DeepAI AI Chat
Log In Sign Up

Domain Adaptation for Real-World Single View 3D Reconstruction

by   Brandon Leung, et al.
University of California, San Diego

Deep learning-based object reconstruction algorithms have shown remarkable improvements over classical methods. However, supervised learning based methods perform poorly when the training data and the test data have different distributions. Indeed, most current works perform satisfactorily on the synthetic ShapeNet dataset, but dramatically fail in when presented with real world images. To address this issue, unsupervised domain adaptation can be used transfer knowledge from the labeled synthetic source domain and learn a classifier for the unlabeled real target domain. To tackle this challenge of single view 3D reconstruction in the real domain, we experiment with a variety of domain adaptation techniques inspired by the maximum mean discrepancy (MMD) loss, Deep CORAL, and the domain adversarial neural network (DANN). From these findings, we additionally propose a novel architecture which takes advantage of the fact that in this setting, target domain data is unsupervised with regards to the 3D model but supervised for class labels. We base our framework off a recent network called pix2vox. Results are performed with ShapeNet as the source domain and domains within the Object Dataset Domain Suite (ODDS) dataset as the target, which is a real world multiview, multidomain image dataset. The domains in ODDS vary in difficulty, allowing us to assess notions of domain gap size. Our results are the first in the multiview reconstruction literature using this dataset.


page 2

page 4

page 6


A Brief Review of Domain Adaptation

Classical machine learning assumes that the training and test sets come ...

3D Reconstruction of Sculptures from Single Images via Unsupervised Domain Adaptation on Implicit Models

Acquiring the virtual equivalent of exhibits, such as sculptures, in vir...

Source-Free Domain Adaptation for Real-world Image Dehazing

Deep learning-based source dehazing methods trained on synthetic dataset...

Unsupervised Domain Adaptation with Temporal-Consistent Self-Training for 3D Hand-Object Joint Reconstruction

Deep learning-solutions for hand-object 3D pose and shape estimation are...

VoloGAN: Adversarial Domain Adaptation for Synthetic Depth Data

We present VoloGAN, an adversarial domain adaptation network that transl...

Multi-Scale Multi-Target Domain Adaptation for Angle Closure Classification

Deep learning (DL) has made significant progress in angle closure classi...