Solv3R: 3D Looped Transformer as a Multi-view Solver
Reuses one transformer block to refine a multi-view geometric state. Trains stable, corrective updates so reconstruction can continue when new images arrive, with stopping based on changes in the hidden state.
First public: · Added to this list: November 3, 2026
Explore this approach
Recurrent reasoning — Repeat parts of the model or keep intermediate information in memory while working through a problem. Some methods also learn how many passes to run.