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.
Resshift: Efficient diffusion model for image super-resolution by residual shifting
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
baseline 1
citation-polarity summary
fields
cs.CV 4years
2026 4representative citing papers
PiD is a pixel diffusion decoder that performs latent-to-pixel conversion and 4-8x upsampling in one generative step, enabling early stopping of latent diffusion and achieving sub-second 2048x2048 decoding with claimed better fidelity than cascaded baselines.
MetaSR adaptively orchestrates metadata in a DiT-based generative SR model to deliver up to 1 dB PSNR gains and 50% bitrate savings across diverse content and degradations.
PERCEPT-Net uses motion perceptual loss in a residual U-Net with attention and multi-scale modules to remove MRI motion artifacts more effectively than prior methods on clinical data.
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.
-
PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion
PiD is a pixel diffusion decoder that performs latent-to-pixel conversion and 4-8x upsampling in one generative step, enabling early stopping of latent diffusion and achieving sub-second 2048x2048 decoding with claimed better fidelity than cascaded baselines.
-
MetaSR: Content-Adaptive Metadata Orchestration for Generative Super-Resolution
MetaSR adaptively orchestrates metadata in a DiT-based generative SR model to deliver up to 1 dB PSNR gains and 50% bitrate savings across diverse content and degradations.
-
Removing Motion Artifact in MRI by Using a Perceptual Loss Driven Deep Learning Framework
PERCEPT-Net uses motion perceptual loss in a residual U-Net with attention and multi-scale modules to remove MRI motion artifacts more effectively than prior methods on clinical data.