Pith. sign in

REVIEW 3 cited by

Editable Image Elements for Controllable Synthesis

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 2404.16029 v1 pith:VJDBQIIC submitted 2024-04-24 cs.CV

Jiteng Mu , Michaël Gharbi , Richard Zhang , Eli Shechtman , Nuno Vasconcelos , Xiaolong Wang , Taesung Park This is my paper · ORCID
classification cs.CV
keywords imagediffusioneditingelementsinputimageseditablemodel
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Diffusion models have made significant advances in text-guided synthesis tasks. However, editing user-provided images remains challenging, as the high dimensional noise input space of diffusion models is not naturally suited for image inversion or spatial editing. In this work, we propose an image representation that promotes spatial editing of input images using a diffusion model. Concretely, we learn to encode an input into "image elements" that can faithfully reconstruct an input image. These elements can be intuitively edited by a user, and are decoded by a diffusion model into realistic images. We show the effectiveness of our representation on various image editing tasks, such as object resizing, rearrangement, dragging, de-occlusion, removal, variation, and image composition. Project page: https://jitengmu.github.io/Editable_Image_Elements/

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

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

  1. Pattern Analogies: Learning to Perform Programmatic Image Edits by Analogy

    cs.CV 2024-12 conditional novelty 7.0 of 10

    A diffusion model, trained on synthetic pattern quartets generated by the SplitWeave DSL, can apply a program-level edit demonstrated on one pattern pair to a new real-world pattern.

  2. LoRA of Change: Learning to Generate LoRA for the Editing Instruction from A Single Before-After Image Pair

    cs.CV 2024-11 conditional novelty 7.0 of 10

    A hypernetwork generates a per-instruction LoRA from a before-after image pair, and a reverse training loss allows learning from paired data alone.

  3. SceneDiffuser: Efficient and Controllable Driving Simulation Initialization and Rollout

    cs.LG 2024-12 conditional novelty 6.0 of 10

    A diffusion model for traffic simulation amortizes denoising over physical time, enabling cheap and stable closed-loop rollout, controllable scene edits, and LLM-driven scenario generation.

Pith tools