489 citations · 624 across the 26 of their papers we have counts for
26 papers · 1 filter
Towards Grounded Visual Spatial Reasoning in Multi-Modal Vision Language Models
Navid Rajabi, Jana Kosecka
Large vision-and-language models (VLMs) trained to match images with text on large-scale datasets of image-text pairs have shown impressive generalization ability on several vision…
Graph-CoVis: GNN-based Multi-view Panorama Global Pose Estimation
Negar Nejatishahidin, Will Hutchcroft, Manjunath Narayana +5
In this paper, we address the problem of wide-baseline camera pose estimation from a group of 360 panoramas under upright-camera assumption. Recent work has demonstrated th…
U2RLE: Uncertainty-Guided 2-Stage Room Layout Estimation
Pooya Fayyazsanavi, Zhiqiang Wan, Will Hutchcroft +4
While the existing deep learning-based room layout estimation techniques demonstrate good overall accuracy, they are less effective for distant floor-wall boundary. To tackle this…
Self-supervised Pre-training for Semantic Segmentation in an Indoor Scene
Sulabh Shrestha, Yimeng Li, Jana Kosecka
The ability to endow maps of indoor scenes with semantic information is an integral part of robotic agents which perform different tasks such as target driven navigation, object se…
Object Pose Estimation using Mid-level Visual Representations
Negar Nejatishahidin, Pooya Fayyazsanavi, Jana Kosecka
This work proposes a novel pose estimation model for object categories that can be effectively transferred to previously unseen environments. The deep convolutional network models…
Uncertainty Aware Proposal Segmentation for Unknown Object Detection
Yimeng Li, Jana Kosecka
Recent efforts in deploying Deep Neural Networks for object detection in real world applications, such as autonomous driving, assume that all relevant object classes have been obse…
Generative Multi-Stream Architecture For American Sign Language Recognition
Dom Huh, Sai Gurrapu, Frederick Olson +3
With advancements in deep model architectures, tasks in computer vision can reach optimal convergence provided proper data preprocessing and model parameter initialization. However…
FineHand: Learning Hand Shapes for American Sign Language Recognition
Al Amin Hosain, Panneer Selvam Santhalingam, Parth Pathak +2
American Sign Language recognition is a difficult gesture recognition problem, characterized by fast, highly articulate gestures. These are comprised of arm movements with differen…
Learning View and Target Invariant Visual Servoing for Navigation
Yimeng Li, Jana Kosecka
The advances in deep reinforcement learning recently revived interest in data-driven learning based approaches to navigation. In this paper we propose to learn viewpoint invariant…
Hierarchical Kinematic Human Mesh Recovery
Georgios Georgakis, Ren Li, Srikrishna Karanam +3
We consider the problem of estimating a parametric model of 3D human mesh from a single image. While there has been substantial recent progress in this area with direct regression…
Simultaneous Mapping and Target Driven Navigation
Georgios Georgakis, Yimeng Li, Jana Kosecka
This work presents a modular architecture for simultaneous mapping and target driven navigation in indoors environments. The semantic and appearance stored in 2.5D map is distilled…
Learning Local RGB-to-CAD Correspondences for Object Pose Estimation
Georgios Georgakis, Srikrishna Karanam, Ziyan Wu +1
We consider the problem of 3D object pose estimation. While much recent work has focused on the RGB domain, the reliance on accurately annotated images limits their generalizabilit…
Self-supervisory Signals for Object Discovery and Detection
Etienne Pot, Alexander Toshev, Jana Kosecka
In robotic applications, we often face the challenge of discovering new objects while having very little or no labelled training data. In this paper we explore the use of self-supe…
Visual Representations for Semantic Target Driven Navigation
Arsalan Mousavian, Alexander Toshev, Marek Fiser +3
What is a good visual representation for autonomous agents? We address this question in the context of semantic visual navigation, which is the problem of a robot finding its way t…
Target Driven Instance Detection
Phil Ammirato, Cheng-Yang Fu, Mykhailo Shvets +2
While state-of-the-art general object detectors are getting better and better, there are not many systems specifically designed to take advantage of the instance detection problem.…
End-to-end learning of keypoint detector and descriptor for pose invariant 3D matching
Georgios Georgakis, Srikrishna Karanam, Ziyan Wu +2
Finding correspondences between images or 3D scans is at the heart of many computer vision and image retrieval applications and is often enabled by matching local keypoint descript…
Dense Piecewise Planar RGB-D SLAM for Indoor Environments
Phi-Hung Le, Jana Kosecka
The paper exploits weak Manhattan constraints to parse the structure of indoor environments from RGB-D video sequences in an online setting. We extend the previous approach for sin…
A Dataset for Developing and Benchmarking Active Vision
Phil Ammirato, Patrick Poirson, Eunbyung Park +2
We present a new public dataset with a focus on simulating robotic vision tasks in everyday indoor environments using real imagery. The dataset includes 20,000+ RGB-D images and 50…
Synthesizing Training Data for Object Detection in Indoor Scenes
Georgios Georgakis, Arsalan Mousavian, Alexander C. Berg +1
Detection of objects in cluttered indoor environments is one of the key enabling functionalities for service robots. The best performing object detection approaches in computer vis…
3D Bounding Box Estimation Using Deep Learning and Geometry
Arsalan Mousavian, Dragomir Anguelov, John Flynn +1
We present a method for 3D object detection and pose estimation from a single image. In contrast to current techniques that only regress the 3D orientation of an object, our method…
Multiview RGB-D Dataset for Object Instance Detection
Georgios Georgakis, Md Alimoor Reza, Arsalan Mousavian +2
This paper presents a new multi-view RGB-D dataset of nine kitchen scenes, each containing several objects in realistic cluttered environments including a subset of objects from th…
Fast Single Shot Detection and Pose Estimation
Patrick Poirson, Phil Ammirato, Cheng-Yang Fu +3
For applications in navigation and robotics, estimating the 3D pose of objects is as important as detection. Many approaches to pose estimation rely on detecting or tracking parts…
Semantic Image Based Geolocation Given a Map
Arsalan Mousavian, Jana Kosecka
The problem visual place recognition is commonly used strategy for localization. Most successful appearance based methods typically rely on a large database of views endowed with l…
Reinforcement Learning for Semantic Segmentation in Indoor Scenes
Md. Alimoor Reza, Jana Kosecka
Future advancements in robot autonomy and sophistication of robotics tasks rest on robust, efficient, and task-dependent semantic understanding of the environment. Semantic segment…