Pith. sign in

REVIEW 5 cited by

OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting

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 2503.08677 v2 pith:5P3WXLCV submitted 2025-03-11 cs.CV

Yongsheng Yu , Ziyun Zeng , Haitian Zheng , Jiebo Luo This is my paper · ORCID
classification cs.CV
keywords objecteditinginsertionomnipaintimageobject-orientedpairedremoval
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Diffusion-based generative models have revolutionized object-oriented image editing, yet their deployment in realistic object removal and insertion remains hampered by challenges such as the intricate interplay of physical effects and insufficient paired training data. In this work, we introduce OmniPaint, a unified framework that re-conceptualizes object removal and insertion as interdependent processes rather than isolated tasks. Leveraging a pre-trained diffusion prior along with a progressive training pipeline comprising initial paired sample optimization and subsequent large-scale unpaired refinement via CycleFlow, OmniPaint achieves precise foreground elimination and seamless object insertion while faithfully preserving scene geometry and intrinsic properties. Furthermore, our novel CFD metric offers a robust, reference-free evaluation of context consistency and object hallucination, establishing a new benchmark for high-fidelity image editing. Project page: https://yeates.github.io/OmniPaint-Page/

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

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

  1. EraseLoRA: MLLM-Driven Foreground Exclusion and Background Subtype Aggregation for Dataset-Free Object Removal

    cs.CV 2025-12 conditional novelty 6.0 of 10

    EraseLoRA removes masked objects by having an MLLM separate target, non-target foreground, and background, then test-time LoRA optimization aggregates background subtypes to reconstruct the occluded region.

  2. InsertAnywhere: Geometrically Grounded and Optics-Aware Video Object Insertion

    cs.CV 2025-12 conditional novelty 6.0 of 10

    InsertAnywhere inserts a reference object into arbitrary videos by reconstructing 4D geometry to propagate a user-given placement across frames and fine-tuning video diffusion on ROSE++, a removal-to-insertion dataset...

  3. Mask Consistency Regularization in Object Removal

    cs.CV 2025-09 conditional novelty 6.0 of 10

    A mask-consistency training loss, enforcing equal predictions across dilated and reshaped masks, is proposed to reduce hallucination and mask-shape bias in diffusion-based object removal.

  4. HOComp: Interaction-Aware Human-Object Composition

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A diffusion-transformer method that composes a foreground object into a human image with MLLM-chosen interaction regions, pose keypoint supervision, and appearance/background consistency losses, plus a new paired dataset.

  5. In-Context Brush: Zero-shot Customized Subject Insertion with Context-Aware Latent Space Manipulation

    cs.CV 2025-05 conditional novelty 4.0 of 10

    In-Context Brush performs zero-shot customized subject insertion by amplifying prompt and reference attention and reweighting attention heads in a pre-trained Flux-Fill diffusion transformer.

Pith tools