-
QuiltGAN: An Adversarially Trained, Procedural Algorithm for Texture Generation
-
How to Read Paintings: Semantic Art Understanding with Multi-Modal Retrieval
Automatic art analysis has been mostly focused on classifying artworks intondifferent artistic styles. However, understanding an artistic representationninvolves more complex processes, such as identifying the elements in the scenenor recognizing author influences. We present SemArt, a multi-modal dataset fornsemantic art…
-
Dyna-DM: Dynamic Object-aware Self-supervised Monocular Depth Maps
Self-supervised monocular depth estimation has been a subject of intense study in recent years, because of its applications in robotics and autonomous driving. Much of the recent work focuses on improving depth estimation by increasing architecture complexity. This paper shows…
-
Multi-model fitting based on minimum spanning tree
This paper presents a novel approach to the computation of primitive geometrical structures, where no prior knowledge about the visual scene is available and a high level of noise is expected. We based our work on the grouping principles of…
-
Lighting-Up Geometry: Accurate 3D Modelling of Museum Artifacts with a Torch and a Camera
This paper addresses the problem of obtaining complete, very detailed reconstructions of shiny objects such as glazed ceramics. We present an algorithm which uses silhouettes of the object, as well as images obtained under changing illumination conditions. In contrast with…
-
Optimization of Facade Segmentation Based on Layout Priors
-
Multi-camera Torso Pose Estimation using Graph Neural Networks
Estimating the location and orientation of humans is an essential skill for service and assistive robots. To achieve a reliable estimation in a wide area such as an apartment, multiple RGBD cameras are frequently used. Firstly, these setups are relatively…
-
Look and Listen: A Multi-modality Late Fusion Approach to Scene Classification for Autonomous Machines
The novelty of this study consists in a multi-modality approach to scenenclassification, where image and audio complement each other in a process ofndeep late fusion. The approach is demonstrated on a difficult classificationnproblem, consisting of two synchronised and balanced datasets…
