2020/10/01 by Mojtaba Bemana, Bemana, Mojtaba, Karol Myszkowski +6 · 12 citations
Computer Science · Engineering · Mathematics · #Advanced Image Processing Techniques #Advanced Vision and Imaging #Artificial intelligence #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #FOS: Computer and information sciences #Graphics (cs.GR) #Image (mathematics) #Image Processing Techniques and Applications #Interpolation (computer graphics) #Mathematics #cs.CV #cs.GR
paper · pdf · doi:10.48550/arxiv.2010.00450
published in arXiv (Cornell University) (Cornell University) · 15 pages, 19 figures, accepted at SIGGRAPH Asia 2020, project webpage: https://xfields.mpi-inf.mpg.de/
arxiv created 2020/10/01 · openalex publication_date 2020/10/01 · arxiv updated 2020/10/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/04
We suggest to represent an X-Field -a set of 2D images taken across different view, time or illumination conditions, i.e., video, light field, reflectance fields or combinations thereof-by learning a neural network (NN) to map their view, time or light coordinates to 2D images. Executing this NN at new coordinates results in joint view, time or light interpolation. The key idea to make this workable is a NN that already knows the "basic tricks" of graphics (lighting, 3D projection, occlusion) in a hard-coded and differentiable form. The NN represents the input to that rendering as an implicit map, that for any view, time, or light coordinate and for any pixel can quantify how it will move if view, time or light coordinates change (Jacobian of pixel position with respect to view, time, illumination, etc.). Our X-Field representation is trained for one scene within minutes, leading to a compact set of trainable parameters and hence real-time navigation in view, time and illumination.