论文标题
通过使用深神经网络，针对3D重建优化的图像压缩
Image compression optimized for 3D reconstruction by utilizing deep neural networks
论文作者
论文摘要
通常期望在压缩图像上执行计算机视觉任务。像JPEG 2000这样的经典图像压缩标准被广泛使用。但是，它们没有说明手头的特定端任务。由基于复发性神经网络（RNN）基于复发性神经网络（RNN）的图像压缩和三维（3D）重建的动机，我们提出了统一的网络体系结构，以共同解决这两个任务。这些联合模型提供了针对3D重建的特定任务量身定制的图像压缩。与使用JPEG 2000压缩相比，通过我们提出的模型压缩的图像会产生3D重建性能。我们的模型显着扩展了3D重建的压缩率范围。我们还表明，可以在执行3D重建任务所需的计算之上，几乎没有额外的成本来高效地完成此操作。
Computer vision tasks are often expected to be executed on compressed images. Classical image compression standards like JPEG 2000 are widely used. However, they do not account for the specific end-task at hand. Motivated by works on recurrent neural network (RNN)-based image compression and three-dimensional (3D) reconstruction, we propose unified network architectures to solve both tasks jointly. These joint models provide image compression tailored for the specific task of 3D reconstruction. Images compressed by our proposed models, yield 3D reconstruction performance superior as compared to using JPEG 2000 compression. Our models significantly extend the range of compression rates for which 3D reconstruction is possible. We also show that this can be done highly efficiently at almost no additional cost to obtain compression on top of the computation already required for performing the 3D reconstruction task.
