Papers › Repulsive Latent Score Distillation for Solving Inverse Problems

Repulsive Latent Score Distillation for Solving Inverse Problems

24 Jun 2024arXiv:2406.16683archive 2025-07-28

Nicolas Zilberstein, Morteza Mardani, Santiago Segarra

Score Distillation Sampling (SDS) has been pivotal for leveraging pre-trained diffusion models in downstream tasks such as inverse problems, but it faces two major challenges: (i) mode collapse and (ii) latent space inversion, which become more pronounced in high-dimensional data. To address mode collapse, we introduce a novel variational framework for posterior sampling. Utilizing the Wasserstein gradient flow interpretation of SDS, we propose a multimodal variational approximation with a repulsion mechanism that promotes diversity among particles by penalizing pairwise kernel-based similarity. This repulsion acts as a simple regularizer, encouraging a more diverse set of solutions. To mitigate latent space ambiguity, we extend this framework with an augmented variational distribution that disentangles the latent and data. This repulsive augmented formulation balances computational efficiency, quality, and diversity. Extensive experiments on linear and nonlinear inverse tasks with high-resolution images (512 ×512) using pre-trained Stable Diffusion models demonstrate the effectiveness of our approach.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

nzilberstein/Repulsive-score-distillation-RSD- officialmentioned in papermentioned on GitHubjax report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Computational EfficiencyDiversityImage GenerationText-to-Image Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DiffusionFocusSET

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections