Focal Surface Holographic Light Transport using Learned Spatially Adaptive Convolutions
SA Technical Communications ’24, December 03–06, 2024, Tokyo, Japan
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
ACM|SIGGRAPH Asia 2024 Technical Communications
2024
|
| Online Access: | https://hdl.handle.net/1721.1/157841 |
| _version_ | 1824457926920634368 |
|---|---|
| author | Zheng, Chuanjun Zhan, Yicheng Shi, Liang Cakmakci, Ozan Ak?it, Kaan |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Zheng, Chuanjun Zhan, Yicheng Shi, Liang Cakmakci, Ozan Ak?it, Kaan |
| author_sort | Zheng, Chuanjun |
| collection | MIT |
| description | SA Technical Communications ’24, December 03–06, 2024, Tokyo, Japan |
| first_indexed | 2025-02-19T04:17:46Z |
| format | Article |
| id | mit-1721.1/157841 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2025-02-19T04:17:46Z |
| publishDate | 2024 |
| publisher | ACM|SIGGRAPH Asia 2024 Technical Communications |
| record_format | dspace |
| spelling | mit-1721.1/1578412025-02-13T19:35:12Z Focal Surface Holographic Light Transport using Learned Spatially Adaptive Convolutions Zheng, Chuanjun Zhan, Yicheng Shi, Liang Cakmakci, Ozan Ak?it, Kaan Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory SA Technical Communications ’24, December 03–06, 2024, Tokyo, Japan Computer-Generated Holography (CGH) is a set of algorithmic methods for identifying holograms that reconstruct Three-Dimensio-nal (3D) scenes in holographic displays. CGH algorithms decompose 3D scenes into multiplanes at different depth levels and rely on simulations of light that propagated from a source plane to a targeted plane. Thus, for n planes, CGH typically optimizes holograms using n plane-to-plane light transport simulations, leading to major time and computational demands. Our work replaces multiple planes with a focal surface and introduces a learned light transport model that could propagate a light field from a source plane to the focal surface in a single inference. Our model leverages spatially adaptive convolution to achieve depth-varying propagation demanded by targeted focal surfaces. The proposed model reduces the hologram optimization process up to 1.5x, which contributes to hologram dataset generation and the training of future learned CGH models. 2024-12-12T21:04:47Z 2024-12-12T21:04:47Z 2024-12-03 2024-12-01T08:49:50Z Article http://purl.org/eprint/type/ConferencePaper 979-8-4007-1140-4 https://hdl.handle.net/1721.1/157841 Zheng, Chuanjun, Zhan, Yicheng, Shi, Liang, Cakmakci, Ozan and Ak?it, Kaan. 2024. "Focal Surface Holographic Light Transport using Learned Spatially Adaptive Convolutions." PUBLISHER_CC en https://doi.org/10.1145/3681758.3697989 Creative Commons Attribution https://creativecommons.org/licenses/by/4.0/ The author(s) application/pdf ACM|SIGGRAPH Asia 2024 Technical Communications Association for Computing Machinery |
| spellingShingle | Zheng, Chuanjun Zhan, Yicheng Shi, Liang Cakmakci, Ozan Ak?it, Kaan Focal Surface Holographic Light Transport using Learned Spatially Adaptive Convolutions |
| title | Focal Surface Holographic Light Transport using Learned Spatially Adaptive Convolutions |
| title_full | Focal Surface Holographic Light Transport using Learned Spatially Adaptive Convolutions |
| title_fullStr | Focal Surface Holographic Light Transport using Learned Spatially Adaptive Convolutions |
| title_full_unstemmed | Focal Surface Holographic Light Transport using Learned Spatially Adaptive Convolutions |
| title_short | Focal Surface Holographic Light Transport using Learned Spatially Adaptive Convolutions |
| title_sort | focal surface holographic light transport using learned spatially adaptive convolutions |
| url | https://hdl.handle.net/1721.1/157841 |
| work_keys_str_mv | AT zhengchuanjun focalsurfaceholographiclighttransportusinglearnedspatiallyadaptiveconvolutions AT zhanyicheng focalsurfaceholographiclighttransportusinglearnedspatiallyadaptiveconvolutions AT shiliang focalsurfaceholographiclighttransportusinglearnedspatiallyadaptiveconvolutions AT cakmakciozan focalsurfaceholographiclighttransportusinglearnedspatiallyadaptiveconvolutions AT akitkaan focalsurfaceholographiclighttransportusinglearnedspatiallyadaptiveconvolutions |