RestoreDet: Degradation Equivariant Representation for Object Detection
in Low Resolution Images
- URL: http://arxiv.org/abs/2201.02314v1
- Date: Fri, 7 Jan 2022 03:40:23 GMT
- Title: RestoreDet: Degradation Equivariant Representation for Object Detection
in Low Resolution Images
- Authors: Ziteng Cui, Yingying Zhu, Lin Gu, Guo-Jun Qi, Xiaoxiao Li, Peng Gao,
Zenghui Zhang, Tatsuya Harada
- Abstract summary: We propose a novel framework, RestoreDet, to detect objects in degraded low resolution images.
Our framework based on CenterNet has achieved superior performance compared with existing methods when facing variant degradation situations.
- Score: 81.91416537019835
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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.
Related papers
- OneRestore: A Universal Restoration Framework for Composite Degradation [33.556183375565034]
In real-world scenarios, image impairments often manifest as composite degradations, presenting a complex interplay of elements such as low light, haze, rain, and snow.
Our study proposes a versatile imaging model that consolidates four physical corruption paradigms to accurately represent complex, composite degradation scenarios.
OneRestore is a novel transformer-based framework designed for adaptive, controllable scene restoration.
arXiv Detail & Related papers (2024-07-05T16:27:00Z) - Diff-Restorer: Unleashing Visual Prompts for Diffusion-based Universal Image Restoration [19.87693298262894]
We propose Diff-Restorer, a universal image restoration method based on the diffusion model.
We utilize the pre-trained visual language model to extract visual prompts from degraded images.
We also design a Degradation-aware Decoder to perform structural correction and convert the latent code to the pixel domain.
arXiv Detail & Related papers (2024-07-04T05:01:10Z) - Efficient Test-Time Adaptation for Super-Resolution with Second-Order
Degradation and Reconstruction [62.955327005837475]
Image super-resolution (SR) aims to learn a mapping from low-resolution (LR) to high-resolution (HR) using paired HR-LR training images.
We present an efficient test-time adaptation framework for SR, named SRTTA, which is able to quickly adapt SR models to test domains with different/unknown degradation types.
arXiv Detail & Related papers (2023-10-29T13:58:57Z) - All-in-one Multi-degradation Image Restoration Network via Hierarchical
Degradation Representation [47.00239809958627]
We propose a novel All-in-one Multi-degradation Image Restoration Network (AMIRNet)
AMIRNet learns a degradation representation for unknown degraded images by progressively constructing a tree structure through clustering.
This tree-structured representation explicitly reflects the consistency and discrepancy of various distortions, providing a specific clue for image restoration.
arXiv Detail & Related papers (2023-08-06T04:51:41Z) - Exploring Resolution and Degradation Clues as Self-supervised Signal for
Low Quality Object Detection [77.3530907443279]
We propose a novel self-supervised framework to detect objects in degraded low resolution images.
Our methods has achieved superior performance compared with existing methods when facing variant degradation situations.
arXiv Detail & Related papers (2022-08-05T09:36:13Z) - Hierarchical Similarity Learning for Aliasing Suppression Image
Super-Resolution [64.15915577164894]
A hierarchical image super-resolution network (HSRNet) is proposed to suppress the influence of aliasing.
HSRNet achieves better quantitative and visual performance than other works, and remits the aliasing more effectively.
arXiv Detail & Related papers (2022-06-07T14:55:32Z) - Spatially-Adaptive Image Restoration using Distortion-Guided Networks [51.89245800461537]
We present a learning-based solution for restoring images suffering from spatially-varying degradations.
We propose SPAIR, a network design that harnesses distortion-localization information and dynamically adjusts to difficult regions in the image.
arXiv Detail & Related papers (2021-08-19T11:02:25Z) - Gated Fusion Network for Degraded Image Super Resolution [78.67168802945069]
We propose a dual-branch convolutional neural network to extract base features and recovered features separately.
By decomposing the feature extraction step into two task-independent streams, the dual-branch model can facilitate the training process.
arXiv Detail & Related papers (2020-03-02T13:28:32Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.