RGB-D Local Implicit Function for Depth Completion of Transparent Objects

• URL: http://arxiv.org/abs/2104.00622v1
• Date: Thu, 1 Apr 2021 17:00:04 GMT
• Title: RGB-D Local Implicit Function for Depth Completion of Transparent Objects
• Authors: Luyang Zhu, Arsalan Mousavian, Yu Xiang, Hammad Mazhar, Jozef van Eenbergen, Shoubhik Debnath, Dieter Fox
• Abstract summary: Majority of perception methods in robotics require depth information provided by RGB-D cameras. Standard 3D sensors fail to capture depth of transparent objects due to refraction and absorption of light. We present a novel framework that can complete missing depth given noisy RGB-D input.
• Score: 43.238923881620494
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• ASGrasp: Generalizable Transparent Object Reconstruction and Grasping from RGB-D Active Stereo Camera [9.212504138203222]
  We propose ASGrasp, a 6-DoF grasp detection network that uses an RGB-D active stereo camera. Our system distinguishes itself by its ability to directly utilize raw IR and RGB images for transparent object geometry reconstruction. Our experiments demonstrate that ASGrasp can achieve over 90% success rate for generalizable transparent object grasping.
  arXiv  Detail & Related papers  (2024-05-09T09:44:51Z)
• RGB-based Category-level Object Pose Estimation via Decoupled Metric Scale Recovery [72.13154206106259]
  We propose a novel pipeline that decouples the 6D pose and size estimation to mitigate the influence of imperfect scales on rigid transformations. Specifically, we leverage a pre-trained monocular estimator to extract local geometric information. A separate branch is designed to directly recover the metric scale of the object based on category-level statistics.
  arXiv  Detail & Related papers  (2023-09-19T02:20:26Z)
• MVTrans: Multi-View Perception of Transparent Objects [29.851395075937255]
  We forgo the unreliable depth map from RGB-D sensors and extend the stereo based method. Our proposed method, MVTrans, is an end-to-end multi-view architecture with multiple perception capabilities. We establish a novel procedural photo-realistic dataset generation pipeline and create a large-scale transparent object detection dataset.
  arXiv  Detail & Related papers  (2023-02-22T22:45:28Z)
• Grasping the Inconspicuous [15.274311118568715]
  We study deep learning 6D pose estimation from RGB images only for transparent object grasping. Experiments demonstrate the effectiveness of RGB image space for grasping transparent objects.
  arXiv  Detail & Related papers  (2022-11-15T14:45:50Z)
• Pyramidal Attention for Saliency Detection [30.554118525502115]
  This paper exploits only RGB images, estimates depth from RGB, and leverages the intermediate depth features. We employ a pyramidal attention structure to extract multi-level convolutional-transformer features to process initial stage representations. We report significantly improved performance against 21 and 40 state-of-the-art SOD methods on eight RGB and RGB-D datasets.
  arXiv  Detail & Related papers  (2022-04-14T06:57:46Z)
• TransCG: A Large-Scale Real-World Dataset for Transparent Object Depth Completion and Grasping [46.6058840385155]
  We contribute a large-scale real-world dataset for transparent object depth completion. Our dataset contains 57,715 RGB-D images from 130 different scenes. We propose an end-to-end depth completion network, which takes the RGB image and the inaccurate depth map as inputs and outputs a refined depth map.
  arXiv  Detail & Related papers  (2022-02-17T06:50:20Z)
• Accurate RGB-D Salient Object Detection via Collaborative Learning [101.82654054191443]
  RGB-D saliency detection shows impressive ability on some challenge scenarios. We propose a novel collaborative learning framework where edge, depth and saliency are leveraged in a more efficient way.
  arXiv  Detail & Related papers  (2020-07-23T04:33:36Z)
• A Single Stream Network for Robust and Real-time RGB-D Salient Object Detection [89.88222217065858]
  We design a single stream network to use the depth map to guide early fusion and middle fusion between RGB and depth. This model is 55.5% lighter than the current lightest model and runs at a real-time speed of 32 FPS when processing a $384 times 384$ image.
  arXiv  Detail & Related papers  (2020-07-14T04:40:14Z)
• Is Depth Really Necessary for Salient Object Detection? [50.10888549190576]
  We make the first attempt in realizing an unified depth-aware framework with only RGB information as input for inference. Not only surpasses the state-of-the-art performances on five public RGB SOD benchmarks, but also surpasses the RGBD-based methods on five benchmarks by a large margin.
  arXiv  Detail & Related papers  (2020-05-30T13:40:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.