VOSR shows that competitive generative image super-resolution with faithful structures can be achieved by training a diffusion-style model from scratch on visual data alone, using a vision encoder for guidance and a restoration-oriented sampling strategy.
Pixel-aware stable diffusion for realistic image super-resolution and personalized stylization
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 4roles
baseline 1polarities
baseline 1representative citing papers
FoA-SR trains separate Faithful and Aesthetic LoRA adapters by ranking a shared stochastic candidate pool with profile-specific rewards after initial supervised Flux2SR training.
EAM is a DiT-based blind super-resolution model that uses a triple-flow Ψ-DiT block, progressive masked image modeling, and in-context subject-aware prompting to reach state-of-the-art quantitative and visual results on standard datasets.
The NTIRE 2026 mobile real-world image super-resolution challenge received 16 valid submissions and overviews methods balancing image quality with mobile execution speed.
citing papers explorer
-
VOSR: A Vision-Only Generative Model for Image Super-Resolution
VOSR shows that competitive generative image super-resolution with faithful structures can be achieved by training a diffusion-style model from scratch on visual data alone, using a vision encoder for guidance and a restoration-oriented sampling strategy.
-
FoA-SR: Faithful or Aesthetic? Profile-Aware Preference Optimization for Real-World Image Super-Resolution
FoA-SR trains separate Faithful and Aesthetic LoRA adapters by ranking a shared stochastic candidate pool with profile-specific rewards after initial supervised Flux2SR training.
-
EAM: Enhancing Anything with Diffusion Transformers for Blind Super-Resolution
EAM is a DiT-based blind super-resolution model that uses a triple-flow Ψ-DiT block, progressive masked image modeling, and in-context subject-aware prompting to reach state-of-the-art quantitative and visual results on standard datasets.
-
The First Challenge on Mobile Real-World Image Super-Resolution at NTIRE 2026: Benchmark Results and Method Overview
The NTIRE 2026 mobile real-world image super-resolution challenge received 16 valid submissions and overviews methods balancing image quality with mobile execution speed.