Seurat predicts per-point depth changes over time in monocular video from 2D point trajectories alone, trained on synthetic data and evaluated zero-shot on real benchmarks.
Recovering non-rigid 3d shape from image streams
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
-
Seurat: From Moving Points to Depth
Seurat predicts per-point depth changes over time in monocular video from 2D point trajectories alone, trained on synthetic data and evaluated zero-shot on real benchmarks.