Related papers: Efficient Selection of Disambiguating Actions for …

Semantic segmentation and 3D reconstruction are two fundamental tasks in remote sensing, typically treated as separate or loosely coupled tasks. Despite attempts to integrate them into a unified network, the constraints between the two…

Accurate 6-DoF object pose estimation and tracking are critical for reliable robotic manipulation. However, zero-shot methods often fail under viewpoint-induced ambiguities and fixed-camera setups struggle when objects move or become…

A smart navigation system (an Electronic Travel Aid) based on an object detection mechanism has been designed to detect the presence of obstacles that immediately impede the path, by means of real time video processing. The algorithm can be…

Dense stereo matching with deep neural networks is of great interest to the research community. Existing stereo matching networks typically use slow and computationally expensive 3D convolutions to improve the performance, which is not…

Traditional stereo algorithms have focused their efforts on reconstruction quality and have largely avoided prioritizing for run time performance. Robots, on the other hand, require quick maneuverability and effective computation to observe…

Robust feature matching forms the backbone for most Visual Simultaneous Localization and Mapping (vSLAM), visual odometry, 3D reconstruction, and Structure from Motion (SfM) algorithms. However, recovering feature matches from texture-poor…

Videos acquired in low-light conditions often exhibit motion blur, which depends on the motion of the objects relative to the camera. This is not only visually unpleasing, but can hamper further processing. With this paper we are the first…

Active localization is the problem of generating robot actions that allow it to maximally disambiguate its pose within a reference map. Traditional approaches to this use an information-theoretic criterion for action selection and…

Learning-based approaches for semantic segmentation have two inherent challenges. First, acquiring pixel-wise labels is expensive and time-consuming. Second, realistic segmentation datasets are highly unbalanced: some categories are much…

Recent advances in robot imitation learning have yielded powerful visuomotor policies capable of manipulating a wide variety of objects directly from monocular visual inputs. However, monocular observations inherently lack reliable depth…

Many autonomous robotic applications require object-level understanding when deployed. Actively reconstructing objects of interest, i.e. objects with specific semantic meanings, is therefore relevant for a robot to perform downstream tasks…

The stereo-matching problem, i.e., matching corresponding features in two different views to reconstruct depth, is efficiently solved in biology. Yet, it remains the computational bottleneck for classical machine vision approaches. By…

Active learning is a promising alternative to alleviate the issue of high annotation cost in the computer vision tasks by consciously selecting more informative samples to label. Active learning for object detection is more challenging and…

Active learning is a unique abstraction of machine learning techniques where the model/algorithm could guide users for annotation of a set of data points that would be beneficial to the model, unlike passive machine learning. The primary…

Event stereo matching is an emerging technique to estimate depth from neuromorphic cameras; however, events are unlikely to trigger in the absence of motion or the presence of large, untextured regions, making the correspondence problem…

Stereo superpixel segmentation aims at grouping the discretizing pixels into perceptual regions through left and right views more collaboratively and efficiently. Existing superpixel segmentation algorithms mostly utilize color and spatial…

Using deep learning, we now have the ability to create exceptionally good semantic segmentation systems; however, collecting the prerequisite pixel-wise annotations for training images remains expensive and time-consuming. Therefore, it…

Stereo rectification is the determination of two image transformations (or homographies) that map corresponding points on the two images, projections of the same point in the 3D space, onto the same horizontal line in the transformed…

Under noisy conditions, automatic speech recognition (ASR) can greatly benefit from the addition of visual signals coming from a video of the speaker's face. However, when multiple candidate speakers are visible this traditionally requires…

Efficient face detection is critical to provide natural human-robot interactions. However, computer vision tends to involve a large computational load due to the amount of data (i.e. pixels) that needs to be processed in a short amount of…