Estimating Defocus Blur via Rank of Local Patches

ICCV 2017  ·  Guodong Xu, Yuhui Quan, Hui Ji ·

This paper addresses the problem of defocus map estimation from a single image. We present a fast yet effective approach to estimate the spatially varying amounts of defocus blur at edge locations, which is based on the maximum, ranks of the corresponding local patches with different orientations in gradient domain... Such an approach is motivated by the theoretical analysis which reveals the connection between the rank of a local patch blurred by a defocus blur kernel and the blur amount by the kernel. After the amounts of defocus blur at edge locations are obtained, a complete defocus map is generated by a standard propagation procedure. The proposed method is extensively evaluated on real image datasets, and the experimental results show its superior performance to existing approaches.proposed method is extensively evaluated on real data, and the experimental results show its superior performance to existing approaches. read more

PDF Abstract
No code implementations yet. Submit your code now

Tasks


Datasets


  Add Datasets introduced or used in this paper

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods


No methods listed for this paper. Add relevant methods here