We present a scalable 3D reconstruction model that addresses a critical limitation in offline feed-forward methods: their computational and memory requirements grow quadratically w.r.t. the number of input images. Our approach is built on the key insight that this bottleneck stems from the varying-length Key-Value (KV) space representation of scene geometry, which we distill into a fixed-size Multi-Layer Perceptron (MLP) via test-time training. VGG-T3 (Visual Geometry Grounded Test Time Training) scales linearly w.r.t. the number of input views, similar to online models, and reconstructs a 1k image collection in just 54 seconds, achieving a 11.6× speed-up over baselines that rely on softmax attention. Since our method retains global scene aggregation capability, our point map reconstruction error outperforming other linear-time methods by large margins. Finally, we demonstrate visual localization capabilities of our model by querying the scene representation with unseen images.
@article{arxiv.2602.23361,
title = {VGG-T$^3$: Offline Feed-Forward 3D Reconstruction at Scale},
author = {Sven Elflein and Ruilong Li and Sérgio Agostinho and Zan Gojcic and Laura Leal-Taixé and Qunjie Zhou and Aljosa Osep},
journal= {arXiv preprint arXiv:2602.23361},
year = {2026}
}