- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper introduces FREPix, a frequency-heterogeneous flow-matching framework for pixel-space image generation. FREPix uses an orthonormal Haar wavelet transform to decompose images into low- and high-frequency states, assigns them distinct interpolation schedules, and explicitly factorizes prediction between a low-frequency DiT structure predictor and a lightweight high-frequency decoder conditioned on the predicted structure. It further applies time-dependent frequency weighting to the flow-matching objective while preserving the same population-optimal velocity field, supplemented by REPA and LPIPS losses. On class-conditional ImageNet generation, FREPix achieves competitive results at both and resolutions, including FIDs of 1.91 and 2.38, respectively. Ablations examine the interpolation schedules, frequency weighting, and auxiliary losses, while additional experiments show particularly strong performance under limited training budgets and low-NFE sampling.
Critical strengths
-
A coherent frequency-heterogeneous formulation. FREPix consistently incorporates frequency heterogeneity into the transport path, prediction targets, architecture, and training objective. This is more consequential than merely adding frequency-aware features or an auxiliary loss: it turns coarse-to-fine generation into an explicit modeling principle while retaining an exact, lossless pixel-space representation through an orthonormal DWT.
-
Strong performance in practically important efficiency regimes. FREPix is particularly competitive under limited training budgets and low-NFE sampling, while requiring fewer GFLOPs than most comparable pixel-space models. These results suggest that the proposed inductive bias improves not only final generation quality but also optimization and sampling efficiency, which substantially strengthens the practical significance of the work.
Critical weaknesses
-
The contribution of the proposed frequency-heterogeneous design is not sufficiently isolated. The reported performance is heavily influenced by REPA and LPIPS—for example, the ablation FID improves from 53.78 to 13.85 when both are added—while the paper lacks a controlled, component-wise comparison of joint versus explicitly decoupled prediction, homogeneous versus heterogeneous paths, and uniform versus frequency-aware weighting. Consequently, it is difficult to determine how much of the gain is attributable to FREPix itself rather than auxiliary supervision.
-
Important inconsistencies undermine reproducibility and confidence in the empirical claims. The paper alternately reports Euler and Heun as the solver for the main FREPix-XL results, gives inconsistent CFG intervals, and the sampling pseudocode appears to update from rather than the current state , contrary to a standard Euler step. Since sampling configuration directly affects FID and low-NFE performance—one of the paper’s central claims—these ambiguities are consequential to the overall assessment.
Questions for authors
Clarification requests
-
What sampling procedure was used for the main FREPix-XL results: Euler or Heun? Please also clarify the CFG interval and the actual number of network evaluations. In Algorithm 2, should the Euler update start from the current state , rather than from ?
-
Were the baselines in Tables 1 and 3 trained or evaluated with the same REPA and LPIPS supervision, time sampler, CFG configuration, and computational budget as FREPix? If not, please clarify which components and settings differ.
Additional evidence that would materially affect the assessment
-
Can the authors provide a controlled component-wise ablation comparing: (i) joint versus explicitly frequency-decoupled prediction, (ii) homogeneous versus heterogeneous transport paths, and (iii) uniform versus frequency-aware loss weighting, while keeping the architecture size and auxiliary losses fixed? The current ablations do not isolate the contribution of the paper’s central design choices.
-
Can the authors report matched comparisons of FREPix, JiT, and DeCo with identical REPA and LPIPS supervision? Given that these auxiliary losses reduce FREPix’s FID from 53.78 to 13.85, such a comparison would materially affect whether the reported gains can be attributed to frequency-heterogeneous modeling.