Restoring Real-World Degraded Events Improves Deblurring Quality
Yeqing Shen, Shang Li, Kun Song

TL;DR
This paper introduces RDNet, a novel method for restoring degraded real-world events to enhance motion deblurring quality, supported by a new dataset DavisMCR and extensive experiments showing superior performance.
Contribution
The paper models event degradation, proposes RDNet for event restoration and deblurring, and introduces DavisMCR dataset for real-world evaluation.
Findings
RDNet outperforms classical event denoising methods.
RDNet achieves better deblurring results than state-of-the-art methods.
DavisMCR dataset enables comprehensive real-world event evaluation.
Abstract
Due to its high speed and low latency, DVS is frequently employed in motion deblurring. Ideally, high-quality events would adeptly capture intricate motion information. However, real-world events are generally degraded, thereby introducing significant artifacts into the deblurred results. In response to this challenge, we model the degradation of events and propose RDNet to improve the quality of image deblurring. Specifically, we first analyze the mechanisms underlying degradation and simulate paired events based on that. These paired events are then fed into the first stage of the RDNet for training the restoration model. The events restored in this stage serve as a guide for the second-stage deblurring process. To better assess the deblurring performance of different methods on real-world degraded events, we present a new real-world dataset named DavisMCR. This dataset incorporates…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsPublic Relations and Crisis Communication
MethodsSPEED: Separable Pyramidal Pooling EncodEr-Decoder for Real-Time Monocular Depth Estimation on Low-Resource Settings · RDNet
