Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 764

The DOI matches its Crossref record; 49 of the 49 references it cites were found in a registry or an index.

Blended Diffusion for Text-driven Editing of Natural Images

Open access
Avrahami, Omri, Lischinski, Dani, Fried, Ohad·2022·2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Abstract

Natural language offers a highly intuitive interface for image editing. In this paper, we introduce the first solution for performing local (region-based) edits in generic natural images, based on a natural language description along with an ROI mask. We achieve our goal by leveraging and combining a pretrained language-image model (CLIP), to steer the edit towards a user-provided text prompt, with a denoising diffusion probabilistic model (DDPM) to generate natural-looking results. To seamlessly fuse the edited region with the unchanged parts of the image, we spatially blend noised versions of the input image with the local text-guided diffusion latent at a progression of noise levels. In addition, we show that adding augmentations to the diffusion process mitigates adversarial results. We compare against several baselines and related methods, both qualitatively and quantitatively, and show that our method outperforms these solutions in terms of overall realism, ability to preserve the background and matching the text. Finally, we show several text-driven editing applications, including adding a new object to an image, removing/replacing/altering existing objects, background replacement, and image extrapolation.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/cvpr52688.2022.01767

Cites

49 of 49 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 14

  1. murdock, 0, The big sleep BigGANxCLIP
  2. mansimov, 2016, Generating images from captions with attention, CoRR, abs 1511 2793
  3. nichol, 0, Improved denoising diffusion probabilistic models, International Conference on Machine Learning, 8162
  4. li, 2019, Controllable text-to-image generation, ArXiv Preprint
  5. vaswani, 2017, Attention is all you need, Advances in neural information processing systems, 5998
  6. zhu, 0, Indomain GAN inversion for real image editing, European Conference on Computer Vision, 592
  7. xia, 2021, GAN inversion: A survey, ArXiv Preprint
  8. 10.1145/1531326.1531373 · doi:10.1145/1531326.1531373
  9. fried, 2020, Editing self-image, 63, 70
  10. goh, 2021, Distillation
  11. bau, 2021, Paint by word, ArXiv Preprint
  12. blake, 0, Trump is reportedly suggesting the ‘access hollywood’ tape was fake news
  13. crowson, 0, CLIP guided diffusion HQ 256x256
  14. crowson, 0, VQGAN+CLIP

Cited by

See all 764

Metadata

Authors
Avrahami, O., Lischinski, D., & Fried, O.
Venue
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2022-06
Pages
18187-18197
ISSN
1063-6919 (ISSN-L)
OpenAlex
W3216352822
Cited by
764
References
49
FWCI
63.26
Type
conference paper
Language
en
Open access
green
Funders
Israel Science Foundation (2492/20,1574/21)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.