arXiv:2607. 12171v1 Announce Type: cross Abstract: In rectified-flow-based generative models, the neural network can be trained to predict two different targets, such as the instantaneous velocity or the data endpoint, to perform denoising.
By Xu Han, Jiajing Hu, Li-Ping Liu
In rectified-flow-based generative models, the neural network can be trained to predict two different targets, such as the instantaneous velocity or the data endpoint, to perform denoising. Although prior work shows that these parameterizations lead to different empirical behaviors, the mechanisms underlying their respective advantages remain to be underexplored, and how to combine them effectively is still unclear.
Pixel-space generative models bypass lossy latent compression, yet necessitate joint learning of global structure and fine-grained details in a high-dimensional space. Standard flow matching interpolates noise toward a fixed clean-image endpoint, leaving the spectral evolution to be learned implicitly.
The paper revisits pixel-space diffusion models, showing that a vanilla diffusion transformer can generate directly in pixel space by swapping velocity prediction for clean image prediction. It introduces MFlow, an adaptive parameterization that interpolates between these two prediction modes based on data representation and model capacity, and demonstrates competitive performance on ImageNet, UCF‑101, and text‑to‑image tasks. Additionally, the authors add ConvRefiner, a lightweight convolutional module trained post‑hoc to restore high‑frequency details while preserving FID.
By Soumik Mukhopadhyay, Long Mai, Abhinav Shrivastava, Aniruddha Mahapatra
The paper introduces Wiener-informed Decoding (WiD), a method that leverages frozen Wiener estimates and statistical knowledge to improve the training of pixel-space flow models. By integrating a trainable Wiener prediction path with coefficient interfaces that inject features into the native decoder, WiD accelerates training, enhances generation quality, and yields smoother gradient trajectories across various model scales and decoder architectures. Experiments on ImageNet 256×256 show that PixelDiT-XL with WiD achieves an FID of 1.53 after 500 epochs, matching the quality of the baseline while requiring 37.5% fewer training epochs.
By Ziqiao Wang, Yang You
The paper introduces a Focal Log-Frequency Loss (f-loss) to counteract the spectral imbalance in pixel-space flow matching, where low frequencies dominate training. By balancing learning signals across frequencies and combining early frequency-domain supervision with later pixel-space refinement, the method accelerates convergence by up to 40% and improves FID and perceptual fidelity across multiple model scales. It requires no architectural changes and can replace existing flow matching losses as a drop‑in solution.
By Lucas Degeorge, Paul Couairon, Arijit Ghosh, Alexei A. Efros, David Picard, Vicky Kalogeiton
The paper introduces continuous adversarial flow models, a continuous-time flow framework trained with an adversarial objective that replaces the fixed mean-squared-error criterion of flow matching. By incorporating a learned discriminator, the method guides training toward a different generalized distribution, yielding samples more closely aligned with the target data distribution. Applied as a post‑training step, it markedly improves ImageNet 256px generation metrics—reducing the guidance‑free FID of latent‑space SiT from 8.26 to 3.63 and of pixel‑space JiT from 7.17 to 3.57—and also enhances guided generation and text‑to‑image benchmarks.
By Shanchuan Lin, Ceyuan Yang, Zhijie Lin, Hao Chen, Haoqi Fan
arXiv:2610.08717v1 Announce Type: cross
Abstract: We study path-flow alignment as a unified training objective for flow matching. Instead of fixing the interpolation path and learning only the veloci...
By Zeyu Michael Li, William Xingxu Chen, Xiang Cheng
arXiv:2602. 20360v2 Announce Type: replace Abstract: Flow-based generative methods offer a simple and effective framework for high-fidelity generation, yet pretrained flow models are rarely used in their vanilla conditional form: in image generation, samples without guidance often appear diffuse and lack fine-grained detail.
By Runlong Liao, Jian Yu, Baiyu Su, Chi Zhang, Lizhang Chen, Qiang Liu
arXiv:2608. 10544v1 Announce Type: cross Abstract: Image restoration is fundamentally constrained by the tradeoff between distortion and perception: minimizing pixel-wise error yields over-smoothed results, whereas optimizing for perceptual realism often introduces structural deviations.
By Sangwoo Jo, Donggeun Ko, Jayeon Kang, Youngsang Kwak, Jaehwa Kwak, Sungjoon Choi
The paper investigates training objectives for denoising-based generative models, focusing on loss weighting and output parameterization such as noise-, clean image-, and velocity-based formulations. It conducts a systematic numerical study across synthetic datasets with controlled geometry and real image data, evaluating denoising accuracy via PSNR and generative quality via FID. The goal is to disentangle how training choices interact with data manifold dimensionality, model architecture, and dataset size, offering practical design insights rather than proposing a new method.
By Anne Gagneux, S\'egol\`ene Martin, R\'emi Gribonval, Mathurin Massias
We study path-flow alignment as a unified training objective for flow matching. Instead of fixing the interpolation path and learning only the velocity field, we jointly train an endpoint-preserving p...