Towards Real-World Burst Image Super-Resolution: Benchmark and Method

Liang Lin, Chang Liu, Jie Chen, Xiangyang Ji, Guanbin Li, Yujing Sun, Pengxu Wei, Xingbei Guo

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 29 functions out of this paper's own repositories and ran 22 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• yjsunnn/fbanet — marked official in Papers with Code; named in the paper
• yjsunnn/FBANet

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Despite substantial advances, single-image superresolution (SISR) is always in a dilemma to reconstruct high-quality images with limited information from one input image, especially in realistic scenarios. In this paper, we establish a large-scale real-world burst super-resolution dataset, i.e., RealBSR, to explore the faithful reconstruction of image details from multiple frames. Furthermore, we introduce a Federated Burst Affinity network (FBAnet) to investigate non-trivial pixel-wise displacements among images under real-world image degradation. Specifically, rather than using pixel-wise alignment, our FBAnet employs a simple homography alignment from a structural geometry aspect and a Federated Affinity Fusion (FAF) strategy to aggregate the complementary information among frames. Those fused informative representations are fed to a Transformerbased module of burst representation decoding. Besides, we have conducted extensive experiments on two versions of our datasets, i.e., RealBSR-RAW and RealBSR-RGB. Experimental results demonstrate that our FBAnet outperforms existing state-of-the-art burst SR methods and also achieves visually-pleasant SR image predictions with model details. Our dataset, codes, and models are publicly available at https://github.com/yjsunnn/FBANet.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2309.04803")
get_code_for_paper("2309.04803")
have("2309.04803")

Connect an agent — have() is free.