A coarse canonical mesh bottleneck plus multi-view consistency lets a shared object frame emerge from self-supervised training on in-the-wild videos without canonical labels or category conditioning.
Ov9d: Open-vocabulary category-level 9d object pose and size estimation,
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
-
Emergence of a Shared Canonical Object Frame from In-the-Wild Videos
A coarse canonical mesh bottleneck plus multi-view consistency lets a shared object frame emerge from self-supervised training on in-the-wild videos without canonical labels or category conditioning.