End-to-End Autoregressive Image Generation with 1D Semantic Tokenizer
Autoregressive image modeling relies on visual tokenizers to compress images into compact latent representations. We design an end-to-end training pipeline that jointly optimizes reconstruction and generation, enabling direct supervision from generation results to the tokenizer. This contrasts with prior two-stage approaches that train tokenizers and generative models separately. We further investigate leveraging vision foundation models to improve 1D tokenizers for autoregressive modeling. Our autoregressive generative model achieves strong empirical results, including a state-of-the-art FID score of 1.48 without guidance on ImageNet 256x256 generation.
Code (0)
등록된 구현이 없습니다.
Tasks
Image GenerationResults from the Paper
| Rank | Task | Dataset | Model | Metrics |
|---|---|---|---|---|
| #24 | Image Generation | ImageNet 256x256 | End-to-End Autoregressive Image Generati | FID: 1.48 |
Similar Papers 제목 키워드 기반
GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation
In autoregressive (AR) image generation, visual tokenizers compress images into compact discrete latent tokens, enabling efficient training of downstream autoregressive models for visual generation via next-token predict…
DecoderImage GenerationImage ReconstructionRepresentation LearningImageFolder: Autoregressive Image Generation with Folded Tokens
Image tokenizers are crucial for visual generative models, e.g., diffusion models (DMs) and autoregressive (AR) models, as they construct the latent representation for modeling. Increasing token length is a common approa…
Image GenerationImage ReconstructionQuantizationVision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generation
Leveraging the powerful representations of pre-trained vision foundation models -- traditionally used for visual comprehension -- we explore a novel direction: building an image tokenizer directly atop such models, a lar…
Image GenerationImage ReconstructionQuantizationMergeTok: Unified Continuous and Discrete Visual Tokenization via Token Merging
Most visual tokenizers for image generation are bifurcated into two families with complementary limitations: continuous VAEs offer high-fidelity reconstruction but suffer from dense, entangled latents that are poorly sui…
Image GenerationHeptapod: Language Modeling on Visual Signals
We introduce Heptapod, an image autoregressive model that adheres to the foundational principles of language modeling. Heptapod employs \textbf{causal attention}, \textbf{eliminates reliance on CFG}, and \textbf{eschews …
Self-Supervised Learning