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.

通常期望计算机视觉任务在压缩图像上执行。JPEG 2000 等经典图像压缩标准被广泛使用。但是，它们没有考虑手头的特定最终任务。受基于循环神经网络 (RNN) 的图像压缩和三维 (3D) 重建工作的启发，我们提出了统一的网络架构来共同解决这两个任务。这些联合模型提供为 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，由我们提出的模型压缩的图像产生更优越的 3D 重建性能。我们的模型显着扩展了可以进行 3D 重建的压缩率范围。