Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
WAVELET TRANSFORM BASED DEEP HIGH DYNAMIC RANGE IMAGING
Document Type and Number:
WIPO Patent Application WO/2022/094824
Kind Code:
A1
Abstract:
Described herein is an image processing apparatus (701) comprising one or more processors (704) configured to: receive (601) a plurality of input images (301, 302, 303); for each input image, form (602) a set of decomposed data by decomposing the input image (301, 302, 303) or a filtered version thereof (307, 308, 309) into a plurality of frequency-specific components (313) each representing the occurrence of features of a respective frequency interval in the input image or the filtered version thereof; process (603) each set of decomposed data using one or more convolutional neural networks to form a combined image dataset (327); and subject (604) the combined image dataset (327) to a construction operation that is adapted for image construction from a plurality of frequency-specific components to thereby form an output image (333) representing a combination of the input images. The resulting HDR output image may have fewer artifacts and provide a better quality result. The apparatus is also computationally efficient, having a good balance between accuracy and efficiency.

Inventors:
DAI TIANHONG (CN)
YUAN SHANXIN (CN)
JIA XU (CN)
Application Number:
PCT/CN2020/126617
Publication Date:
May 12, 2022
Filing Date:
November 05, 2020
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
HUAWEI TECH CO LTD (CN)
International Classes:
H04N19/63; G06T5/50
Domestic Patent References:
WO2015133593A12015-09-11
WO2019112085A12019-06-13
Foreign References:
CN111861957A2020-10-30
CN111382795A2020-07-07
CN111161128A2020-05-15
CN110728614A2020-01-24
CN103700072A2014-04-02
Other References:
K.RAM PRABHAKARKSUSMIT AGRAWALDURGESH KUMAR SINGHBALRAJ ASHWATHR.VENKATESH BABU: "Towards practical and efficient high-resolution HDR deghosting with CNN", PROCEEDINGS OF THE EUROPEAN CONFERENCE ON COMPUTER VISION (ECCV, 2020
SHANGZHE WUJIARUI XUYU-WING TAICHI-KEUNG TANG: "Deep high dynamic range imaging with large foreground motions", PROCEEDINGS OF THE EUROPEAN CONFERENCE ON COMPUTER VISION (ECCV, 2018
QINGSEN YANDONG GONGPINGPING ZHANGQINGFENG SHIJINQIU SUNIAN REIDYANNING ZHANG: "Multi-scale dense networks for deep high dynamic range imaging", IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV, 2019
QINGSEN YANLEI ZHANGYU LIUYU ZHUJINQIU SUNQINFENG SHIYANNING ZHANG: "Deep hdr imaging via a non-local network", IEEE TRANSACTIONS ON IMAGE PROCESSING, 2020
QINGSEN YANDONG GONGQINFENG SHIANTON VAN DEN HENGELCHUNHUA SHENIAN REIDYANNING ZHANG: "Attention-guided network for ghost-free high dynamic range imaging", PROCEEDINGS OF THE IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR, 2019
MATSUOKA RYO ET AL., TRANSFORMED-DOMAIN ROBUST MULTIPLE-EXPOSURE BLENDING WITH HUBER LOSS
YAN QINGSEN ET AL., ATTENTION-GUIDED NETWORK FOR GHOST-FREE HIGH DYNAMIC RANGE IMAGING
RONNEBERGER, OLAFPHILIPP FISCHERTHOMAS BROX: "Conference on Medical image computing and computer-assisted intervention", 2015, SPRINGER, article "U-net: Convolutional networks for biomedical image segmentation", pages: 234 - 241
See also references of EP 4197192A4
Download PDF: