FPNforV-PCC

Citation Author(s):
Que
Shicheng
Submitted by:
Zhui Zuo
Last updated:
Sat, 09/23/2023 - 07:46
DOI:
10.21227/hb84-q682
License:
18 Views
Categories:
Keywords:
0
0 ratings - Please login to submit your rating.

Abstract 

This dataset is for paper "FPN-based V-PCC Fast CU Partition Approach", and is what the authors use for training the FPN mentioned in the paper. The CU partitioning data in this dataset comes from V-PCC using VVC to make CU partition and extracting data for a sample based on 64×64 CU. Encoder configuration when extracting data as described in Section III-A of the paper, the point cloud source is the first 32 frames of basketball_player order by owlii, including the partitioning of 5 different QPs. In the dataset, "AttrI_TOri" and "GeomP_TOri" represents the input for luma values, "AttrI_Resi" and "GeomP_Resi" stands for the prediction residual input, "AttrI_Occu" and "GeomP_Occu" denotes the placeholder information input, and "AttrI_y_QP" and "GeomP_y_QP" encompasses both the label value and QP input.

Instructions: 

"AttrI_TOri" and "GeomP_TOri" represents the input for luma values, "AttrI_Resi" and "GeomP_Resi" stands for the prediction residual input, "AttrI_Occu" and "GeomP_Occu" denotes the placeholder information input, and "AttrI_y_QP" and "GeomP_y_QP" encompasses both the label value and QP input, in "XXXX_y_QP" the first 480 columns are label vectors' elements and the last column is QP value.