Pith. sign in

REVIEW 4 cited by

UNIT-DDPM: UNpaired Image Translation with Denoising Diffusion Probabilistic Models

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 2104.05358 v1 pith:IFT5QSYA submitted 2021-04-12 cs.CV cs.LGeess.IV

Hiroshi Sasaki , Chris G. Willcocks , Toby P. Breckon This is my paper
classification cs.CVcs.LGeess.IV
keywords translationdenoisingdomainmodelsdiffusionimageimage-to-imageimages
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We propose a novel unpaired image-to-image translation method that uses denoising diffusion probabilistic models without requiring adversarial training. Our method, UNpaired Image Translation with Denoising Diffusion Probabilistic Models (UNIT-DDPM), trains a generative model to infer the joint distribution of images over both domains as a Markov chain by minimising a denoising score matching objective conditioned on the other domain. In particular, we update both domain translation models simultaneously, and we generate target domain images by a denoising Markov Chain Monte Carlo approach that is conditioned on the input source domain images, based on Langevin dynamics. Our approach provides stable model training for image-to-image translation and generates high-quality image outputs. This enables state-of-the-art Fr\'echet Inception Distance (FID) performance on several public datasets, including both colour and multispectral imagery, significantly outperforming the contemporary adversarial image-to-image translation methods.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

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

  1. DualMat: PBR Material Estimation via Coherent Dual-Path Diffusion

    cs.CV 2025-08 conditional novelty 6.0 of 10

    DualMat is a dual-path diffusion model combining an albedo-optimized pretrained latent path with a material-specialized compact latent path, using feature distillation and rectified flow to estimate PBR materials from...

  2. Collaborative Learning for Unsupervised Multimodal Remote Sensing Image Registration: Integrating Self-Supervision and MIM-Guided Diffusion-Based Image Translation

    eess.IV 2025-05 conditional novelty 6.0 of 10

    An unsupervised collaborative training framework with MIM-guided diffusion translation and pseudo-label distillation reaches competitive or better cross-modal registration accuracy on five remote sensing datasets than...

  3. Diffusion-based translation between unpaired spontaneous premature neonatal EEG and fetal MEG

    eess.SP 2025-07 conditional novelty 4.0 of 10

    A diffusion bridge method with a higher-order ODE solver translates between unpaired neonatal EEG and fetal MEG bursts with near-perfect cycle reconstruction, though translation correctness is not directly verifiable.

  4. ThermalDiffusion: Visual-to-Thermal Image-to-Image Translation for Autonomous Navigation

    cs.RO 2025-06 conditional novelty 4.0 of 10

    A conditional diffusion model with self-attention at half input resolution translates RGB images to thermal images with better object-level thermal detail than lower-resolution attention, evaluated on four datasets.

Pith tools