Robust Shape from Focus via Multiscale Directional Dilated Laplacian and Recurrent Network

TL;DR

This paper introduces a hybrid deep learning framework for shape-from-focus that combines handcrafted multiscale focus volumes with a recurrent network for efficient, high-resolution depth estimation, outperforming existing methods.

Contribution

It proposes a novel combination of handcrafted Directional Dilated Laplacian focus volumes with a lightweight recurrent network for improved depth accuracy and detail preservation.

Findings

Outperforms state-of-the-art methods on synthetic and real datasets.

Achieves higher accuracy and better generalization across diverse focal conditions.

Effectively preserves scene details and sharp boundaries in high-resolution depth maps.

Abstract

Shape-from-Focus (SFF) is a passive depth estimation technique that infers scene depth by analyzing focus variations in a focal stack. Most recent deep learning-based SFF methods typically operate in two stages: first, they extract focus volumes (a per pixel representation of focus likelihood across the focal stack) using heavy feature encoders; then, they estimate depth via a simple one-step aggregation technique that often introduces artifacts and amplifies noise in the depth map. To address these issues, we propose a hybrid framework. Our method computes multi-scale focus volumes traditionally using handcrafted Directional Dilated Laplacian (DDL) kernels, which capture long-range and directional focus variations to form robust focus volumes. These focus volumes are then fed into a lightweight, multi-scale GRU-based depth extraction module that iteratively refines an initial depth estimate at a lower resolution for computational efficiency. Finally, a learned convex upsampling module within our recurrent network reconstructs high-resolution depth maps while preserving fine scene details and sharp boundaries. Extensive experiments on both synthetic and real-world datasets demonstrate that our approach outperforms state-of-the-art deep learning and traditional methods, achieving superior accuracy and generalization across diverse focal conditions.