arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2010.04030cs.CV
收藏

基于深度形状先验的多目标三维场景分解弱监督学习

Weakly Supervised Learning of Multi-Object 3D Scene Decompositions Using Deep Shape Priors

Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);Max Planck ETH Center for Learning Systems(马克斯·普朗克-ETH学习系统中心);ETH Zurich(苏黎世联邦理工学院);Microsoft(微软)

Cathrin Elich, Martin R. Oswald, Marc Pollefeys, Joerg Stueckler

摘要:

以对象的粒度表示场景是场景理解和决策的前提。我们提出了PriSMONet,一种新的方法,基于先验形状知识学习多对象3D场景分解和表示从单个图像。我们的方法学习将平面上具有多个对象的合成场景的图像分解为其组成场景对象,并从单个视图中推断其3D属性。递归编码器从输入RGB图像中回归每个对象的3D形状、姿态和纹理的潜在表示。通过微分绘制,我们训练我们的模型分解场景从RGB-D图像在一个自我监督的方式。3D形状在函数空间中连续表示为有符号距离函数,我们以监督的方式从示例形状中进行预训练。这些形状先验提供了弱监督信号,以更好地调节具有挑战性的整体学习任务。我们评估我们的模型在推断3D场景布局的准确性,展示其生成能力,评估其泛化到真实图像,并指出学习表示的好处。

英文摘要:

Representing scenes at the granularity of objects is a prerequisite for scene understanding and decision making. We propose PriSMONet, a novel approach based on Prior Shape knowledge for learning Multi-Object 3D scene decomposition and representations from single images. Our approach learns to decompose images of synthetic scenes with multiple objects on a planar surface into its constituent scene objects and to infer their 3D properties from a single view. A recurrent encoder regresses a latent representation of 3D shape, pose and texture of each object from an input RGB image. By differentiable rendering, we train our model to decompose scenes from RGB-D images in a self-supervised way. The 3D shapes are represented continuously in function-space as signed distance functions which we pre-train from example shapes in a supervised way. These shape priors provide weak supervision signals to better condition the challenging overall learning task. We evaluate the accuracy of our model in inferring 3D scene layout, demonstrate its generative capabilities, assess its generalization to real images, and point out benefits of the learned representation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑