Pith. sign in

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

We introduce DC-AR, a novel masked autoregressive (AR) text-to-image generation framework that delivers superior image generation quality with exceptional computational efficiency. Due to the tokenizers' limitations, prior masked AR models have lagged behind diffusion models in terms of quality or efficiency. We overcome this limitation by introducing DC-HT - a deep compression hybrid tokenizer for AR models that achieves a 32x spatial compression ratio while maintaining high reconstruction fidelity and cross-resolution generalization ability. Building upon DC-HT, we extend MaskGIT and create a new hybrid masked autoregressive image generation framework that first produces the structural elements through discrete tokens and then applies refinements via residual tokens. DC-AR achieves state-of-the-art results with a gFID of 5.49 on MJHQ-30K and an overall score of 0.69 on GenEval, while offering 1.5-7.9x higher throughput and 2.0-3.5x lower latency compared to prior leading diffusion and autoregressive models.

citation-role summary

background 1

citation-polarity summary

fields

cs.CV 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

background 1

representative citing papers

HPSv3: Towards Wide-Spectrum Human Preference Score

cs.CV · 2025-08-05 · conditional · novelty 6.0

HPSv3, trained on the new 1.08M-pair HPDv3 dataset, reaches 76.9% pairwise preference accuracy on its own test set and Spearman 0.94 against human model rankings, and is used to iteratively refine generated images (CoHP).

citing papers explorer

Showing 1 of 1 citing paper.

  • HPSv3: Towards Wide-Spectrum Human Preference Score cs.CV · 2025-08-05 · conditional · none · ref 45 · internal anchor

    HPSv3, trained on the new 1.08M-pair HPDv3 dataset, reaches 76.9% pairwise preference accuracy on its own test set and Spearman 0.94 against human model rankings, and is used to iteratively refine generated images (CoHP).