Li, ZhongSong, LiangchenLiu, CelongYuan, JunsongXu, YiGhosh, AbhijeetWei, Li-Yi2022-07-012022-07-012022978-3-03868-187-81727-3463https://doi.org/10.2312/sr.20221156https://diglib.eg.org:443/handle/10.2312/sr20221156In this paper, we present an efficient and robust deep learning solution for novel view synthesis of complex scenes. In our approach, a 3D scene is represented as a light field, i.e., a set of rays, each of which has a corresponding color when reaching the image plane. For efficient novel view rendering, we adopt a two-plane parameterization of the light field, where each ray is characterized by a 4D parameter. We then formulate the light field as a function that indexes rays to corresponding color values. We train a deep fully connected network to optimize this implicit function and memorize the 3D scene. Then, the scene-specific model is used to synthesize novel views. Different from previous light field approaches which require dense view sampling to reliably render novel views, our method can render novel views by sampling rays and querying the color for each ray from the network directly, thus enabling high-quality light field rendering with a sparser set of training images. Per-ray depth can be optionally predicted by the network, thus enabling applications such as auto refocus. Our novel view synthesis results are comparable to the state-of-the-arts, and even superior in some challenging scenes with refraction and reflection. We achieve this while maintaining an interactive frame rate and a small memory footprint.Attribution 4.0 International LicenseCCS Concepts: Computing methodologies --> Rendering; Computer vision problems; Virtual realityComputing methodologiesRenderingComputer vision problemsVirtual reality10.2312/sr.2022115659-6911 pages