Welcome to the Computer Vision Group at RWTH Aachen University!

The Computer Vision group has been established at RWTH Aachen University in context with the Cluster of Excellence "UMIC - Ultra High-Speed Mobile Information and Communication" and is associated with the Chair Computer Sciences 8 - Computer Graphics, Computer Vision, and Multimedia. The group focuses on computer vision applications for mobile devices and robotic or automotive platforms. Our main research areas are visual object recognition, tracking, self-localization, 3D reconstruction, and in particular combinations between those topics.

We offer lectures and seminars about computer vision and machine learning.

You can browse through all our publications and the projects we are working on.

We have one papers accepted at the IEEE International Conference on Computer Vision (ICCV) 2017, 3DRMS Workshop.

Sept. 18, 2017

We have two papers accepted at the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2017.

June 15, 2017

We have two papers accepted at the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017. One oral and one spotlight.

Feb. 28, 2017

We have two papers accepted at the IEEE Winter Conference on Applications of Computer Vision (WACV) 2017.

Jan. 4, 2017

We have a paper on Scene Flow Propagation for Semantic Mapping and Object Discovery in Dynamic Street Scenes at IROS 2016

Aug. 19, 2016

We have three papers accepted at the British Machine Vision Conference (BMVC) 2016.

Aug. 19, 2016

Recent Publications

Exploring Spatial Context for 3D Semantic Segmentation of Point Clouds

IEEE International Conference on Computer Vision (ICCV'17) 3DRMS Workshop

Deep learning approaches have made tremendous progress in the field of semantic segmentation over the past few years. However, most current approaches operate in the 2D image space. Direct semantic segmentation of unstructured 3D point clouds is still an open research problem. The recently proposed PointNet architecture presents an interesting step ahead in that it can operate on unstructured point clouds, achieving decent segmentation results. However, it subdivides the input points into a grid of blocks and processes each such block individually. In this paper, we investigate the question how such an architecture can be extended to incorporate larger-scale spatial context. We build upon PointNet and propose two extensions that enlarge the receptive field over the 3D scene. We evaluate the proposed strategies on challenging indoor and outdoor datasets and show improved results in both scenarios.


Online Adaptation of Convolutional Neural Networks for Video Object Segmentation

BMVC 2017 Oral

We tackle the task of semi-supervised video object segmentation, i.e. segmenting the pixels belonging to an object in the video using the ground truth pixel mask for the first frame. We build on the recently introduced one-shot video object segmentation (OSVOS) approach which uses a pretrained network and fine-tunes it on the first frame. While achieving impressive performance, at test time OSVOS uses the fine-tuned network in unchanged form and is not able to adapt to large changes in object appearance. To overcome this limitation, we propose Online Adaptive Video Object Segmentation (OnAVOS) which updates the network online using training examples selected based on the confidence of the network and the spatial configuration. Additionally, we add a pretraining step based on objectness, which is learned on PASCAL. Our experiments show that both extensions are highly effective and improve the state of the art on DAVIS to an intersection-over-union score of 85.7%.


Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes

Conference on Computer Vision and Pattern Recognition (CVPR'17) Oral

Semantic image segmentation is an essential component of modern autonomous driving systems, as an accurate understanding of the surrounding scene is crucial to navigation and action planning. Current state-of-the-art approaches in semantic image segmentation rely on pre-trained networks that were initially developed for classifying images as a whole. While these networks exhibit outstanding recognition performance (i.e., what is visible?), they lack localization accuracy (i.e., where precisely is something located?). Therefore, additional processing steps have to be performed in order to obtain pixel-accurate segmentation masks at the full image resolution. To alleviate this problem we propose a novel ResNet-like architecture that exhibits strong localization and recognition performance. We combine multi-scale context with pixel-level accuracy by using two processing streams within our network: One stream carries information at the full image resolution, enabling precise adherence to segment boundaries. The other stream undergoes a sequence of pooling operations to obtain robust features for recognition. The two streams are coupled at the full image resolution using residuals. Without additional processing steps and without pre-training, our approach achieves an intersection-over-union score of 71.8% on the Cityscapes dataset.

Disclaimer Home Visual Computing institute RWTH Aachen University