Skip to main content
Search

# Image Deblending

1 related articles

Subscribe to updates
  1. arXiv

    Two photos blended into one can be split again: training-free diffusion sampling recovers both sources and the blend map

    Image deblending must split one composite image back into its source images, and a single observation admits many plausible decompositions, making the problem ill-posed. Training-free diffusion posterior sampling had addressed only single-output reconstruction, while supervised methods need domain-specific training and mostly assume a spatially constant blend coefficient. This work formulates deblending as a joint inverse problem, denoises two source images in parallel with one pretrained diffusion prior, constrains the solution with text prompts and a second-order polynomial alpha map, and reports the best PSNR, SSIM and LPIPS on unseen domains while staying competitive with supervised baselines on known-scalar benchmarks.

You’re all caught up