Log In Sign Up

Learning Deep Object Detectors from 3D Models

by   Xingchao Peng, et al.

Crowdsourced 3D CAD models are becoming easily accessible online, and can potentially generate an infinite number of training images for almost any object category.We show that augmenting the training data of contemporary Deep Convolutional Neural Net (DCNN) models with such synthetic data can be effective, especially when real training data is limited or not well matched to the target domain. Most freely available CAD models capture 3D shape but are often missing other low level cues, such as realistic object texture, pose, or background. In a detailed analysis, we use synthetic CAD-rendered images to probe the ability of DCNN to learn without these cues, with surprising findings. In particular, we show that when the DCNN is fine-tuned on the target detection task, it exhibits a large degree of invariance to missing low-level cues, but, when pretrained on generic ImageNet classification, it learns better when the low-level cues are simulated. We show that our synthetic DCNN training approach significantly outperforms previous methods on the PASCAL VOC2007 dataset when learning in the few-shot scenario and improves performance in a domain shift scenario on the Office benchmark.


page 1

page 2

page 6

page 7


Combining Texture and Shape Cues for Object Recognition With Minimal Supervision

We present a novel approach to object classification and detection which...

Synthetic to Real Adaptation with Generative Correlation Alignment Networks

Synthetic images rendered from 3D CAD models are useful for augmenting t...

Seeing Beyond Appearance - Mapping Real Images into Geometrical Domains for Unsupervised CAD-based Recognition

While convolutional neural networks are dominating the field of computer...

Anatomy of Domain Shift Impact on U-Net Layers in MRI Segmentation

Domain Adaptation (DA) methods are widely used in medical image segmenta...

Pose Estimation for Texture-less Shiny Objects in a Single RGB Image Using Synthetic Training Data

In the industrial domain, the pose estimation of multiple texture-less s...

Real-time texturing for 6D object instance detection from RGB Images

For objected detection, the availability of color cues strongly influenc...

Looking Beyond Appearances: Synthetic Training Data for Deep CNNs in Re-identification

Re-identification is generally carried out by encoding the appearance of...