Differentiable surface splatting for point-based geometry processing
- Submitting institution
-
University of Cambridge
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1941
- Type
- D - Journal article
- DOI
-
10.1145/3355089.3356513
- Title of journal
- ACM Transactions on Graphics
- Article number
- -
- First page
- 1
- Volume
- 38
- Issue
- 6
- ISSN
- 0730-0301
- Open access status
- Deposit exception
- Month of publication
- November
- Year of publication
- 2019
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
4
- Research group(s)
-
-
- Citation count
- 1
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This is the first technique for high-quality differentiable rendering of point clouds, which is the essential step for running machine learning algorithms on images to capture point-sampled 3D geometry. It has thus attracted substantial attention from computer graphics, vision, and machine learning communities that try to solve the inverse-rendering problem, i.e. capturing 3D content from images and video. A patent is filed titled "Techniques for performing point-based inverse rendering". It has led to the ongoing collaboration with Prof. Olga Sorkine-Hornung from ETH Zurich.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -