Differentiable volume rendering using signed distance functions
This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | eng |
| Published: |
Massachusetts Institute of Technology
2020
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/1721.1/124253 |
| _version_ | 1826204835726229504 |
|---|---|
| author | Kaza, Srinivas,M. Eng.Massachusetts Institute of Technology. |
| author2 | Fredo Durand. |
| author_facet | Fredo Durand. Kaza, Srinivas,M. Eng.Massachusetts Institute of Technology. |
| author_sort | Kaza, Srinivas,M. Eng.Massachusetts Institute of Technology. |
| collection | MIT |
| description | This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections. |
| first_indexed | 2024-09-23T13:02:09Z |
| format | Thesis |
| id | mit-1721.1/124253 |
| institution | Massachusetts Institute of Technology |
| language | eng |
| last_indexed | 2024-09-23T13:02:09Z |
| publishDate | 2020 |
| publisher | Massachusetts Institute of Technology |
| record_format | dspace |
| spelling | mit-1721.1/1242532020-03-25T03:21:36Z Differentiable volume rendering using signed distance functions Kaza, Srinivas,M. Eng.Massachusetts Institute of Technology. Fredo Durand. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Electrical Engineering and Computer Science. This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections. Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019 Cataloged from student-submitted PDF version of thesis. Includes bibliographical references (pages 55-58). Gradient-based methods are often used in a computer graphics and computer vision context to solve inverse rendering problems. These methods can be used to infer camera parameters, material properties, and even object pose and geometry from 2D images. One of the challenges that faces differentiable rendering systems is handling visibility terms in the rendering equation, which are not continuous on object boundaries. We present a renderer that solves this problem by introducing a form of visibility that is not discontinuous, and thus can be differentiated. This "soft visibility" is inspired by volumetric rendering, and is facilitated by our decision to represent geometry within the scene as a signed distance function. We also present methods for performing gradient descent upon distance fields while preserving Lipschitz continuity. Unlike most differentiable mesh-based renderers, our renderer can optimize between geometry of different homeomorphism classes in a variety of image-based shape fitting tasks. by Srinivas Kaza. M. Eng. M.Eng. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science 2020-03-24T15:36:32Z 2020-03-24T15:36:32Z 2019 2019 Thesis https://hdl.handle.net/1721.1/124253 1145123039 eng MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission. http://dspace.mit.edu/handle/1721.1/7582 58 pages application/pdf Massachusetts Institute of Technology |
| spellingShingle | Electrical Engineering and Computer Science. Kaza, Srinivas,M. Eng.Massachusetts Institute of Technology. Differentiable volume rendering using signed distance functions |
| title | Differentiable volume rendering using signed distance functions |
| title_full | Differentiable volume rendering using signed distance functions |
| title_fullStr | Differentiable volume rendering using signed distance functions |
| title_full_unstemmed | Differentiable volume rendering using signed distance functions |
| title_short | Differentiable volume rendering using signed distance functions |
| title_sort | differentiable volume rendering using signed distance functions |
| topic | Electrical Engineering and Computer Science. |
| url | https://hdl.handle.net/1721.1/124253 |
| work_keys_str_mv | AT kazasrinivasmengmassachusettsinstituteoftechnology differentiablevolumerenderingusingsigneddistancefunctions |