Attention-based View Selection Networks for Light-field Disparity Estimation

This paper introduces a novel deep network for estimating depth maps from a light field image. For utilizing the views more effectively and reducing redundancy within views, we propose a view selection module that generates an attention map indicating the importance of each view and its potential for contributing to accurate depth estimation. By exploring the symmetric property of light field views, we enforce symmetry in the attention map and further improve accuracy. With the attention map, our architecture utilizes all views more effectively and efficiently. Experiments show that the proposed method achieves state-of-the-art performance in terms of accuracy and ranks the first on a popular benchmark for disparity estimation for light field images.

Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Depth Estimation 4D Light Field Dataset LFattNet BadPix(0.07) 3.756 # 1
MSE 1.904 # 1
BadPix(0.03) 6.823 # 1
BadPix(0.01) 17.226 # 1


No methods listed for this paper. Add relevant methods here