A ray-conditioned transformer turns single-image 3D shape completion into novel-view depth prediction, achieving state-of-the-art chamfer distance on synthetic and real benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
RaySt3R: Predicting Novel Depth Maps for Zero-Shot Object Completion
A ray-conditioned transformer turns single-image 3D shape completion into novel-view depth prediction, achieving state-of-the-art chamfer distance on synthetic and real benchmarks.