跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 20 天前AI 評分37

Solv3R:以 3D 循環式 Transformer 作為多視圖求解器

Solv3R: 3D Looped Transformer as a Multi-view Solver

AI 導讀

Solv3R 是一種循環式 Transformer,會從目前狀態反覆修正多視圖幾何,支援增量更新、快取及多種重建任務,無需專用模組。其更新運算子不受迭代次數影響,可共同更新已求解及新加入的視圖,亦能在持續迭代時修正不準確的重建。單一求解器支援離線重建、增量重建、重新定位及串流,毋須針對不同任務訓練或配置專用模組。

正文

Abstract

Solv3R is a looped transformer that iteratively refines multi-view geometry from its current state, supporting incremental updates, caching, and multiple reconstruction tasks without specialized modules.

Classical structure-from-motion reconstruction proceeds iteratively, refining camera poses and scene geometry from a current estimate. This allows maps to easily expand without recomputing already computed views, or geometry estimates to improve as more observations are provided. Most geometric foundation models, however, predict entire geometry in a single forward pass or update a recurrent state as frames arrive sequentially, making this expansion and refinement non-trivial. We introduce Solv3R, a looped transformer that learns to continue solving multi-view geometry from its current state. Importantly, its update operator is independent of the iteration count, allowing previously refined and newly introduced views to be jointly updated regardless of how ``solved'' they are. We train the operator to preserve accurate reconstructions under continued iteration and correct inaccurate states, enabling refinement of fixed image collections and integration of new observations. Representations of solved views can also be cached once and reused as geometric context across iterations, enabling compact and efficient key-value caching. We analyze the solver dynamics and compare it with the state-of-the-art, demonstrating that a single learned solver supports offline reconstruction, incremental reconstruction, relocalization, and streaming without task-specific training or modules. The code and models will be made publicly available at https://ubc-vision.github.io/solv3r/.

View arXiv page View PDF Project page GitHub 102 Add to collection

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2611.02857 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2611.02857 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2611.02857 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co