Machine Perception

Most existing image retrieval systems use text queries as a way for the user to express what they are looking for. However, fine-grained image retrieval often requires the ability to also express the where in the image the content they are looking for is. The text modality can only cumbersomely express such localization preferences, whereas pointing is a more natural fit. In this paper, we...

This paper proposes Panoptic Narrative Grounding, a spatially fine and general formulation of the natural language visual grounding problem. We establish an experimental framework for the study of this new task, including new ground truth and metrics, and we propose a strong baseline method to serve as stepping stone for future work. We exploit the intrinsic semantic richness in an image by...

We introduce a novel method for reconstructing 3D geometry of botanical trees from a single photograph. Faithfully reconstructing a tree from single-view sensor data is a challenging and open problem because many possible 3D trees exist that fit the tree's shape observed from a single view. We address this challenge by defining a reconstruction pipeline based on three neural networks. The...

Due to the complex interplay of various meteorological phenomena, simulating weather is a challenging and open research problem. In this paper, we propose a novel physically-accurate model that enables simulating weather. By considering atmosphere and pedosphere we can define the hydrologic cycle – and consequently weather – in unprecedented detail. Specifically, we distinguish different warm...