VGG-T$^3$: Offline Feed-Forward 3D Reconstruction at Scale
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-T$^3$ (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 $11.6\times$ speed-up over baselines that...
| Authors | Sven Elflein, Ruilong Li, Sérgio Agostinho et al. |
|---|---|
| Primary category | cs.CV |
| Published | 26 February 2026 |
| Last updated at source | 26 February 2026 |
Popularity, last 2 days
0 now. Counts as reported by the source, snapshotted daily by Silytics.
Connected in the knowledge graph
- nvidia/vgg-tttModel · cited by
Models and datasets referencing this paper
- nvidia/vgg-tttModel
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 19 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.