AI Paper Atlas

Research map / 3D vision / 3D generation

Pano3D: Unified 3D Reconstruction and Panoptic Segmentation

Victor Barberteguy, Ahmet Iscen, Mathilde Caron, Alireza Fathi, Gül Varol, Cordelia Schmid

ECCV 2026 · 3D vision › 3D generation · approach: Learning 3D reconstruction from images · 2 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
joint finetuning of geometry decoder and segmentation head vs frozen backbone (ablation)Pano3D (MUSt3R) · ScanNet valAP3D: 10.8 -> 15.7Improved
joint finetuning vs frozen backbone (ablation)Pano3D (MUSt3R) · ScanNet val3D mIoU: 61.9 -> 65.3Improved
finetune semantics only without geometry loss (ablation)Pano3D (MUSt3R) · ScanNet valAbsRel (MVD): 3.5 -> 156.3Hurt
joint training vs frozen MUSt3R for multi-view depth (ablation)Pano3D (MUSt3R) · ScanNet valAbsRel (MVD): 5.2 -> 3.5Improved
unfreeze encoder for end-to-end training (ablation)Pano3D (MUSt3R) · ScanNet val3D mIoU: 65.3 -> 63.4 mIoU3D; AP 15.7 -> 16.6; AbsRel 3.5 -> 3.3Mixed
combine encoder and decoder features (ablation)Pano3D (MUSt3R) · ScanNet val3D mIoU: 60.4 -> 65.3Improved
use decoder features only (no encoder skip) (ablation)Pano3D (MUSt3R) · ScanNet val3D mIoU: 65.3 -> 63.8Hurt
use equal geometry and semantic loss weights (ablation)Pano3D (MUSt3R) · ScanNet valAbsRel (MVD): 3.5 -> 5.1Hurt
raise geometry weight to 20x semantic (ablation)Pano3D (MUSt3R) · ScanNet val3D mIoU: 65.3 -> 63.3Mixed
scale segmentation gradients into geometry decoder by 0.1 (ablation)Pano3D (Pi3) · ScanNet++MVD AbsRel: 2.95 -> 2.77Improved
scale segmentation gradients by 0.1 (ablation)Pano3D (Pi3) · ScanNet++mIoU: 47.41 -> 44.91Hurt
add DINOv2 features to mask decoder (ablation)Pano3D · ScanNet valmIoU2D: 73.5 -> 71.7Hurt

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