Objective: To implement ‘the fast bilateral solver’ in OpenCV, which can be generally taken as an efficient bilateral filter.
To implement diverse tutorial examples with ‘the fast bilateral solver’, e.g. de-noising, colorization and stereo.

Introduction: The bilateral solver is 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. This algorithm was presented by Jonathan T. Barron and Ben Poole as an ECCV2016 oral and best paper nominee. Algorithm details and applications can be found in https://arxiv.org/pdf/1511.03296.pdf [1]

Significance: The naive bilateral filtering functions in OpenCV are generally computationally expensive and often insufficient for solving more challenging computer vision tasks. By contrast, the bilateral solver is 10-1000× faster than existing domain-specific approaches with comparable accuracy, and produces higher-quality output than lightweight filtering techniques with comparable runtimes.



Kuan Wang


  • Bo Li