Related papers: Multi-Agent Pose Uncertainty: A Differentiable Ren…

A version of quantum Cram\'{e}r-Rao bound dictates that the covariance of any set of operators is bounded by a product of the derivatives of expectation values and the inverse of quantum metric. We elaborate that because quantum metric…

Six degree of freedom (6DoF) pose estimation for novel objects is a critical task in computer vision, yet it faces significant challenges in high-speed and low-light scenarios where standard RGB cameras suffer from motion blur. While event…

This work focuses on assessing the information-theoretic limits of scene parameter estimation in plenoptic imaging systems. A general framework to compute lower bounds on the parameter estimation error from noisy plenoptic observations is…

Deep Learning (DL) has become essential in various robotics applications due to excelling at processing raw sensory data to extract task specific information from semantic objects. For example, vision-based object-relative navigation relies…

Sensor selection is a useful method to help reduce data throughput, as well as computational, power, and hardware requirements, while still maintaining acceptable performance. Although minimizing the Cram\'er-Rao bound has been adopted…

Inverse problems, such as accelerated MRI reconstruction, are ill-posed and an infinite amount of possible and plausible solutions exist. This may not only lead to uncertainty in the reconstructed image but also in downstream tasks such as…

One core challenge in object pose estimation is to ensure accurate and robust performance for large numbers of diverse foreground objects amidst complex background clutter. In this work, we present a scalable framework for accurately…

Robotic applications require a comprehensive understanding of the scene. In recent years, neural fields-based approaches that parameterize the entire environment have become popular. These approaches are promising due to their continuous…

Multi-perspective cameras with potentially non-overlapping fields of view have become an important exteroceptive sensing modality in a number of applications such as intelligent vehicles, drones, and mixed reality headsets. In this work, we…

This work addresses visual cross-view metric localization for outdoor robotics. Given a ground-level color image and a satellite patch that contains the local surroundings, the task is to identify the location of the ground camera within…

Given sparse views of a 3D object, estimating their camera poses is a long-standing and intractable problem. Toward this goal, we consider harnessing the pre-trained diffusion model of novel views conditioned on viewpoints (Zero-1-to-3). We…

Multi-perspective cameras are quickly gaining importance in many applications such as smart vehicles and virtual or augmented reality. However, a large system size or absence of overlap in neighbouring fields-of-view often complicate their…

Neural Radiance Fields (NeRF) have recently gained a surge of interest within the computer vision community for its power to synthesize photorealistic novel views of real-world scenes. One limitation of NeRF, however, is its requirement of…

In this work, we present an effective multi-view approach to closed-loop end-to-end learning of precise manipulation tasks that are 3D in nature. Our method learns to accomplish these tasks using multiple statically placed but uncalibrated…

In this note an intrinsic version of the Cram\'er-Rao bound on estimation accuracy is established on the Special Orthogonal group $SO(3)$. It is intrinsic in the sense that it does not rely on a specific choice of coordinates on $SO(3)$:…

Uncertainty quantification in automated image analysis is highly desired in many applications. Typically, machine learning models in classification or segmentation are only developed to provide binary answers; however, quantifying the…

We propose embodied scene-aware human pose estimation where we estimate 3D poses based on a simulated agent's proprioception and scene awareness, along with external third-person observations. Unlike prior methods that often resort to…

The recovery of multi-person 3D poses from a single RGB image is a severely ill-conditioned problem due to the inherent 2D-3D depth ambiguity, inter-person occlusions, and body truncations. To tackle these issues, recent works have shown…

Face alignment aims to estimate the locations of a set of landmarks for a given image. This problem has received much attention as evidenced by the recent advancement in both the methodology and performance. However, most of the existing…

Recognizing objects in images is a fundamental problem in computer vision. Although detecting objects in 2D images is common, many applications require determining their pose in 3D space. Traditional category-level methods rely on RGB-D…