Guidefill: GPU accelerated, artist guided geometric inpainting for 3D conversion of film
From MaRDI portal
Publication:4689656
Numerical computation using splines (65D07) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08) Computing methodologies for image processing (68U10) Parallel algorithms in computer science (68W10) Numerical algorithms for specific classes of architectures (65Y10)
Abstract: The conversion of traditional film into stereo 3D has become an important problem in the past decade. One of the main bottlenecks is a disocclusion step, which in commercial 3D conversion is usually done by teams of artists armed with a toolbox of inpainting algorithms. A current difficulty in this is that most available algorithms are either too slow for interactive use, or provide no intuitive means for users to tweak the output. In this paper we present a new fast inpainting algorithm based on transporting along automatically detected splines, which the user may edit. Our algorithm is implemented on the GPU and fills the inpainting domain in successive shells that adapt their shape on the fly. In order to allocate GPU resources as efficiently as possible, we propose a parallel algorithm to track the inpainting interface as it evolves, ensuring that no resources are wasted on pixels that are not currently being worked on. Theoretical analysis of the time and processor complexiy of our algorithm without and with tracking (as well as numerous numerical experiments) demonstrate the merits of the latter. Our transport mechanism is similar to the one used in coherence transport, but improves upon it by corrected a "kinking" phenomena whereby extrapolated isophotes may bend at the boundary of the inpainting domain. Theoretical results explaining this phenomena and its resolution are presented. Although our method ignores texture, in many cases this is not a problem due to the thin inpainting domains in 3D conversion. Experimental results show that our method can achieve a visual quality that is competitive with the state-of-the-art while maintaining interactive speeds and providing the user with an intuitive interface to tweak the results.
Recommendations
Cites work
- scientific article; zbMATH DE number 1111402 (Why is no real title available?)
- scientific article; zbMATH DE number 1374053 (Why is no real title available?)
- A variational framework for exemplar-based image inpainting
- A variational model for gradient-based video editing
- A well-posedness framework for inpainting based on coherence transport
- Cahn-Hilliard inpainting and a generalization for grayvalue images
- Depth-Guided Disocclusion Inpainting of Synthesized RGB-D Images
- Euler's Elastica and Curvature-Based Inpainting
- Exemplar-based Inpainting: Technical Review and new Heuristics for better Geometric Reconstructions
- Fast image inpainting based on coherence transport
- Filling-in by joint interpolation of vector fields and gray levels
- GMRES: A Generalized Minimal Residual Algorithm for Solving Nonsymmetric Linear Systems
- Geometrically guided exemplar-based inpainting
- Image inpainting based on coherence transport with adapted distance functions
- Partial differential equation methods for image inpainting
- Space-Time Hole Filling With Random Walks in View Extrapolation for 3D Video
- Variational image inpainting
- Video inpainting of complex scenes
Cited in
(1)
This page was built for publication: Guidefill: GPU accelerated, artist guided geometric inpainting for 3D conversion of film
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4689656)
