Compact and adaptive multiplane images for view synthesis
Not on the map. Why?
Abstract (arXiv)
Recently, learning methods have been designed to create Multiplane Images (MPIs) for view synthesis. While MPIs are extremely powerful and facilitate high quality renderings, a great amount of memory is required, making them impractical for many applications. In this paper, we propose a learning method that optimizes the available memory to render compact and adaptive MPIs. Our MPIs avoid redundant information and take into account the scene geometry to determine the depth sampling.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 8 of its 17 references that are in the map. First posted on arXiv 19 Feb 2021.
Builds on
8 of 17 references.
References · 8
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
- 2016Layer Normalizationcited by 5,669
- 2019DeepView: View Synthesis with Learned Gradient Descentcited by 253
- 2018Stereo Magnification: Learning View Synthesis using Multiplane Imagescited by 211
- 2019Pushing the Boundaries of View Extrapolation with Multiplane Imagescited by 191
- 2020Learning light field synthesis with Multi-Plane Images: scene encoding as a recurrent segmentation taskcited by 1
Built on by
Citing papers per year: 2021: 1.
1 paper.
- 2021Spectral analysis of re-parameterized light fieldscited by 0
- 2021Spectral analysis of re-parameterized light fields12 Oct 2021