Despite receiving significant attention from the research community, the task of segmenting and tracking objects in monocular videos still has much room for improvement. Existing works have simultaneously justified the efficacy of dilated and deformable convolutions for various image-level segmentation tasks. This gives reason to believe that 3D extensions of such convolutions should also yield performance improvements for video-level segmentation tasks. However, this aspect has not yet been explored thoroughly in existing literature. In this paper, we propose Dynamic Dilated Convolutions (D^2Conv3D): a novel type of convolution which draws inspiration from dilated and deformable convolutions and extends them to the 3D (spatio-temporal) domain. We experimentally show that D^2Conv3D can be used to improve the performance of multiple 3D CNN architectures across multiple video segmentation related benchmarks by simply employing D^2Conv3D as a drop-in replacement for standard convolutions. We further show that D^2Conv3D out-performs trivial extensions of existing dilated and deformable convolutions to 3D. Lastly, we set a new state-of-the-art on the DAVIS 2016 Unsupervised Video Object Segmentation benchmark. Code is made publicly available at https://github.com/Schmiddo/d2conv3d .

本文提出了一种新的卷积方法：Dynamic Dilated Convolutions (D^2Conv3D)，并经过实验证明它可以作为标准卷积的替代方法，用于提高 3D CNN 架构的性能，从而提高视频分割相关基准任务的表现，进一步表明该方法优于现有扩展的 3D 卷积方法，最终在 DAVIS 2016 无监督视频物体分割基准测试中实现了新的最佳成绩。

D^2Conv3D: 在视频中进行物体分割的动态空洞卷积