paper-with-me

Papers

SpectralAR: Spectral Autoregressive Visual Generation

2025-06-12 · Yuanhui Huang, Weiliang Chen, Wenzhao Zheng, Yueqi Duan, Jie zhou, Jiwen Lu

Autoregressive visual generation has garnered increasing attention due to its scalability and compatibility with other modalities compared with diffusion models. Most existing methods construct visual sequences as spatial patches for autoregressive generation. However, image patches are inherently parallel, contradicting the causal nature of autoregressive modeling. To address this, we propose a Spectral AutoRegressive (SpectralAR) visual generation framework, which realizes causality for visual sequences from the spectral perspective. Specifically, we first transform an image into ordered spectral tokens with Nested Spectral Tokenization, representing lower to higher frequency components. We then perform autoregressive generation in a coarse-to-fine manner with the sequences of spectral tokens. By considering different levels of detail in images, our SpectralAR achieves both sequence causality and token efficiency without bells and whistles. We conduct extensive experiments on ImageNet-1K for image reconstruction and autoregressive generation, and SpectralAR achieves 3.02 gFID with only 64 tokens and 310M parameters. Project page: https://huang-yh.github.io/spectralar/.

📄 PDF Abstract BibTeX arXiv:2506.10962

Code (0)

등록된 구현이 없습니다.

Tasks

Image Reconstruction

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

SAGA: Stable Acceleration Guidance for Autoregressive Video Generation

2026-07-09 · Thanh-Nhan Vo, Trong-Thuan Nguyen, Trung-Hoang Le, Tam V. Nguyen 외 arxiv

Autoregressive video diffusion enables efficient streaming and long-horizon video generation, but repeatedly reusing generated latents as causal context can amplify temporal errors, resulting in flickering, motion jitter…

Video Generation

FreqForcing: Autoregressive Long Video Generation via Spectral Self-Anchoring

2026-07-29 · Jiatong Li, Leo Liang, Linghe Kong, Yulun Zhang arxiv

Autoregressive video diffusion models enable real-time streaming video generation. However, errors introduced during self-rollout accumulate over long horizons, manifesting as color drift, motion stagnation, and eventual…

Video Generation

Spectral Progressive Diffusion for Efficient Image and Video Generation

2026-05-18 · Howard Xiao, Brian Chao, Lior Yariv, Gordon Wetzstein arxiv

Diffusion models have been shown to implicitly generate visual content autoregressively in the frequency domain, where low-frequency components are generated earlier in the denoising process while high-frequency details …

Video Generation

Guiding Visual Autoregressive Models through Spectrum Weakening

2025-11-28 · Chaoyang Wang, Tianmeng Yang, Jingdong Wang, Yunhai Tong arxiv

Classifier-free guidance (CFG) has become a widely adopted and practical approach for enhancing generation quality and improving condition alignment. Recent studies have explored guidance mechanisms for unconditional gen…

SPECTRE: Spectral Conditioning Helps to Overcome the Expressivity Limits of One-shot Graph Generators

2022-04-04 · Karolis Martinkus, Andreas Loukas, Nathanaël Perraudin, Roger Wattenhofer

We approach the graph generation problem from a spectral perspective by first generating the dominant parts of the graph Laplacian spectrum and then building a graph matching these eigenvalues and eigenvectors. Spectral …

Graph GenerationGraph Matching