Learning Descriptor Networks for 3D Shape Synthesis and Analysis
This addresses 3D shape synthesis and analysis for computer vision and graphics applications, but appears incremental as it adapts existing energy-based models to 3D data.
The paper tackles the problem of modeling volumetric shape patterns by proposing a 3D shape descriptor network based on a deep convolutional energy-based model, which can synthesize realistic 3D shapes and be used for tasks like 3D object recovery and super-resolution.
This paper proposes a 3D shape descriptor network, which is a deep convolutional energy-based model, for modeling volumetric shape patterns. The maximum likelihood training of the model follows an "analysis by synthesis" scheme and can be interpreted as a mode seeking and mode shifting process. The model can synthesize 3D shape patterns by sampling from the probability distribution via MCMC such as Langevin dynamics. The model can be used to train a 3D generator network via MCMC teaching. The conditional version of the 3D shape descriptor net can be used for 3D object recovery and 3D object super-resolution. Experiments demonstrate that the proposed model can generate realistic 3D shape patterns and can be useful for 3D shape analysis.