We propose a method to train an autonomous agent to learn to accumulate a 3D scene graph representation of its […]
Supun Samarasekera
SRI Author
SASRA: Semantically-aware Spatio-temporal Reasoning Agent for Vision-and-Language Navigation in Continuous Environments
This paper presents a novel approach for the Vision-and-Language Navigation (VLN) task in continuous 3D environments.
Head-Worn Markerless Augmented Reality Inside a Moving Vehicle
This paper describes a system that provides general head-worn outdoor AR capability for the user inside a moving vehicle.
SIGNAV: Semantically-Informed GPS-Denied Navigation and Mapping in Visually-Degraded Environments
We present SIGNAV, a real-time semantic SLAM system to operate in perceptually-challenging situations.
Global Heading Estimation for Wide Area Augmented Reality Using Road Semantics for Geo-referencing
We present a method to estimate global camera head- ing by associating directional information from road segments in the camera view with annotated satellite imagery.
Long-Range Augmented Reality with Dynamic Occlusion Rendering
This paper addresses the problem of fast and accurate dynamic occlusion reasoning by real objects in the scene for large scale outdoor AR applications.
MaAST: Map Attention with Semantic Transformers for Efficient Visual Navigation
By using our novel attention schema and auxiliary rewards to better utilize scene semantics, we outperform multiple baselines trained with only raw inputs or implicit semantic information while operating with an 80% decrease in the agent’s experience.
RGB2LIDAR: Towards Solving Large-Scale Cross-Modal Visual Localization
We study an important, yet largely unexplored problem of large-scale cross-modal visual localization by matching ground RGB images to a geo-referenced aerial LIDAR 3D point cloud (rendered as depth images). Prior works were demonstrated on small datasets and did not lend themselves to scaling up for large-scale applications. To enable large-scale evaluation, we introduce a new dataset containing over 550K pairs (covering 143 km^2 area) of RGB and aerial LIDAR depth images. We propose a novel joint embedding based method that effectively combines the appearance and semantic cues from both modalities to handle drastic cross-modal variations. Experiments on the proposed dataset show that our model achieves a strong result of a median rank of 5 in matching across a large test set of 50K location pairs collected from a 14km^2 area. This represents a significant advancement over prior works in performance and scale. We conclude with qualitative results to highlight the challenging nature of this task and the benefits of the proposed model. Our work provides a foundation for further research in cross-modal visual localization.
Semantically-Aware Attentive Neural Embeddings for 2D Long-Term Visual Localization
We present an approach that combines appearance and semantic information for 2D image-based localization (2D-VL) across large perceptual changes and time lags. Compared to appearance features, the semantic layout of a scene is generally more invariant to appearance variations. We use this intuition and propose a novel end-to-end deep attention-based framework that utilizes multimodal cues to generate robust embeddings for 2D-VL. The proposed attention module predicts a shared channel attention and modality-specific spatial attentions to guide the embeddings to focus on more reliable image regions. We evaluate our model against state-of-the-art (SOTA) methods on three challenging localization datasets. We report an average (absolute) improvement of 19% over current SOTA for 2D-VL. Furthermore, we present an extensive study demonstrating the contribution of each component of our model, showing 8–15% and 4% improvement from adding semantic information and our proposed attention module. We finally show the predicted attention maps to offer useful insights into our model.
