large 16.303; small 2.32Mixed
joint feed-forward reconstruction with SMPL fitting versus HSfM optimization on EgoExo4D world-coordinatesHAMSt3R · EgoExo4DW-MPJPE: 0.56 -> 0.51Improved
HAMSt3R versus HSfM on Procrustes-aligned pose on EgoHumansHAMSt3R · EgoHumansPA-MPJPE: 0.05 -> 0.14Hurt
feed-forward pipeline instead of optimization pipeline (HSfM)HAMSt3R · Runtime 4-view scenetotal runtime: ~118s -> ~32sImproved
human-aware training on RealEstate10K pose regressionHAMSt3R · RealEstate10KmAA(30): 76.4 -> 77.4 (vs MASt3R)Improved
human-aware training on CO3Dv2 pose regressionHAMSt3R · CO3Dv2mAA(30): 81.8 -> 76.3 (vs MASt3R)Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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