DiSI disentangles stochastic interpolants into separate generation and regression paths, allowing controllable transitions between regression and generative image restoration with a unified few-step sampler.
International Journal of Computer Vision 132(12), 5929–5949 (2024)
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
fields
cs.CV 8years
2026 8verdicts
UNVERDICTED 8representative citing papers
OP4KSR enables efficient one-step 4K super-resolution without patches by adapting Flux with RoPE rescaling and periodicity loss to suppress artifacts.
DS-DiT decouples low-resolution and reference interactions in a siamese diffusion transformer and adds a patch-level weights module plus autoguidance to improve reference-based super-resolution for remote sensing images.
TOC-SR builds a compact one-step diffusion model for image super-resolution achieving 6.6x fewer parameters and 2.8x fewer GMACs while maintaining strong reconstruction quality.
BurstGP enhances raw burst image super-resolution by integrating pretrained video diffusion priors through a multiframe-aware model, degradation-aware conditioning, and color-space conversion, outperforming prior methods on perceptual metrics.
Allo{SR}^2 rectifies one-step super-resolution trajectories with allomorphic generative flows via SNR initialization, velocity supervision, and self-adversarial matching to deliver state-of-the-art fidelity and realism.
LucidNFT combines a new LR-referenced consistency reward, decoupled normalization, and a real-degradation dataset to improve perceptual quality in flow-matching super-resolution while preserving input fidelity.
GleSAM++ improves SAM robustness on degraded images by using generative enhancement, feature alignment, and adaptive degradation prediction while adding few parameters.
citing papers explorer
-
Disentangling Generation and Regression in Stochastic Interpolants for Controllable Image Restoration
DiSI disentangles stochastic interpolants into separate generation and regression paths, allowing controllable transitions between regression and generative image restoration with a unified few-step sampler.
-
OP4KSR: One-Step Patch-Free 4K Super-Resolution with Periodic Artifact Suppression
OP4KSR enables efficient one-step 4K super-resolution without patches by adapting Flux with RoPE rescaling and periodicity loss to suppress artifacts.
-
Learning to Balance: Decoupled Siamese Diffusion Transformer for Reference-Based Remote Sensing Image Super-Resolution
DS-DiT decouples low-resolution and reference interactions in a siamese diffusion transformer and adds a patch-level weights module plus autoguidance to improve reference-based super-resolution for remote sensing images.
-
TOC-SR: Task-Optimal Compact diffusion for Image Super Resolution
TOC-SR builds a compact one-step diffusion model for image super-resolution achieving 6.6x fewer parameters and 2.8x fewer GMACs while maintaining strong reconstruction quality.
-
BurstGP: Enhancing Raw Burst Image Super Resolution with Generative Priors
BurstGP enhances raw burst image super-resolution by integrating pretrained video diffusion priors through a multiframe-aware model, degradation-aware conditioning, and color-space conversion, outperforming prior methods on perceptual metrics.
-
Allo{SR}$^2$: Rectifying One-Step Super-Resolution to Stay Real via Allomorphic Generative Flows
Allo{SR}^2 rectifies one-step super-resolution trajectories with allomorphic generative flows via SNR initialization, velocity supervision, and self-adversarial matching to deliver state-of-the-art fidelity and realism.
-
LucidNFT: LR-Anchored Multi-Reward Preference Optimization for Flow-Based Real-World Super-Resolution
LucidNFT combines a new LR-referenced consistency reward, decoupled normalization, and a real-degradation dataset to improve perceptual quality in flow-matching super-resolution while preserving input fidelity.
-
Towards Any-Quality Image Segmentation via Generative and Adaptive Latent Space Enhancement
GleSAM++ improves SAM robustness on degraded images by using generative enhancement, feature alignment, and adaptive degradation prediction while adding few parameters.