Related papers: Supercharging Floorplan Localization with Semantic…
Visual place recognition algorithms trade off three key characteristics: their storage footprint, their computational requirements, and their resultant performance, often expressed in terms of recall rate. Significant prior work has…
Compared with expensive pixel-wise annotations, image-level labels make it possible to learn semantic segmentation in a weakly-supervised manner. Within this pipeline, the class activation map (CAM) is obtained and further processed to…
We investigate the task of object goal navigation in unknown environments where the target is specified by a semantic label (e.g. find a couch). Such a navigation task is especially challenging as it requires understanding of semantic…
Visual localization for planar moving robot is important to various indoor service robotic applications. To handle the textureless areas and frequent human activities in indoor environments, a novel robust visual localization algorithm…
Loop detection plays a key role in visual Simultaneous Localization and Mapping (SLAM) by correcting the accumulated pose drift. In indoor scenarios, the richly distributed semantic landmarks are view-point invariant and hold strong…
In recent years, the demand for service robots capable of executing tasks beyond autonomous navigation has grown. In the future, service robots will be expected to perform complex tasks like 'Set table for dinner'. High-level tasks like…
We focus on the problem of semantic segmentation based on RGB-D data, with emphasis on analyzing cluttered indoor scenes containing many instances from many visual categories. Our approach is based on a parametric figure-ground intensity…
This paper proposes a semi-sequential probabilistic model (SSP) that applies an additional short term memory to enhance the performance of the probabilistic indoor localization. The conventional probabilistic methods normally treat the…
Semantic segmentation is a powerful method to facilitate visual scene understanding. Each pixel is assigned a label according to a pre-defined list of object classes and semantic entities. This becomes very useful as a means to summarize…
With the rapid development of Remote Sensing acquisition techniques, there is a need to scale and improve processing tools to cope with the observed increase of both data volume and richness. Among popular techniques in remote sensing, Deep…
Efficient object level representation for monocular semantic simultaneous localization and mapping (SLAM) still lacks a widely accepted solution. In this paper, we propose the use of an efficient representation, based on structural points,…
In recent years, floor plan segmentation has gained significant attention due to its wide range of applications in floor plan reconstruction and robotics. In this paper, we propose a novel 2D floor plan segmentation technique based on a…
In this paper, we introduce a novel geometry-aware self-training framework for room layout estimation models on unseen scenes with unlabeled data. Our approach utilizes a ray-casting formulation to aggregate multiple estimates from…
Vision and language tasks such as Visual Relation Detection and Visual Question Answering benefit from semantic features that afford proper grounding of language. The 3D depth of objects depicted in 2D images is one such feature. However it…
This paper contributes a novel strategy for semantics-aware autonomous exploration and inspection path planning. Attuned to the fact that environments that need to be explored often involve a sparse set of semantic entities of particular…
The challenge of labeling large example datasets for computer vision continues to limit the availability and scope of image repositories. This research provides a new method for automated data collection, curation, labeling, and iterative…
Robots in the construction industry can reduce costs through constant monitoring of the work progress, using high precision data capturing. Accurate data capturing requires precise localization of the mobile robot within the environment. In…
Semantic embeddings have advanced the state of the art for countless natural language processing tasks, and various extensions to multimodal domains, such as visual-semantic embeddings, have been proposed. While the power of visual-semantic…
Dimension reduction (DR) can transform high-dimensional text embeddings into a 2D visual projection facilitating the exploration of document similarities. However, the projection often lacks connection to the text semantics, due to the…
While depth sensors are becoming increasingly popular, their spatial resolution often remains limited. Depth super-resolution therefore emerged as a solution to this problem. Despite much progress, state-of-the-art techniques suffer from…