DIFFER: Moving Beyond 3D Reconstruction with Differentiable Feature Rendering

K L Navaneet, Priyanka Mandikal, Varun Jampani, Venkatesh Babu; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2019, pp. 18-24

Abstract


Perception of 3D object properties from 2D images form one of the core computer vision problems. In this work, we propose a deep learning system that can simultaneously reason about 3D shape as well as associated properties (such as color, semantic part segments) directly from a single 2D image. We devise a novel depth-aware differentiable feature rendering module (DIFFER) that is used to train our model by using only 2D supervision. Experiments on both synthetic ShapeNet dataset and the real-world Pix3D dataset demonstrate that our 2D supervised DIFFER model performs on par or sometimes even outperforms existing 3D supervised models.

Related Material


[pdf]
[bibtex]
@InProceedings{Navaneet_2019_CVPR_Workshops,
author = {L Navaneet, K and Mandikal, Priyanka and Jampani, Varun and Babu, Venkatesh},
title = {DIFFER: Moving Beyond 3D Reconstruction with Differentiable Feature Rendering},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2019}
}