Search for: All records

Affine correspondences have traditionally been used to improve feature matching over wide baselines. While recent work has successfully used affine correspondences to solve various relative camera pose estimation problems, less attention has been given to their use in absolute pose estimation. We introduce the first general solution to the problem of estimating the pose of a calibrated camera given a single observation of an oriented point and an affine correspondence. The advantage of our approach (P1AC) is that it requires only a single correspondence, in comparison to the traditional point-based approach (P3P), significantly reducing the combinatorics in robust estimation. P1AC provides a general solution that removes restrictive assumptions made in prior work and is applicable to large-scale image-based localization. We propose a minimal solution to the P1AC problem and evaluate our novel solver on synthetic data, showing its numerical stability and performance under various types of noise. On standard image-based localization benchmarks we show that P1AC achieves more accurate results than the widely used P3P algorithm. Code for our method is available at https://github.com/jonathanventura/P1AC/ . 

In augmented reality applications it is essential to know the position and orientation of the user to correctly register virtual 3D content in the user’s field of view. For this purpose, visual tracking through simultaneous localization and mapping (SLAM) is often used. However, when applied to the commonly occurring situation where the users are mostly stationary, many methods presented in previous research have two key limitations. First, SLAM techniques alone do not address the problem of global localization with respect to prior models of the environment. Global localization is essential in many applications where multiple users are expected to track within a shared space, such as spectators at a sporting event. Secondly, these methods often assume significant translational movement to accurately reconstruct and track from a local model of the environment, causing challenges for many stationary applications. In this paper, we extend recent research on Spherical Localization and Tracking to support relocalization after tracking failure, as well as global localization in large shared environments, and optimize the method for operation on mobile hardware. We also evaluate various state-of-the-art localization approaches, the robustness of our visual tracking method, and demonstrate the effectiveness of our system in real-life scenarios. 

As one part of an NSF-sponsored Data Science Fellowship at Cal Poly, San Luis Obispo, a group of faculty offered a unique one-unit quarter-long seminar on the history of ideas behind the core principles of Data Science. We present an overview of this seminar, its learning objectives, and outcomes and lessons learned. 

Recent advances in Neural Radiance Field (NeRF)-based methods have enabled high-fidelity novel view synthesis for video with dynamic elements. However, these methods often require expensive hardware, take days to process a second-long video and do not scale well to longer videos. We create an end-to-end pipeline for creating dynamic 3D video from a monocular video that can be run on consumer hardware in minutes per second of footage, not days. Our pipeline handles the estimation of the camera parameters, depth maps, 3D reconstruction of dynamic foreground and static background elements, and the rendering of the 3D video on a computer or VR headset. We use a state-of-the-art visual transformer model to estimate depth maps which we use to scale COLMAP poses and enable RGB-D fusion with estimated depth data. In our preliminary experiments, we rendered the output in a VR headset and visually compared the method against ground-truth datasets and state-of-the-art NeRF-based methods. 

We investigate how real-time, 360 degree view synthesis can be achieved on current virtual reality hardware from a single panoramic image input. We introduce a light-weight method to automatically convert a single panoramic input into a multi-cylinder image representation that supports real-time, free-viewpoint view synthesis rendering for virtual reality. We apply an existing convolutional neural network trained on pinhole images to a cylindrical panorama with wrap padding to ensure agreement between the left and right edges. The network outputs a stack of semi-transparent panoramas at varying depths which can be easily rendered and composited with over blending. Quantitative experiments and a user study show that the method produces convincing parallax and fewer artifacts than a textured mesh representation. 

We introduce a convolutional neural network model for unsupervised learning of depth and ego-motion from cylindrical panoramic video. Panoramic depth estimation is an important technology for applications such as virtual reality, 3d modeling, and autonomous robotic navigation. In contrast to previous approaches for applying convolutional neural networks to panoramic imagery, we use the cylindrical panoramic projection which allows for the use of the traditional CNN layers such as convolutional filters and max pooling without modification. Our evaluation of synthetic and real data shows that unsupervised learning of depth and ego-motion on cylindrical panoramic images can produce high-quality depth maps and that an increased field-of-view improves ego-motion estimation accuracy. We also introduce Headcam, a novel dataset of panoramic video collected from a helmet-mounted camera while biking in an urban setting. 

We introduce a method to automatically convert a single panoramic input into a multi-cylinder image representation that supports real-time, free-viewpoint view synthesis for virtual reality. We apply an existing convolutional neural network trained on pinhole images to a cylindrical panorama with wrap padding to ensure agreement between the left and right edges. The network outputs a stack of semi-transparent panoramas at varying depths which can be easily rendered and composited with over blending. Initial experiments show that the method produces convincing parallax and cleaner object boundaries than a textured mesh representation. 

We propose the use of dilated filters to construct an aggregation module in a multicolumn convolutional neural network for perspective-free counting. Counting is a common problem in computer vision (e.g. traffic on the street or pedestrians in a crowd). Modern approaches to the counting problem involve the production of a density map via regression whose integral is equal to the number of objects in the image. However, objects in the image can occur at different scales (e.g. due to perspective effects) which can make it difficult for a learning agent to learn the proper density map. While the use of multiple columns to extract multiscale information from images has been shown before, our approach aggregates the multiscale information gathered by the multicolumn convolutional neural network to improve performance. Our experiments show that our proposed network outperforms the state-of-the-art on many benchmark datasets, and also that using our aggregation module in combination with a higher number of columns is beneficial for multiscale counting. 

Complex neural network architectures are being increasingly used to learn to compute the semantic resemblances among natural language texts. It is necessary to establish a lower bound of performance that must be met in or- der for new complex architectures to be not only novel, but also worthwhile in terms of implementation. This paper focuses on the specific task of determin- ing semantic textual similarity (STS). We construct a number of models from simple to complex within a framework and report our results. Our findings show that a small number of LSTM stacks with an LSTM stack comparator produces the best results. We use Se- mEval 2017 STS Competition Dataset for evaluation.