Pith. sign in

REVIEW 1 cited by

A Theoretical Justification for Image Inpainting using Denoising Diffusion Probabilistic Models

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 2302.01217 v1 pith:7V3XNIPY submitted 2023-02-02 stat.ML cs.AIcs.LGmath.STstat.TH

classification stat.MLcs.AIcs.LGmath.STstat.TH
keywords diffusioninpaintingalgorithmimagelinearrepaintsampleconvergence
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

We provide a theoretical justification for sample recovery using diffusion based image inpainting in a linear model setting. While most inpainting algorithms require retraining with each new mask, we prove that diffusion based inpainting generalizes well to unseen masks without retraining. We analyze a recently proposed popular diffusion based inpainting algorithm called RePaint (Lugmayr et al., 2022), and show that it has a bias due to misalignment that hampers sample recovery even in a two-state diffusion process. Motivated by our analysis, we propose a modified RePaint algorithm we call RePaint$^+$ that provably recovers the underlying true sample and enjoys a linear rate of convergence. It achieves this by rectifying the misalignment error present in drift and dispersion of the reverse process. To the best of our knowledge, this is the first linear convergence result for a diffusion based image inpainting algorithm.

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. SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis

    cs.CV 2024-11 conditional novelty 6.0 of 10

    SplatFlow jointly generates multi-view images, depths, and camera poses with a rectified flow model, then decodes them into editable 3D Gaussian Splatting scenes.

Pith tools