Learning from THEODORE: A Synthetic Omnidirectional Top-View Indoor Dataset for Deep Transfer Learning
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Image GenerationObjectobject-detectionObject DetectionSemantic SegmentationTransfer LearningSimilar Papers 제목 키워드 기반
Human Pose Estimation in Monocular Omnidirectional Top-View Images
Human pose estimation (HPE) with convolutional neural networks (CNNs) for indoor monitoring is one of the major challenges in computer vision. In contrast to HPE in perspective views, an indoor monitoring system can cons…
2D Human Pose Estimation3D Human Pose EstimationKeypoint DetectionPose EstimationCasual Indoor HDR Radiance Capture from Omnidirectional Images
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 l…
NeRFMCPDepth: Omnidirectional Depth Estimation via Stereo Matching from Multi-Cylindrical Panoramas
We introduce Multi-Cylindrical Panoramic Depth Estimation (MCPDepth), a two-stage framework for omnidirectional depth estimation via stereo matching between multiple cylindrical panoramas. MCPDepth uses cylindrical panor…
Depth EstimationStereo MatchingOmniPD: One-Step Person Detection in Top-View Omnidirectional Indoor Scenes
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, miss…
Data AugmentationHuman DetectionTransfer LearningOmniMVS: End-to-End Learning for Omnidirectional Stereo Matching
In this paper, we propose a novel end-to-end deep neural network model for omnidirectional depth estimation from a wide-baseline multi-view stereo setup. The images captured with ultra wide field-of-view (FOV) cameras on…
DecoderDepth EstimationStereo MatchingStereo Matching Hand