Piece-wise 3D planar reconstruction provides holistic scene understanding of man-made environments, especially for indoor scenarios. Most recent approaches focused on improving the segmentation and reconstruction results by introducing advanced network architectures but overlooked the dual characteristics of piece-wise planes as objects and geometric models. Different from other existing approaches, we start from enforcing cross-task consistency for our multi-task convolutional neural network, PlaneRecNet, which integrates a single-stage instance segmentation network for piece-wise planar segmentation and a depth decoder to reconstruct the scene from a single RGB image. To achieve this, we introduce several novel loss functions (geometric constraint) that jointly improve the accuracy of piece-wise planar segmentation and depth estimation. Meanwhile, a novel Plane Prior Attention module is used to guide depth estimation with the awareness of plane instances. Exhaustive experiments are conducted in this work to validate the effectiveness and efficiency of our method.
翻译:平面 3D 平面重建提供了人造环境的整体场景理解, 特别是室内情景。 大部分最近的方法都侧重于通过引入先进的网络结构来改善分割和重建结果,但忽略了作为物体和几何模型的片段平面的双重特性。 与其他现有方法不同, 我们从执行多任务进化神经网络的跨任务一致性开始, 即PlaneRecNet, 它将一个单阶段的碎片- 平面分割网络和深度解码器整合在一起, 以从一个 RGB 图像重建场景。 为了实现这一点, 我们引入了几个新的损失功能( 几何限制), 共同提高片段平面分割和深度估计的准确性。 与此同时, 一个新型的Plane Retat RecNet 模块用于指导深度估算, 并意识到平面实例。 在此工作中进行了Exhaustive 实验, 以验证我们的方法的有效性和效率 。