AI Paper Atlas

Research map / 3D vision / Human pose estimation

Reconstruction by Generation: 3D Multi-Object Scene Reconstruction from Sparse Observations

Andrii Zadaianchuk, Leonardo Barcellona, Lennard Schuenemann, Christian Gumbsch, Zehao Wang, Muhammad Zubair Irshad, Fabien Despinoy, Rahaf Aljundi, Efstratios Gavves, Sergey Zakharov

ECCV 2026 · 3D vision › Human pose estimation · approach: Category-level object pose estimation · 8 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 stereo-noise depth augmentation during training (ablation)RecGen · object-centric (HB, LM-O, ReOcS)ADD-SB: 0.078 -> 0.062Improved
add stereo-noise augmentation (ablation)RecGen · ArtVIP parts (synthetic)ADD-SB: 0.039 vs 0.043No clear effect
add pose z-score normalization (ablation)RecGen · object-centricADD-SB: 0.074 -> 0.062Improved
add pose normalization (ablation)RecGen · ArtVIP partsADD-SB: 0.056 -> 0.043Improved
add part-level training data (ablation)RecGen · ArtVIP partsCD_norm: 0.073 -> 0.033Improved
add part-level training data (ablation)RecGen · object-centricADD-SB: 0.060 vs 0.062No clear effect
initialize from pretrained TRELLIS weights (ablation)RecGen · object-centricADD-SB: 0.067 -> 0.062Improved
use 2-view instead of 1-view inputRecGen · LM-OCD_norm: 0.050 -> 0.056Hurt
use 2-view instead of 1-view inputRecGen · HBCD_norm: 0.032 -> 0.029Improved
joint shape-pose generation with pointmap conditioning vs SAM3DRecGen vs SAM3D · ArtVIP partsADD-SB@0.05: 45.8% -> 84.0%Improved
joint shape-pose generation vs SAM3DRecGen vs SAM3D · HBADD-SB@0.05: 54.6% -> 73.8%Improved
pick best of 5 samples by pointmap alignmentRecGen · HBCD_n: 0.031 -> 0.029Improved

Earlier methods this paper compares with

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