Light Field Compression Based on Implicit Neural Representation
This addresses data storage and transmission challenges for multimedia applications using light fields, but it is incremental as it builds on existing implicit neural representation techniques.
The paper tackles the problem of large data volume in light field compression by proposing a scheme based on implicit neural representation to reduce redundancies between views, achieving comparable rate-distortion performance and superior perceptual quality over traditional methods.
Light field, as a new data representation format in multimedia, has the ability to capture both intensity and direction of light rays. However, the additional angular information also brings a large volume of data. Classical coding methods are not effective to describe the relationship between different views, leading to redundancy left. To address this problem, we propose a novel light field compression scheme based on implicit neural representation to reduce redundancies between views. We store the information of a light field image implicitly in an neural network and adopt model compression methods to further compress the implicit representation. Extensive experiments have demonstrated the effectiveness of our proposed method, which achieves comparable rate-distortion performance as well as superior perceptual quality over traditional methods.