Denoising single images by feature ensemble revisited
This addresses denoising challenges like spatial fidelity for computer vision applications, but appears incremental as it builds on existing modular concepts.
The paper tackled image denoising by proposing a simple architecture using modular concatenation to improve spatial fidelity and reduce cartoon-like smoothing, achieving significant improvements over state-of-the-art networks with fewer parameters.
Image denoising is still a challenging issue in many computer vision sub-domains. Recent studies show that significant improvements are made possible in a supervised setting. However, few challenges, such as spatial fidelity and cartoon-like smoothing remain unresolved or decisively overlooked. Our study proposes a simple yet efficient architecture for the denoising problem that addresses the aforementioned issues. The proposed architecture revisits the concept of modular concatenation instead of long and deeper cascaded connections, to recover a cleaner approximation of the given image. We find that different modules can capture versatile representations, and concatenated representation creates a richer subspace for low-level image restoration. The proposed architecture's number of parameters remains smaller than the number for most of the previous networks and still achieves significant improvements over the current state-of-the-art networks.