Pith. sign in

REVIEW 7 cited by

Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting

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 2212.06909 v2 pith:J7LLRMK3 submitted 2022-12-13 cs.CV cs.AI

classification cs.CVcs.AI
keywords imageimageneditorinpaintingeditbenchtext-guidedattributesedits
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Text-guided image editing can have a transformative impact in supporting creative applications. A key challenge is to generate edits that are faithful to input text prompts, while consistent with input images. We present Imagen Editor, a cascaded diffusion model built, by fine-tuning Imagen on text-guided image inpainting. Imagen Editor's edits are faithful to the text prompts, which is accomplished by using object detectors to propose inpainting masks during training. In addition, Imagen Editor captures fine details in the input image by conditioning the cascaded pipeline on the original high resolution image. To improve qualitative and quantitative evaluation, we introduce EditBench, a systematic benchmark for text-guided image inpainting. EditBench evaluates inpainting edits on natural and generated images exploring objects, attributes, and scenes. Through extensive human evaluation on EditBench, we find that object-masking during training leads to across-the-board improvements in text-image alignment -- such that Imagen Editor is preferred over DALL-E 2 and Stable Diffusion -- and, as a cohort, these models are better at object-rendering than text-rendering, and handle material/color/size attributes better than count/shape attributes.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

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

  1. D-Fusion: Direct Preference Optimization for Aligning Diffusion Models with Visually Consistent Samples

    cs.CV 2025-05 conditional novelty 7.0 of 10

    Mask-guided self-attention fusion creates well-aligned target images that stay visually close to poorly-aligned base images, with full denoising trajectories, and DPO on these pairs improves alignment.

  2. EditInspector: A Benchmark for Evaluation of Text-Guided Image Edits

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A new human-labeled benchmark shows leading vision-language models are unreliable at judging image edits, and the authors' methods improve artifact detection and difference captioning.

  3. Towards Reliable Identification of Diffusion-based Image Manipulations

    cs.CV 2025-06 conditional novelty 6.0 of 10

    RADAR combines semantic and geometric vision features with contrastive learning to detect and localize diffusion-based image edits, outperforming prior methods on a new 28-model benchmark.

  4. LightLab: Controlling Light Sources in Images with Diffusion Models

    cs.CV 2025-05 conditional novelty 6.0 of 10

    A diffusion model fine-tuned on paired real and synthetic images can edit the intensity, color, and ambient level of visible light sources in a single photograph while keeping shadows and reflections plausible.

  5. VideoDPO: Omni-Preference Alignment for Video Diffusion Generation

    cs.CV 2024-12 reject novelty 6.0 of 10

    VideoDPO shows that DPO-style training on automatically selected best and worst video pairs improves overall VBench scores on three open text-to-video models, with some sub-metrics degrading and weak gains on external...

  6. VBench++: Comprehensive and Versatile Benchmark Suite for Video Generative Models

    cs.CV 2024-11 conditional novelty 5.0 of 10

    VBench++ is a benchmark that scores text-to-video and image-to-video models on 16 quality dimensions plus trustworthiness, reporting human-alignment correlations for each.

  7. Localize, Don't Beautify: Client-Side Control of Image-Editing APIs for Cosmetic Surgery Previews

    cs.CV 2026-08 conditional novelty 4.0 of 10

    A client-side landmark mask and feathered composite confined image-editing API outputs to the requested facial region in a 15-face pilot, at the cost of little on-target change, while no tested editor moved identity e...

Pith tools