Pith. sign in

REVIEW 1 cited by

M6-UFC: Unifying Multi-Modal Controls for Conditional Image Synthesis via Non-Autoregressive Generative Transformers

Not yet reviewed by Pith; the record is open.

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 2105.14211 v4 pith:3FPFRXEM submitted 2021-05-29 cs.CV

classification cs.CV
keywords imagem6-ufcmulti-modalcontrolssynthesissynthesizedblocksconditional
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Conditional image synthesis aims to create an image according to some multi-modal guidance in the forms of textual descriptions, reference images, and image blocks to preserve, as well as their combinations. In this paper, instead of investigating these control signals separately, we propose a new two-stage architecture, M6-UFC, to unify any number of multi-modal controls. In M6-UFC, both the diverse control signals and the synthesized image are uniformly represented as a sequence of discrete tokens to be processed by Transformer. Different from existing two-stage autoregressive approaches such as DALL-E and VQGAN, M6-UFC adopts non-autoregressive generation (NAR) at the second stage to enhance the holistic consistency of the synthesized image, to support preserving specified image blocks, and to improve the synthesis speed. Further, we design a progressive algorithm that iteratively improves the non-autoregressively generated image, with the help of two estimators developed for evaluating the compliance with the controls and evaluating the fidelity of the synthesized image, respectively. Extensive experiments on a newly collected large-scale clothing dataset M2C-Fashion and a facial dataset Multi-Modal CelebA-HQ verify that M6-UFC can synthesize high-fidelity images that comply with flexible multi-modal controls.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

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

  1. Disentangling 3D from Large Vision-Language Models for Controlled Portrait Generation

    cs.CV 2025-06 conditional novelty 8.0 of 10

    CLIPortrait disentangles camera and geometry information from CLIP embeddings via 2D canonicalization, then prevents distribution collapse with a Jacobian regularizer, enabling text-guided 3D portrait generation from ...

Pith tools