Coherent rendering is important for generating plausible Mixed Reality presentations of virtual objects within a user’s real-world environment. Besides photo-realistic rendering and correct lighting, visual coherence requires simulating the imaging system that is used to capture the real environment. While existing approaches either focus on a specific camera or a specific component of the imaging system, we introduce Neural Cameras, the first approach that jointly simulates all major components of an arbitrary modern camera using neural networks. Our system allows for adding new cameras to the framework by learning the visual properties from a database of images that has been captured using the physical camera. We present qualitative and quantitative results and discuss future direction for research that emerge from using Neural Cameras.
|Title of host publication
|2021 IEEE International Symposium on Mixed and Augmented Reality (ISMAR)
|Maud Marchal, Jonathan Ventura, Anne-Helene Olivier, Lili Wang, Rafael Radkowski
|Place of Publication
|New Jersey, U.S.A.
|Institute of Electrical and Electronics Engineers Inc.
|Number of pages
|Published - 2021
|20th IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2021 - Virtual, Online, Italy
Duration: 4 Oct 2021 → 8 Oct 2021
|International Symposium on Mixed and Augmented Reality (ISMAR). Proceedings
|I E E E Computer Society
|20th IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2021
|4/10/21 → 8/10/21
- Camera Characteristics
- virtual objects
- photo-realistic rendering
- Neural Cameras