透明物体の深度補完のためのRGB-D局所陰関数
RGB-D Local Implicit Function for Depth Completion of Transparent Objects
単一のRGB-D画像から透明物体の欠損深度を補完するため、レイ・ボクセル対に基づく局所陰関数表現と自己修正型の反復精緻化を組み合わせた手法を提案し、合成・実世界データで従来法を大きく上回る精度と約20倍の高速推論を実現した。
著者: Luyang Zhu, Arsalan Mousavian, Yu Xiang, Hammad Mazhar, Jozef van Eenbergen, Shoubhik Debnath, Dieter Fox
分類: cs.CV, cs.RO
原文アブストラクト
Majority of the perception methods in robotics require depth information provided by RGB-D cameras. However, standard 3D sensors fail to capture depth of transparent objects due to refraction and absorption of light. In this paper, we introduce a new approach for depth completion of transparent objects from a single RGB-D image. Key to our approach is a local implicit neural representation built on ray-voxel pairs that allows our method to generalize to unseen objects and achieve fast inference speed. Based on this representation, we present a novel framework that can complete missing depth given noisy RGB-D input. We further improve the depth estimation iteratively using a self-correcting refinement model. To train the whole pipeline, we build a large scale synthetic dataset with transparent objects. Experiments demonstrate that our method performs significantly better than the current state-of-the-art methods on both synthetic and real world data. In addition, our approach improves the inference speed by a factor of 20 compared to the previous best method, ClearGrasp. Code and dataset will be released at https://research.nvidia.com/publication/2021-03_RGB-D-Local-Implicit.
