VGG-T$^3$: Offline Feed-Forward 3D Reconstruction at Scale
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917297276321792 |
|---|---|
| author | Elflein, Sven Li, Ruilong Agostinho, Sérgio Gojcic, Zan Leal-Taixé, Laura Zhou, Qunjie Osep, Aljosa |
| author_facet | Elflein, Sven Li, Ruilong Agostinho, Sérgio Gojcic, Zan Leal-Taixé, Laura Zhou, Qunjie Osep, Aljosa |
| contents | 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 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_23361 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | VGG-T$^3$: Offline Feed-Forward 3D Reconstruction at Scale Elflein, Sven Li, Ruilong Agostinho, Sérgio Gojcic, Zan Leal-Taixé, Laura Zhou, Qunjie Osep, Aljosa Computer Vision and Pattern Recognition 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 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. |
| title | VGG-T$^3$: Offline Feed-Forward 3D Reconstruction at Scale |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.23361 |