The authors propose T3lescope, a generative reconstruction framework that reconstructs a full scene mesh at coarse-to-fine levels.
Single generator reconstructs 3D scenes at any scale without per-scene optimization
T3lescope applies one fixed-resolution generative model across an inference-time coarse-to-fine cascade, matching or beating per-scene optimization on indoor, outdoor, and city-scale scenes.
Top University
Atsuhiro Noguchi · Tianhan Xu · Yiming Liang · Yuta Kikuchi · Masahiro Ishiyama · Shintaro Takagi · +2 more
Preferred Networks, Inc. · The University of Tokyo
Research Digest··2 min read
T3lescope, from researchers at Preferred Networks and the University of Tokyo, reconstructs high-fidelity 3D meshes from posed images using a single fixed-resolution generative model applied repeatedly across scales.
Why this paper
From The University of Tokyo and Preferred Networks, Inc.
In one line
T3lescope reconstructs arbitrary-resolution high-fidelity 3D scene meshes from posed multi-view images without per-scene optimization.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ✓Limitations stated by the authors (3 noted)
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§