Models trained only on a 300K procedurally generated human dataset achieve accuracy comparable to 2B-parameter foundation models on depth, surface normals, and matting, at a fraction of the compute.
Richter, and Vladlen Koltun
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
DAViD: Data-efficient and Accurate Vision Models from Synthetic Data
Models trained only on a 300K procedurally generated human dataset achieve accuracy comparable to 2B-parameter foundation models on depth, surface normals, and matting, at a fraction of the compute.