![]() Virtual Reality (VR) for Serious Games (SGs) is attracting increasing attention for training applications due to its potential to provide significantly enhanced learning to users. We also apply our network to the problem of converting monocular panoramas to stereo panoramas. We create two new datasets to evaluate our approach: a synthetic dataset created using the CARLA simulator, and Headcam, a novel dataset of panoramic video collected from a helmet-mounted camera while biking in an urban setting. 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. 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. Panoramic depth estimation is an important technology for applications such as virtual reality, 3D modeling, and autonomous robotic navigation. We introduce a convolutional neural network model for unsupervised learning of depth and ego-motion from cylindrical panoramic video. We also consider the resources used in training and other qualitative factors. We then modify monodepth2 to support cylindrical and cubemap panoramas, incorporating current best practices for depth detection on those panorama types, and evaluate its performance for each type of image using our dataset. First, we create a simulated depth detection dataset that lends itself to panoramic comparisons and contains pre-made cylindrical and spherical panoramas. Here, we build on previous neural network methods by applying a recent state of the art model to panoramic images in addition to pinhole ones and performing a comparative evaluation. ![]() Neural networks are a natural fit for this. A good example is covering one eye: you still have some idea how far away things are, but it's not exact. While this is possible, it is harder than LIDAR or stereo methods since depth can't be measured from monocular images, it has to be inferred. These costs have given rise to attempts to detect depth from a monocular camera (a single camera). Currently, the best methods for depth detection are either very expensive, like LIDAR, or require precise calibration, like stereo cameras. One of the poster child applications is self driving cars. It shows up primarily in robotics, automation, or 3D visualization domains, as it is essential for converting images to point clouds. In contrast to state-of-the-art methods, the proposed method significantly reduces the complexity of camera rig and data amount, preserving a competitive stereo quality without visible distortions.ĭepth detection is a very common computer vision problem. Experiments show that the proposed method is effective and cost-efficient. To display the ODSV, this paper presents a real-time tracking-based rendering algorithm for head mounted display (HMD). Moreover, a single panoramic camera strategy can be adopted to capture the omnidirectional stereo images in real environment and a normal binocular camera can be used to capture the stereo pair of videos. Using this representation, ODSV can be presented by omnidirectional stereo images and normal stereo pair of videos respectively. This hybrid representation is piecewise linear about the horizontal viewing direction whose domain of definition is 0∘ to 360∘ with an assumption that the background is static, consisting of both static and moving regions. The proposed solution is directly from capturing to displaying, which removes the processing step, thus reducing the total time consumption and visible stitching distortions. This paper presents a practical end-to-end solution based on a novel hybrid representation to solve these problems simultaneously. Even though many attempts have been made to address these challenges, they leave one or more of the following problems: complicated camera rig, high latency and visible distortions. Compared with the traditional video, omnidirectional stereo video (ODSV) provides a larger field of view (FOV) with depth perception but makes the capturing, processing and displaying more complicated.
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |