HDR Video Reconstruction: A Coarse-to-fine Network and A Real-world Benchmark Dataset

03/27/2021
by   Guanying Chen, et al.
0

High dynamic range (HDR) video reconstruction from sequences captured with alternating exposures is a very challenging problem. Existing methods often align low dynamic range (LDR) input sequence in the image space using optical flow, and then merge the aligned images to produce HDR output. However, accurate alignment and fusion in the image space are difficult due to the missing details in the over-exposed regions and noise in the under-exposed regions, resulting in unpleasing ghosting artifacts. To enable more accurate alignment and HDR fusion, we introduce a coarse-to-fine deep learning framework for HDR video reconstruction. Firstly, we perform coarse alignment and pixel blending in the image space to estimate the coarse HDR video. Secondly, we conduct more sophisticated alignment and temporal fusion in the feature space of the coarse HDR video to produce better reconstruction. Considering the fact that there is no publicly available dataset for quantitative and comprehensive evaluation of HDR video reconstruction methods, we collect such a benchmark dataset, which contains 97 sequences of static scenes and 184 testing pairs of dynamic scenes. Extensive experiments show that our method outperforms previous state-of-the-art methods. Our dataset, code and model will be made publicly available.

READ FULL TEXT

page 1

page 3

page 6

page 7

page 8

research
08/22/2023

LAN-HDR: Luminance-based Alignment Network for High Dynamic Range Video Reconstruction

As demands for high-quality videos continue to rise, high-resolution and...
research
08/22/2023

High Dynamic Range Imaging of Dynamic Scenes with Saturation Compensation but without Explicit Motion Compensation

High dynamic range (HDR) imaging is a highly challenging task since a la...
research
06/27/2022

A Novel Unified Self-alignment Method of SINS Based on FGO

The self-alignment process can provide an accurate initial attitude of S...
research
04/03/2020

RANSAC-Flow: generic two-stage image alignment

This paper considers the generic problem of dense alignment between two ...
research
10/14/2021

Coarse to Fine: Video Retrieval before Moment Localization

The current state-of-the-art methods for video corpus moment retrieval (...
research
07/04/2022

Segmentation Guided Deep HDR Deghosting

We present a motion segmentation guided convolutional neural network (CN...
research
08/19/2021

Progressive and Selective Fusion Network for High Dynamic Range Imaging

This paper considers the problem of generating an HDR image of a scene f...

Please sign up or login with your details

Forgot password? Click here to reset