T3lescope: Arbitrary-Resolution High-Fidelity Generative Surface Reconstruction from Images

T3lescope is a generative surface reconstruction method that produces high‑fidelity 3D meshes from posed multi‑view images without per‑scene optimization. It uses a single fixed‑resolution generator in a coarse‑to‑fine cascade, where each level refines geometry within progressively finer spatial cells. Trained on cells at multiple scales, the model shares weights across all levels, allowing it to adapt the number of levels, cell scales, and locations at inference time and achieve consistent geometry across indoor, outdoor, and city‑scale scenes.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.