ZipMap: Linear-Time 3D Reconstruction
rsasaki0109 · x · 2026-07-19
ZipMap introduces a linear-time, stateful 3D reconstruction method, utilizing test-time training layers to compress a set of images into a compact scene state.
The authors claim it matches or exceeds the accuracy of quadratic-complexity methods like VGGT and π³, while reducing computational overhead to linear. On a single H100, 700 frames can be reconstructed in under 10 seconds, making it over 20x faster than SOTA. The paper also demonstrates the extensibility of this state representation in real-time scene querying and sequential streaming reconstruction.
More from Research
- Structural ensembles beat single predictions in TCR:pMHC generalization study — quaidmorris · 2026-07-22
- RSS launches under OMSF to push structural biology data modeling at scale — MoAlQuraishi · 2026-07-22
- enFoldX tops 8 neoantigen scans and an unseen-peptide benchmark — quaidmorris · 2026-07-22
- enFoldX reaches AUC 0.82 on human VDJdb and transfers to mouse at 0.76 — quaidmorris · 2026-07-22
- enFoldX gains accuracy as AF3 ensemble disagreement rises for non-binders — quaidmorris · 2026-07-22
- A 3D ray plot shows how hard this Jacobian counterexample is to read — moultano · 2026-07-22