Home

Awesome

EDWL (ECCV2022)

An Gia Vien and Chul Lee

Official PyTorch Code for "Exposure-Aware Dynamic Weighted Learning for Single-Shot HDR Imaging"

Paper link: https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136670429.pdf

Supplemental material document: https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136670429-supp.pdf

Introduction

We propose a novel single-shot high dynamic range (HDR) imaging algorithm based on exposure-aware dynamic weighted learning, which reconstructs an HDR image from a spatially varying exposure (SVE) raw image. First, we recover poorly exposed pixels by developing a network that learns local dynamic filters to exploit local neighboring pixels across color channels. Second, we develop another network that combines only valid features in well-exposed regions by learning exposure-aware feature fusion. Third, we synthesize the raw radiance map by adaptively combining the outputs of the two networks that have different characteristics with complementary information. Finally, a full-color HDR image is obtained by interpolating missing color information.

Requirements

Set up

Usage

Running the test code:

    $ python Main_testing.py

We are in preparing to share train and evaluation metric estimation codes soon!

Citation

Please cite the following paper if you feel this repository useful.

    @inproceedings{EDWL,
        author    = {An Gia Vien and Chul Lee}, 
        title     = {Exposure-Aware Dynamic Weighted Learning for Single-Shot HDR Imaging}, 
        booktitle = {European Conference on Computer Vision},
        year      = {2022}
    }

License

See MIT License