Pith. sign in

REVIEW 1 cited by

EdiBERT, a generative model for image editing

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 2111.15264 v3 pith:AOEG4XIY submitted 2021-11-30 cs.CV cs.LG

classification cs.CVcs.LG
keywords imagemodeltasksdenoisingediberteditinggenerativemanipulation
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Advances in computer vision are pushing the limits of im-age manipulation, with generative models sampling detailed images on various tasks. However, a specialized model is often developed and trained for each specific task, even though many image edition tasks share similarities. In denoising, inpainting, or image compositing, one always aims at generating a realistic image from a low-quality one. In this paper, we aim at making a step towards a unified approach for image editing. To do so, we propose EdiBERT, a bi-directional transformer trained in the discrete latent space built by a vector-quantized auto-encoder. We argue that such a bidirectional model is suited for image manipulation since any patch can be re-sampled conditionally to the whole image. Using this unique and straightforward training objective, we show that the resulting model matches state-of-the-art performances on a wide variety of tasks: image denoising, image completion, and image composition.

Discussion (0). Continue with ORCID 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. Multidimensional Byte Pair Encoding: Shortened Sequences for Improved Visual Data Generation

    cs.CV 2024-11 conditional novelty 6.0 of 10

    A multidimensional extension of Byte Pair Encoding compresses visual token grids losslessly into shorter sequences, improving transformer-based generation FID on image and 3D datasets.

Pith tools