Related papers: EAGLE: Episodic Appearance- and Geometry-aware Mem…
Monocular visual localization plays a pivotal role in advanced driver assistance systems and autonomous driving by estimating a vehicle's ego-motion from a single pinhole camera. Nevertheless, conventional monocular visual odometry…
Computed Tomography (CT) image reconstruction is crucial for accurate diagnosis and deep learning approaches have demonstrated significant potential in improving reconstruction quality. However, the choice of loss function profoundly…
Geospatial Location Embedding (GLE) helps a Large Language Model (LLM) assimilate and analyze spatial data. GLE emergence in Geospatial Artificial Intelligence (GeoAI) is precipitated by the need for deeper geospatial awareness in our…
Estimating 3D human motion from an egocentric video sequence plays a critical role in human behavior understanding and has various applications in VR/AR. However, naively learning a mapping between egocentric videos and human motions is…
3D object detection plays a pivotal role in autonomous driving and robotics, demanding precise interpretation of Bird's Eye View (BEV) images. The dynamic nature of real-world environments necessitates the use of dynamic query mechanisms in…
We propose a self-supervised algorithm to learn representations from egocentric video data. Recently, significant efforts have been made to capture humans interacting with their own environments as they go about their daily activities. In…
Cross-view geo-localization for Unmanned Aerial Vehicles (UAVs) operating in GNSS-denied environments remains challenging due to the severe geometric discrepancy between oblique UAV imagery and orthogonal satellite maps. Most existing…
A core task in embodied intelligence is ego-centric 3D visual grounding. Existing methods typically adopt two-stage, heterogeneous pipelines that pair a detector with a separate grounding model. Incompatible decoders and box heads hinder…
Monocular 3D object detection offers a cost-effective solution for autonomous driving but suffers from ill-posed depth and limited field of view. These constraints cause a lack of geometric cues and reduced accuracy in occluded or truncated…
Bird's-eye-view (BEV) is a powerful and widely adopted representation for road scenes that captures surrounding objects and their spatial locations, along with overall context in the scene. In this work, we focus on bird's eye semantic…
Egocentric 3D hand pose estimation and gesture recognition are essential for immersive augmented/virtual reality, human-computer interaction, and robotics. However, conventional frame-based cameras suffer from motion blur and limited…
Despite recent advances in facial recognition, there remains a fundamental issue concerning degradations in performance due to substantial perspective (pose) differences between enrollment and query (probe) imagery. Therefore, we propose a…
Predictive world models that simulate future observations under explicit camera control are fundamental to interactive AI. Despite rapid advances, current systems lack spatial persistence: they fail to maintain stable scene structures over…
Egocentric assistants often rely on first-person view data to capture user behavior and context for personalized services. Since different users exhibit distinct habits, preferences, and routines, such personalization is essential for truly…
Low-cost autonomous agents including autonomous driving vehicles chiefly adopt monocular 3D object detection to perceive surrounding environment. This paper studies 3D intermediate representation methods which generate intermediate 3D…
Recent Multimodal Large Language Models (MLLMs) have shown high potential for spatial reasoning within 3D scenes. However, they typically rely on computationally expensive 3D representations like point clouds or reconstructed Bird's-Eye…
Robust geo-localization in changing environmental conditions is critical for long-term aerial autonomy. While visual place recognition (VPR) models perform well when airborne views match the training domain, adapting them to shifting…
Three-dimensional geometric data offer an excellent domain for studying representation learning and generative modeling. In this paper, we look at geometric data represented as point clouds. We introduce a deep AutoEncoder (AE) network with…
We present ongoing work to harness biological approaches to achieving highly efficient egocentric perception by combining the space-variant imaging architecture of the mammalian retina with Deep Learning methods. By pre-processing images…
Understanding the world in first-person view is fundamental in Augmented Reality (AR). This immersive perspective brings dramatic visual changes and unique challenges compared to third-person views. Synthetic data has empowered…