LDINet: Latent Decomposition-Interpolation for Single Image Fast-moving Objects Deblatting
Keywords: fast moving object deblatting, image deblur, time super-resolution, latent decomposition and interpolation
Abstract: The image of fast-moving objects (FMOs) usually contains a blur stripe indicating the blurred object that is mixed with the background. To deblur the stripe and separate the object from the background in the single image, in this work we propose a novel Latent Decomposition-Interpolation Network (LDINet) to generate the appearances and shapes of the objects. In particular, under the assumption that motion blur is an accumulation of the appearance of the object over exposure time and the long blur can be decomposed into several shorter blur parts, the blurry input is first encoded into latent feature maps and then an efficient Decomposition-Interpolation Module (DIM) is introduced to break down the feature maps into discrete time indexed parts corresponding to different small blurs. And the target latent frames are further interpolated according to the provided time indexes with affine transformations, where the feature maps are categorized into the scalar-like and gradient-like parts to effectively capture the intrinsic properties of features warping in the interpolation. Finally, the sharp and clear images are rendered with a decoder. In addition, based on the generated images by LDINet, a Refining Conditional Deblatting (RCD) approach is presented to use post-image-to-image techniques to further enhance the fidelity of the textures and the accuracy of the masks. Extensive experiments are conducted and have shown that the proposed methods achieve superior performances compared to the existing competing methods.
Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 10002
Loading