AI Paper Atlas

Research map / 3D vision / Face and shape

VGG-T$^3$: Offline Feed-Forward 3D Reconstruction at Scale

Sven Elflein, Ruilong Li, Sérgio Agostinho, Zan Gojcic, Laura Leal-Taixé, Qunjie Zhou, Aljosa Osep

CVPR 2026 · 3D vision › Face and shape · approach: Neural implicit surface reconstruction · 16 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
Initialize from pre-trained softmax-attention weights instead of training TTT from scratch (ablation)VGG-T3 · ScanNet++ 224x224 ablationmAA(30): 52.95 -> 72.16Improved
Use test-time-training linearization instead of T2R (ablation)VGG-T3 · ScanNet++ 224x224 ablationmAA(30): 66.27 -> 72.16Improved
Use test-time-training linearization instead of LoLCATs (ablation)VGG-T3 · ScanNet++ 224x224 ablationmAA(30): 62.87 -> 72.16Improved
Add ShortConv2D spatial mixing on values (ablation)VGG-T3 · ScanNet++ 224x224 ablationmAA(30): 72.16 -> 74.14Improved
Add ShortConv2D spatial mixing on values (ablation)VGG-T3 · ScanNet++ 224x224 ablationCD: 0.074 -> 0.066Improved
Use 2 TTT optimizer steps instead of 1 at test time for large collections (ablation)VGG-T3 · Chamfer distance for up to 2000 viewsChamfer DistanceImproved
Further increase optimizer steps beyond 2 (ablation)VGG-T3 · large image collectionsreconstruction qualityNo clear effect
Replace LayerNorm with L2 normalization on queries and keysVGG-T3 linearization · convergence from pre-trained weightsconvergence speedImproved
Replace softmax global attention with TTT MLP (linear time)VGGT · 1k images on 7scenesruntime: VGGT over 11 minutes -> 58 seconds (11.6x)Improved
Replace softmax global attention with TTT MLP (linear time)VGGT · ScanNet, Sintel, TUM camera poseATE: 0.035 -> 0.070 (ScanNet)Hurt
Replace softmax global attention with TTT MLP (linear time)VGGT · pointmap estimation DTUChamfer Distance: 1.537 -> 1.654Mixed
Shard images across GPUs for distributed TTT inferenceVGG-T3 · 2000 imageslatency (s): 230.7 -> 48.5 (1 to 4 GPUs)Improved

Earlier methods this paper compares with

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