| Presentation | 2023-03-03 Memory Efficient Trilinear Up-sampling for Sparse Voxels Riku Yamashita, Yusuke Matsui, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | We propose a memory-efficient Trilinear Up-sampling algorithm for sparse voxel data. Unlike conventional dense Trilinear Up-sampling, our approach can up-sample the sparse data while keeping it sparse. We first check the region around each input voxel to ensure a valid space. We then iteratively update the feature vectors corresponding to the space while considering the contribution of each input voxel. The experiments on both CPU and GPU showed that our approach is much more memory efficient, especially when the feature vectors are high-dimension ($80$ % for $D=100$). |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | 3D image processing / Voxel / Up-sampling / Memory efficient |
| Paper # | PRMU2022-102,IBISML2022-109 |
| Date of Issue | 2023-02-23 (PRMU, IBISML) |
| Conference Information | |
| Committee | PRMU / IBISML / IPSJ-CVIM |
|---|---|
| Conference Date | 2023/3/2(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Future University Hakodate |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Seiichi Uchida(Kyushu Univ.) / Masashi Sugiyama(Univ. of Tokyo) |
| Vice Chair | Takuya Funatomi(NAIST) / Mitsuru Anpai(Denso IT Lab.) / Toshihiro Kamishima(AIST) / Koji Tsuda(Univ. of Tokyo) |
| Secretary | Takuya Funatomi(CyberAgent) / Mitsuru Anpai(Univ. of Tokyo) / Toshihiro Kamishima(NTT) / Koji Tsuda(Hokkaido Univ.) |
| Assistant | Nakamasa Inoue(Tokyo Inst. of Tech.) / Yasutomo Kawanishi(Riken) / Yoshinobu Kawahara(Osaka Univ.) / Taiji Suzuki(Tokyo Inst. of Tech.) |
| Paper Information | |
| Registration To | Technical Committee on Pattern Recognition and Media Understanding / Technical Committee on Information-Based Induction Sciences and Machine Learning / Special Interest Group on Computer Vision and Image Media |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Memory Efficient Trilinear Up-sampling for Sparse Voxels |
| Sub Title (in English) | |
| Keyword(1) | 3D image processing |
| Keyword(2) | Voxel |
| Keyword(3) | Up-sampling |
| Keyword(4) | Memory efficient |
| 1st Author's Name | Riku Yamashita |
| 1st Author's Affiliation | The University of Tokyo(UTokyo) |
| 2nd Author's Name | Yusuke Matsui |
| 2nd Author's Affiliation | The University of Tokyo(UTokyo) |
| Date | 2023-03-03 |
| Paper # | PRMU2022-102,IBISML2022-109 |
| Volume (vol) | vol.122 |
| Number (no) | PRMU-404,IBISML-405 |
| Page | pp.pp.226-231(PRMU), pp.226-231(IBISML), |
| #Pages | 6 |
| Date of Issue | 2023-02-23 (PRMU, IBISML) |