Gradient-domain path tracing
We introduce gradient-domain rendering for Monte Carlo image synthesis. While previous gradient-domain Metropolis Light Transport sought to distribute more samples in areas of high gradients, we show, in contrast, that estimating image gradients is also possible using standard (non-Metropolis) Monte...
| Հիմնական հեղինակներ: | , , , , , |
|---|---|
| Այլ հեղինակներ: | |
| Ձևաչափ: | Հոդված |
| Լեզու: | English |
| Հրապարակվել է: |
Association for Computing Machinery (ACM)
2021
|
| Առցանց հասանելիություն: | https://hdl.handle.net/1721.1/134651 |
| _version_ | 1826188867763437568 |
|---|---|
| author | Kettunen, Markus Manzi, Marco Aittala, Miika Lehtinen, Jaakko Durand, Frédo Zwicker, Matthias |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Kettunen, Markus Manzi, Marco Aittala, Miika Lehtinen, Jaakko Durand, Frédo Zwicker, Matthias |
| author_sort | Kettunen, Markus |
| collection | MIT |
| description | We introduce gradient-domain rendering for Monte Carlo image synthesis. While previous gradient-domain Metropolis Light Transport sought to distribute more samples in areas of high gradients, we show, in contrast, that estimating image gradients is also possible using standard (non-Metropolis) Monte Carlo algorithms, and furthermore, that even without changing the sample distribution, this often leads to significant error reduction. This broadens the applicability of gradient rendering considerably. To gain insight into the conditions under which gradient-domain sampling is beneficial, we present a frequency analysis that compares Monte Carlo sampling of gradients followed by Poisson reconstruction to traditional Monte Carlo sampling. Finally, we describe Gradient-Domain Path Tracing (G-PT), a relatively simple modification of the standard path tracing algorithm that can yield far superior results. Copyright is held by the owner/author(s). Publication rights licensed to ACM. |
| first_indexed | 2024-09-23T08:06:16Z |
| format | Article |
| id | mit-1721.1/134651 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T08:06:16Z |
| publishDate | 2021 |
| publisher | Association for Computing Machinery (ACM) |
| record_format | dspace |
| spelling | mit-1721.1/1346512023-09-27T20:15:59Z Gradient-domain path tracing Kettunen, Markus Manzi, Marco Aittala, Miika Lehtinen, Jaakko Durand, Frédo Zwicker, Matthias Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory We introduce gradient-domain rendering for Monte Carlo image synthesis. While previous gradient-domain Metropolis Light Transport sought to distribute more samples in areas of high gradients, we show, in contrast, that estimating image gradients is also possible using standard (non-Metropolis) Monte Carlo algorithms, and furthermore, that even without changing the sample distribution, this often leads to significant error reduction. This broadens the applicability of gradient rendering considerably. To gain insight into the conditions under which gradient-domain sampling is beneficial, we present a frequency analysis that compares Monte Carlo sampling of gradients followed by Poisson reconstruction to traditional Monte Carlo sampling. Finally, we describe Gradient-Domain Path Tracing (G-PT), a relatively simple modification of the standard path tracing algorithm that can yield far superior results. Copyright is held by the owner/author(s). Publication rights licensed to ACM. 2021-10-27T20:06:00Z 2021-10-27T20:06:00Z 2015 2019-05-29T12:17:32Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/134651 Kettunen, Markus, et al. "Gradient-Domain Path Tracing." Acm Transactions on Graphics 34 4 (2015). en 10.1145/2766997 ACM Transactions on Graphics Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Association for Computing Machinery (ACM) Other repository |
| spellingShingle | Kettunen, Markus Manzi, Marco Aittala, Miika Lehtinen, Jaakko Durand, Frédo Zwicker, Matthias Gradient-domain path tracing |
| title | Gradient-domain path tracing |
| title_full | Gradient-domain path tracing |
| title_fullStr | Gradient-domain path tracing |
| title_full_unstemmed | Gradient-domain path tracing |
| title_short | Gradient-domain path tracing |
| title_sort | gradient domain path tracing |
| url | https://hdl.handle.net/1721.1/134651 |
| work_keys_str_mv | AT kettunenmarkus gradientdomainpathtracing AT manzimarco gradientdomainpathtracing AT aittalamiika gradientdomainpathtracing AT lehtinenjaakko gradientdomainpathtracing AT durandfredo gradientdomainpathtracing AT zwickermatthias gradientdomainpathtracing |