RGL-NET: A Recurrent Graph Learning framework for Progressive Part Assembly

• URL: http://arxiv.org/abs/2107.12859v1
• Date: Tue, 27 Jul 2021 14:47:43 GMT
• Title: RGL-NET: A Recurrent Graph Learning framework for Progressive Part Assembly
• Authors: Abhinav Narayan Harish, Rajendra Nagar and Shanmuganathan Raman
• Abstract summary: We tackle the problem of developing a generalized framework for assembly robust to structural variants. Our network can learn more plausible predictions of shape structure by accounting for priorly assembled parts. Our resulting latent space facilitates exciting applications such as shape recovery from the point-cloud components.
• Score: 30.143946636770025
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Autonomous assembly of objects is an essential task in robotics and 3D computer vision. It has been studied extensively in robotics as a problem of motion planning, actuator control and obstacle avoidance. However, the task of developing a generalized framework for assembly robust to structural variants remains relatively unexplored. In this work, we tackle this problem using a recurrent graph learning framework considering inter-part relations and the progressive update of the part pose. Our network can learn more plausible predictions of shape structure by accounting for priorly assembled parts. Compared to the current state-of-the-art, our network yields up to 10% improvement in part accuracy and up to 15% improvement in connectivity accuracy on the PartNet dataset. Moreover, our resulting latent space facilitates exciting applications such as shape recovery from the point-cloud components. We conduct extensive experiments to justify our design choices and demonstrate the effectiveness of the proposed framework.

Related papers

• Task-Oriented Real-time Visual Inference for IoVT Systems: A Co-design Framework of Neural Networks and Edge Deployment [61.20689382879937]
  Task-oriented edge computing addresses this by shifting data analysis to the edge. Existing methods struggle to balance high model performance with low resource consumption. We propose a novel co-design framework to optimize neural network architecture.
  arXiv  Detail & Related papers  (2024-10-29T19:02:54Z)
• Scalable Geometric Fracture Assembly via Co-creation Space among Assemblers [24.89380678499307]
  We develop a scalable framework for geometric fracture assembly without relying on semantic information. We introduce a novel loss function, i.e., the geometric-based collision loss, to address collision issues during the fracture assembly process. Our framework exhibits better performance on both PartNet and Breaking Bad datasets compared to existing state-of-the-art frameworks.
  arXiv  Detail & Related papers  (2023-12-19T17:13:51Z)
• Human as Points: Explicit Point-based 3D Human Reconstruction from Single-view RGB Images [78.56114271538061]
  We introduce an explicit point-based human reconstruction framework called HaP. Our approach is featured by fully-explicit point cloud estimation, manipulation, generation, and refinement in the 3D geometric space. Our results may indicate a paradigm rollback to the fully-explicit and geometry-centric algorithm design.
  arXiv  Detail & Related papers  (2023-11-06T05:52:29Z)
• RIFormer: Keep Your Vision Backbone Effective While Removing Token Mixer [95.71132572688143]
  This paper studies how to keep a vision backbone effective while removing token mixers in its basic building blocks. Token mixers, as self-attention for vision transformers (ViTs), are intended to perform information communication between different spatial tokens but suffer from considerable computational cost and latency.
  arXiv  Detail & Related papers  (2023-04-12T07:34:13Z)
• Graph-Transporter: A Graph-based Learning Method for Goal-Conditioned Deformable Object Rearranging Task [1.807492010338763]
  We present a novel framework, Graph-Transporter, for goal-conditioned deformable object rearranging tasks. Our framework adopts an architecture based on Fully Convolutional Network (FCN) to output pixel-wise pick-and-place actions from only visual input.
  arXiv  Detail & Related papers  (2023-02-21T05:21:04Z)
• 3D Part Assembly Generation with Instance Encoded Transformer [22.330218525999857]
  We propose a multi-layer transformer-based framework that involves geometric and relational reasoning between parts to update the part poses iteratively. We extend our framework to a new task called in-process part assembly. Our method achieves far more than 10% improvements over the current state-of-the-art in multiple metrics on the public PartNet dataset.
  arXiv  Detail & Related papers  (2022-07-05T02:40:57Z)
• Goal-driven Self-Attentive Recurrent Networks for Trajectory Prediction [31.02081143697431]
  Human trajectory forecasting is a key component of autonomous vehicles, social-aware robots and video-surveillance applications. We propose a lightweight attention-based recurrent backbone that acts solely on past observed positions. We employ a common goal module, based on a U-Net architecture, which additionally extracts semantic information to predict scene-compliant destinations.
  arXiv  Detail & Related papers  (2022-04-25T11:12:37Z)
• Where2Act: From Pixels to Actions for Articulated 3D Objects [54.19638599501286]
  We extract highly localized actionable information related to elementary actions such as pushing or pulling for articulated objects with movable parts. We propose a learning-from-interaction framework with an online data sampling strategy that allows us to train the network in simulation. Our learned models even transfer to real-world data.
  arXiv  Detail & Related papers  (2021-01-07T18:56:38Z)
• Progressive Self-Guided Loss for Salient Object Detection [102.35488902433896]
  We present a progressive self-guided loss function to facilitate deep learning-based salient object detection in images. Our framework takes advantage of adaptively aggregated multi-scale features to locate and detect salient objects effectively.
  arXiv  Detail & Related papers  (2021-01-07T07:33:38Z)
• Risk-Averse MPC via Visual-Inertial Input and Recurrent Networks for Online Collision Avoidance [95.86944752753564]
  We propose an online path planning architecture that extends the model predictive control (MPC) formulation to consider future location uncertainties. Our algorithm combines an object detection pipeline with a recurrent neural network (RNN) which infers the covariance of state estimates. The robustness of our methods is validated on complex quadruped robot dynamics and can be generally applied to most robotic platforms.
  arXiv  Detail & Related papers  (2020-07-28T07:34:30Z)

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.