Recent work about synthetic indoor datasets from perspective views has shown significant improvements of object detection results with Convolutional Neural Networks(CNNs). In this paper, we introduce THEODORE: a novel, large-scale indoor dataset containing 100,000 high-resolution diversified fisheye images with 14 classes. To this end, we create 3D virtual environments of living rooms, different human characters and interior textures. Beside capturing fisheye images from virtual environments we create annotations for semantic segmentation, instance masks and bounding boxes for object detection tasks. We compare our synthetic dataset to state of the art real-world datasets for omnidirectional images. Based on MS COCO weights, we show that our dataset is well suited for fine-tuning CNNs for object detection. Through a high generalization of our models by means of image synthesis and domain randomization, we reach an AP up to 0.84 for class person on High-Definition Analytics dataset.
We propose a one-step person detector for topview omnidirectional indoor scenes based on convolutional neural networks (CNNs). While state of the art person detectors reach competitive results on perspective images, missing CNN architectures as well as training data that follows the distortion of omnidirectional images makes current approaches not applicable to our data. The method predicts bounding boxes of multiple persons directly in omnidirectional images without perspective transformation, which reduces overhead of pre- and post-processing and enables real-time performance. The basic idea…
International Institute of Information Technology (IIIT)（国际信息技术研究所）；Université Laval（拉瓦尔大学）
We present PanoHDR-NeRF, a neural representation of the full HDR radiance field of an indoor scene, and a pipeline to capture it casually, without elaborate setups or complex capture protocols. First, a user captures a low dynamic range (LDR) omnidirectional video of the scene by freely waving an off-the-shelf camera around the scene. Then, an LDR2HDR network uplifts the captured LDR frames to HDR, which are used to train a tailored NeRF++ model. The resulting PanoHDR-NeRF can render full HDR images from any location of the scene. Through experiments on a novel test dataset of real scenes with…
Providing omnidirectional depth along with RGB information is important for numerous applications, eg, VR/AR. However, as omnidirectional RGB-D data is not always available, synthesizing RGB-D panorama data from limited information of a scene can be useful. Therefore, some prior works tried to synthesize RGB panorama images from perspective RGB images; however, they suffer from limited image quality and can not be directly extended for RGB-D panorama synthesis. In this paper, we study a new problem: RGB-D panorama synthesis under the arbitrary configurations of cameras and depth sensors. Accor…
University of Picardie Jules Verne（儒勒·凡尔纳皮卡第大学）；University of Limoges（利摩日大学）；CNRS（法国国家科学研究中心）；XLim Institute（XLim研究所）
In this paper we present a novel approach for representing and evolving deformable active contours. The method combines piecewise regular B{é}zier models and curve evolution defined by local Free Form Deformation. The contour deformation is locally constrained which allows contour convergence with almost linear complexity while adapting to various shape settings and handling topology changes of the active contour. We demonstrate the effectiveness of the new active contour scheme for visual free space perception and segmentation using omnidirectional images acquired by a robot exploring unknown…
An experimental evaluation of Siamese Neural Networks for robot localization using omnidirectional imaging in indoor environments
Institute for Engineering Research (I3E)（工程研究所（I3E））；Miguel Hernández University（米格尔·埃尔南德斯大学）；Valencian Graduate School and Research Network for Artificial Intelligence (valgrAI)（瓦伦西亚人工智能研究生院及研究网络（valgrAI））
Optical flow is the motion of a pixel between at least two consecutive video frames and can be estimated through an end-to-end trainable convolutional neural network. To this end, large training datasets are required to improve the accuracy of optical flow estimation. Our paper presents OmniFlow: a new synthetic omnidirectional human optical flow dataset. Based on a rendering engine we create a naturalistic 3D indoor environment with textured rooms, characters, actions, objects, illumination and motion blur where all components of the environment are shuffled during the data capturing process.…
Centre for Research and Technology Hellas (CERTH)（希腊研究与技术中心（CERTH））；Information Technologies Institute (ITI)（信息技术研究所（ITI））
Recent work on depth estimation up to now has only focused on projective images ignoring 360 content which is now increasingly and more easily produced. We show that monocular depth estimation models trained on traditional images produce sub-optimal results on omnidirectional images, showcasing the need for training directly on 360 datasets, which however, are hard to acquire. In this work, we circumvent the challenges associated with acquiring high quality 360 datasets with ground truth depth annotations, by re-using recently released large scale 3D datasets and re-purposing them to 360 via r…
School of Electronics and Communication Engineering, Sun Yat-sen University（中山大学电子与通信工程学院）；University of Western Australia（西澳大利亚大学）；Alibaba Group（阿里巴巴集团）
A main challenge for tasks on panorama lies in the distortion of objects among images. In this work, we propose a Distortion-Aware Monocular Omnidirectional (DAMO) dense depth estimation network to address this challenge on indoor panoramas with two steps. First, we introduce a distortion-aware module to extract calibrated semantic features from omnidirectional images. Specifically, we exploit deformable convolution to adjust its sampling grids to geometric variations of distorted objects on panoramas and then utilize a strip pooling module to sample against horizontal distortion introduced by…
Université de Bourgogne Franche-Comté（勃艮第-弗朗什-孔泰大学）；Universidad de Zaragoza（萨拉戈萨大学）
We propose a novel FCN able to work with omnidirectional images that outputs accurate probability maps representing the main structure of indoor scenes, which is able to generalize on different data. Our approach handles occlusions and recovers complex shaped rooms more faithful to the actual shape of the real scenes. We outperform the state of the art not only in accuracy of the 3D models but also in speed.
Real-time Multi-view Omnidirectional Depth Estimation for Real Scenarios based on Teacher-Student Learning with Unlabeled Data
School of Artificial Intelligence/School of Future Technology, Nanjing University of Information Science and Technology（人工智能学院/未来技术学院，信息科学与技术大学）；School of Electronic Science and Engineering, Nanjing University（电子科学与工程学院，南京大学）；School of Computer Engineering, Jinling Institute of Technology（计算机工程学院，金陵科技学院）；Suzhou High Technology Research Institute, Nanjing University（苏州高新技术研究院，南京大学）
Centre for Research and Technology Hellas (CERTH)（希腊研究与技术中心（CERTH））
Omnidirectional vision is becoming increasingly relevant as more efficient $360^o$ image acquisition is now possible. However, the lack of annotated $360^o$ datasets has hindered the application of deep learning techniques on spherical content. This is further exaggerated on tasks where ground truth acquisition is difficult, such as monocular surface estimation. While recent research approaches on the 2D domain overcome this challenge by relying on generating normals from depth cues using RGB-D sensors, this is very difficult to apply on the spherical domain. In this work, we address the unava…
Learning Geometric and Photometric Features from Panoramic LiDAR Scans for Outdoor Place Categorization
Graduate School of Information Science and Electrical Engineering, Kyushu University（九州大学信息科学与电子工程研究生院）；Jet Propulsion Laboratory, California Institute of Technology（加州理工学院喷气推进实验室）；Faculty of Information Science and Electrical Engineering, Kyushu University（九州大学信息科学与电子工程学部）；Technical University of Cartagena（卡塔赫纳技术大学）
The University of Tokyo（东京大学）；National Institute of Informatics（国立情报学研究所）
In recent years, the performance of novel view synthesis using perspective images has dramatically improved with the advent of neural radiance fields (NeRF). This study proposes two novel techniques that effectively build NeRF for 360{\textdegree} omnidirectional images. Due to the characteristics of a 360{\textdegree} image of ERP format that has spatial distortion in their high latitude regions and a 360{\textdegree} wide viewing angle, NeRF's general ray sampling strategy is ineffective. Hence, the view synthesis accuracy of NeRF is limited and learning is not efficient. We propose two non-…
