We present the bilateral solver, a novel algorithm for edge-aware smoothing that
combines the flexibility and speed of simple filtering approaches with the accuracy
of specialized domain-specific optimization algorithms. Our single technique is
capable of matching or improving upon state-of-the-art results on several different
computer vision tasks (stereo, depth superresolution, colorization, and semantic
segmentation) while being 10-1000 times faster than competing approaches. The
bilateral solver is fast, robust, straightforward to generalize to new domains, and
capable of being easily integrated into deep learning pipelines.