AI Paper Atlas

Research map / 3D vision / 3D generation

What VGGT Knows About Overlap: Probing Geometric Foundation Models for Co-Visibility

Filippo Ziliotto, Luciano Serafini, Lamberto Ballan, Tommaso Campari

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
train layer-wise MoE head on frozen VGGT (vs zero-shot)Co-VGGT · Gibson pairwiseGraph IoU*: 0.50 -> 0.85Improved
train layer-wise MoE head on frozen VGGT (vs zero-shot)Co-VGGT · Gibson multiviewGraph IoU*: 0.37 -> 0.74Improved
add |e_i-e_j| to pair features (ablation)Co-VGGT aggregator · Gibson multiviewGraph IoU*: 0.71 -> 0.74Improved
add e_i*e_j product to pair features (ablation)Co-VGGT aggregator · Gibson multiviewAUC: 0.71 -> 0.73Improved
add product feature to simple concatenation (ablation)Co-VGGT aggregator · Gibson multiviewGraph IoU*: 0.67 -> 0.71Improved
add layer-wise MoE over standard aggregation (ablation)Co-VGGT · Gibson multiviewGraph IoU*: 0.69 -> 0.74Improved
add layer-wise MoE over standard aggregation (ablation)Co-VGGT · HM3D multiviewGraph IoU*: 0.72 -> 0.76Improved
use all layers [1,24] instead of last 12 layers [14,24] (ablation)Co-VGGT MoE · Gibson multiviewAUC: 0.72 -> 0.73Improved
use all layers [1,24] instead of only last layer [24] (ablation)Co-VGGT MoE · Gibson multiviewGraph IoU*: 0.69 -> 0.74Improved
use all layers instead of only first 12 layers [1,12] (ablation)Co-VGGT MoE · Gibson pairwiseGraph IoU*: 0.30 -> 0.84Improved
use last 5 layers [19,24] for zero-shot similarity instead of all layers (ablation)Co-VGGT zero-shot · Gibson pairwiseGraph IoU*: 0.50 -> 0.52Improved
train on Gibson, test on HM3D (cross-domain)Co-VGGT · HM3D pairwiseGraph IoU*: 0.84 -> 0.81Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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