AnyRecon enables scalable 3D reconstruction from arbitrary sparse unordered views by combining video diffusion with explicit global geometric memory and retrieval to maintain consistency across large viewpoint changes.
arXiv preprint arXiv:2506.10981 (2025) 4
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
AnyRecon: Arbitrary-View 3D Reconstruction with Video Diffusion Model
AnyRecon enables scalable 3D reconstruction from arbitrary sparse unordered views by combining video diffusion with explicit global geometric memory and retrieval to maintain consistency across large viewpoint changes.