OP4KSR enables efficient one-step 4K super-resolution without patches by adapting Flux with RoPE rescaling and periodicity loss to suppress artifacts.
In: European conference on computer vision
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
fields
cs.CV 6years
2026 6verdicts
UNVERDICTED 6representative citing papers
SEAR introduces a dual-process agentic framework for image restoration that combines pruning-aware MCTS planning with self-evolving episodic memory to address greedy search and episodic amnesia limitations.
FreqOrtho-SR combines FFT-routed MoE adapters with SVD-based orthogonal projection of semantic gradients to improve fidelity-perception trade-off in single-step real-world super-resolution.
DS-DiT decouples LR and Ref conditions in a Siamese diffusion transformer, adds patch-level weighting, and uses 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.
AlloSR² claims state-of-the-art one-step real-world super-resolution by SNR-guided trajectory init, velocity regularization (FATC), and allomorphic self-adversarial distillation that preserves flow-matching generative priors.
citing papers explorer
-
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.
-
Self-Evolving Agentic Image Restoration via Deliberate Planning and Intuitive Execution
SEAR introduces a dual-process agentic framework for image restoration that combines pruning-aware MCTS planning with self-evolving episodic memory to address greedy search and episodic amnesia limitations.
-
FreqOrtho-SR: Frequency-Guided Orthogonal Expert Learning for Real-World Image Super-Resolution
FreqOrtho-SR combines FFT-routed MoE adapters with SVD-based orthogonal projection of semantic gradients to improve fidelity-perception trade-off in single-step real-world super-resolution.
-
Learning to Balance: Decoupled Siamese Diffusion Transformer for Reference-Based Remote Sensing Image Super-Resolution
DS-DiT decouples LR and Ref conditions in a Siamese diffusion transformer, adds patch-level weighting, and uses 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.
-
Allo{SR}$^2$: Rectifying One-Step Super-Resolution to Stay Real via Allomorphic Generative Flows
AlloSR² claims state-of-the-art one-step real-world super-resolution by SNR-guided trajectory init, velocity regularization (FATC), and allomorphic self-adversarial distillation that preserves flow-matching generative priors.