Independent Samples, Correlated Variance A Learnable Cross-View Cue in Path-Traced Stereo Data
Path-traced synthetic stereo is a primary training substrate for disparity networks, and the pipelines that consume it assume Monte~Carlo (MC) rendering noise is independent across the two views. The assumption is correct at the level it is stated---individual samples---but silent about the object a network actually sees. We show that the per-pixel MC \emph{variance fields}, though built from independent samples, are strongly correlated once aligned by the ground-truth disparity, and that a network can learn to match with that correlation. Across 20 indoor scenes the warped correlation is $0.754\pm0.016$ against $0.360$ unwarped; it replicates on a second renderer with a different sampler...
| Authors | Po-Ting Lin |
|---|---|
| Primary category | cs.CV |
| Published | 24 June 2026 |
| Last updated at source | 20 September 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.