WaveDiT proposes a conditional flow matching model in 3D Haar wavelet space with heteroscedastic uncertainty for efficient full-resolution brain MRI synthesis.
arXiv preprint arXiv:2503.00266 (2025)
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
-
WaveDiT: Distribution-Aware Wavelet Flow Matching for Efficient 3D Brain MRI Synthesis
WaveDiT proposes a conditional flow matching model in 3D Haar wavelet space with heteroscedastic uncertainty for efficient full-resolution brain MRI synthesis.