@conference {4235, title = {Synthesizing 3D Shapes via Modeling Multi-view Depth Maps and Silhouettes with Deep Generative Networks}, booktitle = {2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2017}, month = {07/2017}, address = {Honolulu, HI}, abstract = {

We study the problem of learning generative models of 3D shapes. Voxels or 3D parts have been widely used as the underlying representations to build complex 3D shapes; however, voxel-based representations suffer from high memory requirements, and parts-based models require a large collection of cached or richly parametrized parts. We take an alternative approach: learning a generative model over multi-view depth maps or their corresponding silhouettes, and using a deterministic rendering function to produce 3D shapes from these images. A multi-view representation of shapes enables generation of 3D models with fine details, as 2D depth maps and silhouettes can be modeled at a much higher resolution than 3D voxels. Moreover, our approach naturally brings the ability to recover the underlying 3D representation from depth maps of one or a few viewpoints. Experiments show that our framework can generate 3D shapes with variations and details. We also demonstrate that our model has out-of-sample generalization power for real-world tasks with occluded objects.

}, keywords = {2d to 3d, 3D generation, 3D reconstruction, Core object system, depth map, generative, perception, silhouette}, doi = {10.1109/CVPR.2017.269}, url = {http://ieeexplore.ieee.org/document/8099752/http://xplorestaging.ieee.org/ielx7/8097368/8099483/08099752.pdf?arnumber=8099752}, author = {Amir Arsalan Soltani and Haibin Huang and Jiajun Wu and Tejas Kulkarni and Joshua B. Tenenbaum} }