Robust high dynamic range (hdr) imaging with complex motion and parallax
High dynamic range (HDR) imaging is widely used in consumer photography, computer
game rendering, autonomous driving, and surveillance systems. Reconstructing ghosting …
game rendering, autonomous driving, and surveillance systems. Reconstructing ghosting …
Neural augmented exposure interpolation for two large-exposure-ratio images
Brightness order reversal could happen among shadow regions in a bright image and high-
light regions in a dark image if two large-exposure-ratio images are fused directly by using …
light regions in a dark image if two large-exposure-ratio images are fused directly by using …
How to cheat with metrics in single-image HDR reconstruction
Single-image high dynamic range (SI-HDR) reconstruction has recently emerged as a
problem well-suited for deep learning methods. Each successive technique demonstrates …
problem well-suited for deep learning methods. Each successive technique demonstrates …
Deep unsupervised learning based on color un-referenced loss functions for multi-exposure image fusion
Y Qi, S Zhou, Z Zhang, S Luo, X Lin, L Wang, B Qiang - Information Fusion, 2021 - Elsevier
In this paper, an unsupervised learning-based approach is presented for fusing bracketed
exposures into high-quality images that avoids the need for interim conversion to …
exposures into high-quality images that avoids the need for interim conversion to …
Attention-guided progressive neural texture fusion for high dynamic range image restoration
High Dynamic Range (HDR) imaging via multi-exposure fusion is an important task for most
modern imaging platforms. In spite of recent developments in both hardware and algorithm …
modern imaging platforms. In spite of recent developments in both hardware and algorithm …
Attention-based network for low-light image enhancement
The captured images under low-light conditions often suffer insufficient brightness and
notorious noise. Hence, low-light image enhancement is a key challenging task in computer …
notorious noise. Hence, low-light image enhancement is a key challenging task in computer …
[PDF][PDF] Learning Exposure Correction Via Consistency Modeling.
Existing works on exposure correction have exclusively focused on either underexposure or
over-exposure. Recent work targeting both under-, and over-exposure achieved state of the …
over-exposure. Recent work targeting both under-, and over-exposure achieved state of the …
A lightweight network for high dynamic range imaging
Multi-frame high dynamic range (HDR) reconstruction methods try to expand the range of
illuminance with differently exposed images. They suffer from ghost artifacts when camera …
illuminance with differently exposed images. They suffer from ghost artifacts when camera …
LiTMNet: A deep CNN for efficient HDR image reconstruction from a single LDR image
G Wu, R Song, M Zhang, X Li, PL Rosin - Pattern Recognition, 2022 - Elsevier
Existing methods can generate a high dynamic range (HDR) image from a single low
dynamic range (LDR) image using convolutional neural networks (CNNs). However, they …
dynamic range (LDR) image using convolutional neural networks (CNNs). However, they …
BacklitNet: A dataset and network for backlit image enhancement
Backlit images are usually taken when the light source is opposite to the camera. The
uneven exposure (eg, underexposure on the foreground and overexposure on the …
uneven exposure (eg, underexposure on the foreground and overexposure on the …