Progressive Multi-Scale Super-Resolution via Cascaded Bicubic Anchors and Inter-Scale Mutual Refinement
cs.CV, cs.LG, eess.IV
Submitted: 2026-11-02
Updated: 2026-11-16
Comments: 14 pages, 7 figures, 7 tables. Submitted to an IEEE journal. Code and pretrained models will be released at https://github.com/julian135707/PMS-SR upon acceptance
Code: https://github.com/julian135707/PMS-SR
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs