2022/01/07 by Ziteng Cui, Cui, Ziteng, Yingying Zhu +13
Computer Science · Engineering · Physics and Astronomy · #Advanced Image Processing Techniques #Advanced Optical Sensing Technologies #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image Processing Techniques and Applications #Image and Video Processing (eess.IV) #cs.CV #eess.IV #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2201.02314
11 pages, 3figures
arxiv created 2022/01/07 · openalex publication_date 2022/01/07 · arxiv updated 2022/01/10 · openalex created_date 2022/05/05 · openalex updated_date 2026/07/28
Image restoration algorithms such as super resolution (SR) are indispensable pre-processing modules for object detection in degraded images. However, most of these algorithms assume the degradation is fixed and known a priori. When the real degradation is unknown or differs from assumption, both the pre-processing module and the consequent high-level task such as object detection would fail. Here, we propose a novel framework, RestoreDet, to detect objects in degraded low resolution images. RestoreDet utilizes the downsampling degradation as a kind of transformation for self-supervised signals to explore the equivariant representation against various resolutions and other degradation conditions. Specifically, we learn this intrinsic visual structure by encoding and decoding the degradation transformation from a pair of original and randomly degraded images. The framework could further take the advantage of advanced SR architectures with an arbitrary resolution restoring decoder to reconstruct the original correspondence from the degraded input image. Both the representation learning and object detection are optimized jointly in an end-to-end training fashion. RestoreDet is a generic framework that could be implemented on any mainstream object detection architectures. The extensive experiment shows that our framework based on CenterNet has achieved superior performance compared with existing methods when facing variant degradation situations. Our code would be released soon.