SpikeReveal: Unlocking Temporal Sequences from Real Blurry Inputs with Spike Streams
- URL: http://arxiv.org/abs/2403.09486v5
- Date: Sat, 26 Oct 2024 15:05:36 GMT
- Title: SpikeReveal: Unlocking Temporal Sequences from Real Blurry Inputs with Spike Streams
- Authors: Kang Chen, Shiyan Chen, Jiyuan Zhang, Baoyue Zhang, Yajing Zheng, Tiejun Huang, Zhaofei Yu,
- Abstract summary: Spike cameras have proven effective in capturing motion features and beneficial for solving this ill-posed problem.
Existing methods fall into the supervised learning paradigm, which suffers from notable performance degradation when applied to real-world scenarios.
We propose the first self-supervised framework for the task of spike-guided motion deblurring.
- Score: 44.02794438687478
- License:
- Abstract: Reconstructing a sequence of sharp images from the blurry input is crucial for enhancing our insights into the captured scene and poses a significant challenge due to the limited temporal features embedded in the image. Spike cameras, sampling at rates up to 40,000 Hz, have proven effective in capturing motion features and beneficial for solving this ill-posed problem. Nonetheless, existing methods fall into the supervised learning paradigm, which suffers from notable performance degradation when applied to real-world scenarios that diverge from the synthetic training data domain. Moreover, the quality of reconstructed images is capped by the generated images based on motion analysis interpolation, which inherently differs from the actual scene, affecting the generalization ability of these methods in real high-speed scenarios. To address these challenges, we propose the first self-supervised framework for the task of spike-guided motion deblurring. Our approach begins with the formulation of a spike-guided deblurring model that explores the theoretical relationships among spike streams, blurry images, and their corresponding sharp sequences. We subsequently develop a self-supervised cascaded framework to alleviate the issues of spike noise and spatial-resolution mismatching encountered in the deblurring model. With knowledge distillation and re-blurring loss, we further design a lightweight deblur network to generate high-quality sequences with brightness and texture consistency with the original input. Quantitative and qualitative experiments conducted on our real-world and synthetic datasets with spikes validate the superior generalization of the proposed framework. Our code, data and trained models will be available at \url{https://github.com/chenkang455/S-SDM}.
Related papers
- Rethinking High-speed Image Reconstruction Framework with Spike Camera [48.627095354244204]
Spike cameras generate continuous spike streams to capture high-speed scenes with lower bandwidth and higher dynamic range than traditional RGB cameras.
We introduce a novel spike-to-image reconstruction framework SpikeCLIP that goes beyond traditional training paradigms.
Our experiments on real-world low-light datasets demonstrate that SpikeCLIP significantly enhances texture details and the luminance balance of recovered images.
arXiv Detail & Related papers (2025-01-08T13:00:17Z) - Time Step Generating: A Universal Synthesized Deepfake Image Detector [0.4488895231267077]
We propose a universal synthetic image detector Time Step Generating (TSG)
TSG does not rely on pre-trained models' reconstructing ability, specific datasets, or sampling algorithms.
We test the proposed TSG on the large-scale GenImage benchmark and it achieves significant improvements in both accuracy and generalizability.
arXiv Detail & Related papers (2024-11-17T09:39:50Z) - Gear-NeRF: Free-Viewpoint Rendering and Tracking with Motion-aware Spatio-Temporal Sampling [70.34875558830241]
We present a way for learning a-temporal (4D) embedding, based on semantic semantic gears to allow for stratified modeling of dynamic regions of rendering the scene.
At the same time, almost for free, our tracking approach enables free-viewpoint of interest - a functionality not yet achieved by existing NeRF-based methods.
arXiv Detail & Related papers (2024-06-06T03:37:39Z) - SpikeNeRF: Learning Neural Radiance Fields from Continuous Spike Stream [26.165424006344267]
Spike cameras offer distinct advantages over standard cameras.
Existing approaches reliant on spike cameras often assume optimal illumination.
We introduce SpikeNeRF, the first work that derives a NeRF-based volumetric scene representation from spike camera data.
arXiv Detail & Related papers (2024-03-17T13:51:25Z) - RANRAC: Robust Neural Scene Representations via Random Ray Consensus [12.161889666145127]
RANdom RAy Consensus (RANRAC) is an efficient approach to eliminate the effect of inconsistent data.
We formulate a fuzzy adaption of the RANSAC paradigm, enabling its application to large scale models.
Results indicate significant improvements compared to state-of-the-art robust methods for novel-view synthesis.
arXiv Detail & Related papers (2023-12-15T13:33:09Z) - Deep Equilibrium Diffusion Restoration with Parallel Sampling [120.15039525209106]
Diffusion model-based image restoration (IR) aims to use diffusion models to recover high-quality (HQ) images from degraded images, achieving promising performance.
Most existing methods need long serial sampling chains to restore HQ images step-by-step, resulting in expensive sampling time and high computation costs.
In this work, we aim to rethink the diffusion model-based IR models through a different perspective, i.e., a deep equilibrium (DEQ) fixed point system, called DeqIR.
arXiv Detail & Related papers (2023-11-20T08:27:56Z) - RBSR: Efficient and Flexible Recurrent Network for Burst
Super-Resolution [57.98314517861539]
Burst super-resolution (BurstSR) aims at reconstructing a high-resolution (HR) image from a sequence of low-resolution (LR) and noisy images.
In this paper, we suggest fusing cues frame-by-frame with an efficient and flexible recurrent network.
arXiv Detail & Related papers (2023-06-30T12:14:13Z) - Recovering Continuous Scene Dynamics from A Single Blurry Image with
Events [58.7185835546638]
An Implicit Video Function (IVF) is learned to represent a single motion blurred image with concurrent events.
A dual attention transformer is proposed to efficiently leverage merits from both modalities.
The proposed network is trained only with the supervision of ground-truth images of limited referenced timestamps.
arXiv Detail & Related papers (2023-04-05T18:44:17Z) - Fast Image-Anomaly Mitigation for Autonomous Mobile Robots [27.049498074025088]
Camera anomalies like rain or dust can severelydegrade image quality and its related tasks.
In this work we address this importantissue by implementing a pre-processing step that can effectivelymitigate such artifacts in a real-time fashion.
arXiv Detail & Related papers (2021-09-04T15:39:42Z)
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.