The Fast Bilateral Solver

Code

• github.com/sampl-weizmann/deepcut
  pytorch★ 42
• github.com/kuan-wang/The_Bilateral_Solver
  none★ 0
• github.com/poolio/bilateral_solver
  none★ 0

Abstract

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 domain-specific optimization algorithms. Our 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 simple to integrate into deep learning pipelines.

Tasks

Reproductions