HyperCUT: Video Sequence from a Single Blurry Image using Unsupervised Ordering

04/04/2023
by   Bang-Dang Pham, et al.
0

We consider the challenging task of training models for image-to-video deblurring, which aims to recover a sequence of sharp images corresponding to a given blurry image input. A critical issue disturbing the training of an image-to-video model is the ambiguity of the frame ordering since both the forward and backward sequences are plausible solutions. This paper proposes an effective self-supervised ordering scheme that allows training high-quality image-to-video deblurring models. Unlike previous methods that rely on order-invariant losses, we assign an explicit order for each video sequence, thus avoiding the order-ambiguity issue. Specifically, we map each video sequence to a vector in a latent high-dimensional space so that there exists a hyperplane such that for every video sequence, the vectors extracted from it and its reversed sequence are on different sides of the hyperplane. The side of the vectors will be used to define the order of the corresponding sequence. Last but not least, we propose a real-image dataset for the image-to-video deblurring problem that covers a variety of popular domains, including face, hand, and street. Extensive experimental results confirm the effectiveness of our method. Code and data are available at https://github.com/VinAIResearch/HyperCUT.git

READ FULL TEXT

page 4

page 5

page 6

page 12

research
07/20/2019

Order Matters: Shuffling Sequence Generation for Video Prediction

Predicting future frames in natural video sequences is a new challenge t...
research
07/20/2022

Animation from Blur: Multi-modal Blur Decomposition with Motion Guidance

We study the challenging problem of recovering detailed motion from a si...
research
03/24/2023

Conditional Image-to-Video Generation with Latent Flow Diffusion Models

Conditional image-to-video (cI2V) generation aims to synthesize a new pl...
research
08/19/2021

Click to Move: Controlling Video Generation with Sparse Motion

This paper introduces Click to Move (C2M), a novel framework for video g...
research
07/01/2022

How Far Can I Go ? : A Self-Supervised Approach for Deterministic Video Depth Forecasting

In this paper we present a novel self-supervised method to anticipate th...
research
10/16/2019

Animating Landscape: Self-Supervised Learning of Decoupled Motion and Appearance for Single-Image Video Synthesis

Automatic generation of a high-quality video from a single image remains...
research
02/21/2022

Rethinking the Zigzag Flattening for Image Reading

Sequence ordering of word vector matters a lot to text reading, which ha...

Please sign up or login with your details

Forgot password? Click here to reset