- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 1
Read review
Paper summary
This paper analyzes frequency bands interaction when the diffusion model trained with shared parameters for time step image (or noise) recovery. They then proposes a method named SpecDiffusion based on Frequency-Aware Loss (FAL) after they perform the weighting analysis on contributions from high-frequency error and low frequency error after gradient descents are applied to update the images. Their experiments show that their method reduces FID when compared with previous method (pixel space and latent-space diffusion models.
When I like the idea of comparing the frequency contributions over time reconstruction steps, I found this paper is poorly written and needs a major revision to make their paper easier to read. Also, the experiments did not show any real image reconstructed.
Critical strengths
This paper analyzes frequency bands interaction when the diffusion model trained with shared parameters for time step image (or noise) recovery, and they provide a new method that uses Frequency-Aware Loss (FAL) after they performed the weighting analysis on contributions from high-frequency error and low frequency error after gradient descents are applied to update the images.
Critical weaknesses
- The paper overly is poorly written and you need to go to check the appendix in order to understand the main text.
- Frequency content in image is highly sensitive, with high values in the low frequency domain and very small values in the high frequency domain, the analysis doesn't sees address this point clearly.
- Their experiment did not specifically point out how they choose the two bands (low frequency and high frequency). And no reconstruction clean image is provided.
Questions for authors
- Page 3, eqn. (2), line 142-143, the first term at the left hand side of the equation is a multiplication or a function of (ϑ − ηu)?
- why use Nyquist normalization? How it benefits your method?
- Page 2, line 78, the paper states that "Their residuals are orthogonal in output space", what "their" referred to?
- And what is the output space?
- The frequency analysis is performed on mean squared gradient errors. I wonder if that would affect the true frequency content of the errors.
Thank you again for your thoughtful questions. We look forward to hearing your thoughts on the revised manuscript.