LRT: An Efficient Low-Light Restoration Transformer for Dark Light Field Images
arXiv:2209.02197 · doi:10.1109/TIP.2023.3297412
Abstract
Light field (LF) images containing information for multiple views have numerous applications, which can be severely affected by low-light imaging. Recent learning-based methods for low-light enhancement have some disadvantages, such as a lack of noise suppression, complex training process and poor performance in extremely low-light conditions. To tackle these deficiencies while fully utilizing the multi-view information, we propose an efficient Low-light Restoration Transformer (LRT) for LF images, with multiple heads to perform intermediate tasks within a single network, including denoising, luminance adjustment, refinement and detail enhancement, achieving progressive restoration from small scale to full scale. Moreover, we design an angular transformer block with an efficient view-token scheme to model the global angular dependencies, and a multi-scale spatial transformer block to encode the multi-scale local and global information within each view. To address the issue of insufficient training data, we formulate a synthesis pipeline by simulating the major noise sources with the estimated noise parameters of LF camera. Experimental results demonstrate that our method achieves the state-of-the-art performance on low-light LF restoration with high efficiency.
References in corpus (8)
- PVT v2: Improved Baselines with Pyramid Vision Transformer
- Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation
- Learning-Based View Synthesis for Light Field Cameras
- Light Field Image Super-Resolution with Transformers
- Selective Light Field Refocusing for Camera Arrays Using Bokeh Rendering and Superresolution
- Occlusion-aware Unsupervised Learning of Depth from 4-D Light Fields
- Progressive Joint Low-light Enhancement and Noise Removal for Raw Images
- Unsupervised Light Field Depth Estimation via Multi-view Feature Matching with Occlusion Prediction