Transition-constant Normalization for Image Enhancement
Dec 10, 2023
Speakers
Jinghao Zhang
Speaker · 0 followers
Mingde Yao
Speaker · 0 followers
Chongyi Li
Speaker · 0 followers
Zhiwei Xiong
Speaker · 0 followers
About
Normalization techniques that capture image style by statistical representation have become a popular component in deep neural networks.While image enhancement can be considered a form of style transformation, there has been little exploration of how normalization affects enhancement performance. To fully leverage the potential of normalization, we present a novel Transition-Constant Normalization (TCN) for various image enhancement tasks.Specifically, it consists of two streams of normalization operations arranged under an invertible constraint, along with a feature sub-sampling operation that satisfies the normalization constraint.TCN enjoys several merits, including being parameter-free, plug-and-play, and incurring no additional computation costs.We provide various formats to utilize TCN for image enhancement, including seamless integration with enhancement networks, incorporation into encoder-decoder architectures for downsampling, and implementation of efficient architectures.Through extensive experiments on multiple image enhancement tasks, like low-light enhancement, exposure correction, SDR2HDR translation, and image dehazing, our TCN consistently demonstrates performance improvements.Besides, it showcases extensive ability in other tasks including pan-sharpening and medical segmentation.Normalization techniques that capture image style by statistical representation have become a popular component in deep neural networks.While image enhancement can be considered a form of style transformation, there has been little exploration of how normalization affects enhancement performance. To fully leverage the potential of normalization, we present a novel Transition-Constant Normalization (TCN) for various image enhancement tasks.Specifically, it consists of two streams of normalization…
Organizer
NeurIPS 2023
Account · 645 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Curriculum Learning for Graph Neural Network: Which Edges Should We Learn First
Watch later
Zheng Zhang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Enhancing Knowledge Transfer for Task Incremental Learning with Data-free Subnetwork
Watch later
Qiang Gao, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
ContinuAR: Continuous Autoregression For Infinite-Fidelity Fusion
Watch later
Wei W. Xing, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Towards Robust and Expressive Whole-body Human Pose and Shape Estimation
Watch later
Hui En Pang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
On Privacy and Personalization in Federated Learning
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Mitigating Over-smoothing in Transformers via Regularized Nonlocal Functionals
Watch later
Tam Nguyen, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%