Pith. sign in

REVIEW 6 cited by

MaskGIT: Masked Generative Image Transformer

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2202.04200 v1 pith:VG6VFDP3 submitted 2022-02-08 cs.CV

Huiwen Chang , Han Zhang , Lu Jiang , Ce Liu , William T. Freeman This is my paper
classification cs.CV
keywords imagemaskgittokenstransformergenerativemaskedmodelaccelerates
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Generative transformers have experienced rapid popularity growth in the computer vision community in synthesizing high-fidelity and high-resolution images. The best generative transformer models so far, however, still treat an image naively as a sequence of tokens, and decode an image sequentially following the raster scan ordering (i.e. line-by-line). We find this strategy neither optimal nor efficient. This paper proposes a novel image synthesis paradigm using a bidirectional transformer decoder, which we term MaskGIT. During training, MaskGIT learns to predict randomly masked tokens by attending to tokens in all directions. At inference time, the model begins with generating all tokens of an image simultaneously, and then refines the image iteratively conditioned on the previous generation. Our experiments demonstrate that MaskGIT significantly outperforms the state-of-the-art transformer model on the ImageNet dataset, and accelerates autoregressive decoding by up to 64x. Besides, we illustrate that MaskGIT can be easily extended to various image editing tasks, such as inpainting, extrapolation, and image manipulation.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Reconsidering Positional Supervision in Masked Diffusion Language Model Training

    cs.CL 2026-01 conditional novelty 6.0 of 10

    Adding a CTC-style <SLACK> token during MDLM supervised fine-tuning relaxes strict positional supervision and improves open-ended generation benchmarks over a matched cross-entropy baseline.

  2. Transition Matching: Scalable and Flexible Generative Modeling

    cs.LG 2025-06 conditional novelty 6.0 of 10

    Transition Matching unifies flow matching and continuous autoregressive generation as discrete-time Markov processes, with three variants that improve text-to-image quality and speed.

  3. Instella-T2I: Pushing the Limits of 1D Discrete Latent Space Image Generation

    cs.CV 2025-06 conditional novelty 6.0 of 10

    1D binary image latents reduce a 1024x1024 image to 128 discrete tokens and support text-to-image generation with diffusion and autoregressive models.

  4. Humanoid World Models: Open World Foundation Models for Humanoid Robotics

    cs.RO 2025-06 conditional novelty 6.0 of 10

    Masked-transformers trained on humanoid video forecast future frames with better FID than flow-matching models, and parameter sharing cut model size 33-53% with minimal quality loss.

  5. Exploring In-Image Machine Translation with Real-World Background

    cs.CL 2025-05 conditional novelty 6.0 of 10

    DebackX translates text inside images by separating text from the background, translating the text-image directly, and fusing it back, outperforming prior IIMT models on a new real-background dataset.

  6. TACG: Trajectory-Aware Commit Gating for Diffusion Language Model Decoding

    cs.CL 2026-07 conditional novelty 5.5 of 10

    Trajectory-aware commit gating (TILG + History Gate + capped extra promotion) improves or preserves DLLM accuracy while reducing steps and raising tokens-per-forward without retraining.

Pith tools