ForkNet: Multi-Branch Volumetric Semantic Completion From a Single Depth Image

Autor: Federico Tombari, Yida Wang, David Joseph Tan, Nassir Navab
Rok vydání: 2019
Předmět:
Computational Geometry (cs.CG)
FOS: Computer and information sciences
Surface (mathematics)
Computer Science - Machine Learning
Computer Science - Artificial Intelligence
Computer science
Computer Vision and Pattern Recognition (cs.CV)
Computer Science - Computer Vision and Pattern Recognition
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
02 engineering and technology
010501 environmental sciences
Space (commercial competition)
01 natural sciences
Machine Learning (cs.LG)
Image (mathematics)
Transfer (computing)
FOS: Electrical engineering
electronic engineering
information engineering

0202 electrical engineering
electronic engineering
information engineering

ComputingMethodologies_COMPUTERGRAPHICS
0105 earth and related environmental sciences
business.industry
Image and Video Processing (eess.IV)
020207 software engineering
Pattern recognition
Electrical Engineering and Systems Science - Image and Video Processing
Object (computer science)
Artificial Intelligence (cs.AI)
Computer Science - Computational Geometry
Noise (video)
Artificial intelligence
business
Zdroj: ICCV
DOI: 10.1109/iccv.2019.00870
Popis: We propose a novel model for 3D semantic completion from a single depth image, based on a single encoder and three separate generators used to reconstruct different geometric and semantic representations of the original and completed scene, all sharing the same latent space. To transfer information between the geometric and semantic branches of the network, we introduce paths between them concatenating features at corresponding network layers. Motivated by the limited amount of training samples from real scenes, an interesting attribute of our architecture is the capacity to supplement the existing dataset by generating a new training dataset with high quality, realistic scenes that even includes occlusion and real noise. We build the new dataset by sampling the features directly from latent space which generates a pair of partial volumetric surface and completed volumetric semantic surface. Moreover, we utilize multiple discriminators to increase the accuracy and realism of the reconstructions. We demonstrate the benefits of our approach on standard benchmarks for the two most common completion tasks: semantic 3D scene completion and 3D object completion.
Comment: Accepted in International Conference on Computer Vision 2019
Databáze: OpenAIRE