ディストラクタ付き3D物体姿勢認識のための合成画像データセットSIDOD
SIDOD: A Synthetic Image Dataset for 3D Object Pose Recognition with Distractors
NVIDIAのデータ合成ツールで生成した、物体検出・姿勢推定・追跡向けの144k組のステレオ画像データセットを公開し、ドメインランダム化の手法を解説した論文。
著者: Mona Jalal, Josef Spjut, Ben Boudaoud, Margrit Betke
分類: cs.CV, cs.GR, cs.LG, cs.RO, eess.IV
原文アブストラクト
We present a new, publicly-available image dataset generated by the NVIDIA Deep Learning Data Synthesizer intended for use in object detection, pose estimation, and tracking applications. This dataset contains 144k stereo image pairs that synthetically combine 18 camera viewpoints of three photorealistic virtual environments with up to 10 objects (chosen randomly from the 21 object models of the YCB dataset [1]) and flying distractors. Object and camera pose, scene lighting, and quantity of objects and distractors were randomized. Each provided view includes RGB, depth, segmentation, and surface normal images, all pixel level. We describe our approach for domain randomization and provide insight into the decisions that produced the dataset.
