Neighborhood Adaptive Loss Function for Deep Learning-Based Point Cloud Coding With Implicit and Explicit Quantization

Guarda, Andre F. R.; Rodrigues, Nuno M. M.; Pereira, Fernando

http://hdl.handle.net/10400.8/7846

Use this identifier to reference this record.

Name:	Description:	Size:	Format:
Neighborhood_Adaptive_Loss_Function_for_Deep_Learning-Based_Point_Cloud_Coding_With_Implicit_and_Explicit_Quantization.pdf		2.86 MB	Adobe PDF	Download

Send Feedback

Authors

Guarda, Andre F. R.

Rodrigues, Nuno M. M.

Pereira, Fernando

Abstract(s)

As the interest in deep learning tools continues to rise, new multimedia research fields begin to discover its potential. Both image and point cloud coding are good examples of technologies, where deep learning-based solutions have recently displayed very competitive performance. In this context, this article brings two novel contributions to the point cloud geometry coding state-of-the-art; first, a novel neighborhood adaptive distortion metric to be used in the training loss function, which allows significantly improving the rate-distortion performance with commonly used objective quality metrics; second, an explicit quantization approach at the training and coding times to generate varying rate/quality with a single trained deep learning coding model, effectively reducing the training complexity and storage requirements. The result is an improved deep learning-based point cloud geometry coding solution, which is both more compression efficient and less demanding in training complexity and storage.

URI

http://hdl.handle.net/10400.8/7846

Citation

AFR Guarda, NMM Rodrigues e F. Pereira, "Neighborhood Adaptive Loss Function for Deep Learning-Based Point Cloud Coding With Implicit and Explicit Quantization", in IEEE MultiMedia , vol. 28, não. 3, pp. 107-116, 1º de julho-setembro. 2021, doi: 10.1109/MMUL.2020.3046691.