Learning-based view synthesis for light field cameras
@article{Kalantari2016LearningbasedVS, title={Learning-based view synthesis for light field cameras}, author={Nima Khademi Kalantari and T. Wang and R. Ramamoorthi}, journal={ACM Transactions on Graphics (TOG)}, year={2016}, volume={35}, pages={1 - 10} }
With the introduction of consumer light field cameras, light field imaging has recently become widespread. However, there is an inherent trade-off between the angular and spatial resolution, and thus, these cameras often sparsely sample in either spatial or angular domain. In this paper, we use machine learning to mitigate this trade-off. Specifically, we propose a novel learning-based approach to synthesize new views from a sparse set of input views. We build upon existing view synthesis… CONTINUE READING
Supplemental Presentations
Figures and Topics from this paper
303 Citations
Light-field view synthesis using convolutional block attention module
- Computer Science, Engineering
- 2020
- Highly Influenced
- PDF
Light Field View Synthesis via Aperture Flow and Propagation Confidence Map
- Computer Science
- ArXiv
- 2020
- Highly Influenced
- PDF
Learning Occlusion-Aware View Synthesis for Light Fields
- Computer Science
- ArXiv
- 2019
- 3
- Highly Influenced
- PDF
Depth-guided view synthesis for light field reconstruction from a single image
- Computer Science
- Image Vis. Comput.
- 2020
- 1
Light Field Super-resolution via Attention-Guided Fusion of Hybrid Lenses
- Computer Science, Engineering
- ACM Multimedia
- 2020
- 1
- PDF
Light Field Synthesis by Training Deep Network in the Refocused Image Domain
- Computer Science, Mathematics
- IEEE Transactions on Image Processing
- 2020
- PDF
High-Quality Virtual View Synthesis for Light Field Cameras Using Multi-Loss Convolutional Neural Networks
- Computer Science
- 2018 25th IEEE International Conference on Image Processing (ICIP)
- 2018
- 2
- Highly Influenced
Light Field Image Compression Based on Convolutional Neural Networks and Linear Approximation
- Computer Science
- 2018 25th IEEE International Conference on Image Processing (ICIP)
- 2018
- 16
- PDF