Empirical study shows stitching artifacts in patched cycleGAN volumes evade FID detection yet degrade segmentation performance, with 3D models offering limited benefit over more stable 2D training.
Title resolution pending
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
-
Stitching and dimensionality effects on large artificially generated volume datasets
Empirical study shows stitching artifacts in patched cycleGAN volumes evade FID detection yet degrade segmentation performance, with 3D models offering limited benefit over more stable 2D training.