SpectralDiT: Timestep-Conditioned Spectral Residual Correction for Flow-Matching DiTs
We propose SpectralDiT, a lightweight modification to flow-matching Diffusion Transformers that adds timestep-conditioned spectral correction to the MLP residual branch. The module decomposes each residual update into low- and high-frequency components on the patch-token grid, then learns a zero-initialized additive gate so the model initially matches the baseline DiT. On CIFAR-10 pixel-space generation, SpectralDiT improves FID from 20.78 to 19.71 at patch size 1 and reduces the radial Fourier spectrum gap. Furthermore, we scale our method to latent diffusion on ImageNet-100. With 0.6% additional theoretical FLOPs and 1.36% additional parameters, SpectralDiT improves latent flow-matching, achieving an 8.7% relative FID reduction under classifier-free guidance (CFG 2.0). All reported results are averaged over five seeds. Ablations and gate visualizations on CIFAR-10 reveal stable block-specific spectral correction patterns.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
ReCo-Diff: Residual-Conditioned Deterministic Sampling for Cold Diffusion in Sparse-View CT
Cold and generalized diffusion models have recently shown strong potential for sparse-view CT reconstruction by explicitly modeling deterministic degradation processes. However, existing sampling strategies often rely on…
Physics-Consistent Diffusion for Efficient Fluid Super-Resolution via Multiscale Residual Correction
Existing image SR and generic diffusion models transfer poorly to fluid SR: they are sampling-intensive, ignore physical constraints, and often yield spectral mismatch and spurious divergence. We address fluid super-reso…
ResSR: A Computationally Efficient Residual Approach to Super-Resolving Multispectral Images
Multispectral imaging sensors typically have wavelength-dependent resolution, which limits downstream processing. Consequently, researchers have proposed multispectral image super-resolution (MSI-SR) methods which upsamp…
Image Super-ResolutionMultispectral Image Super-resolutionSuper-ResolutionFeatFix: Reuse What You Verify through Local Exact-Feature Correction for Faster Cached Diffusion Inference
Diffusion models are widely used to generate high-quality images and videos, but their iterative denoising process remains computationally intensive. A growing class of training-free accelerators reduces this cost by reu…
Warp RL: Reshaping Base Policy Distributions for Dynamics Adaptation
Residual reinforcement learning adapts a pretrained robot policy by learning an additive correction to its actions. While effective when adaptation amounts to shifting the base policy's action distribution, additive corr…
Reinforcement Learning