Freq-DP Net: A Dual-Branch Network for Fence Removal using Dual-Pixel and Fourier Priors
This addresses the challenge of fence removal in static scenes for computer vision applications, offering a novel approach but is incremental as it builds on prior work with dual-pixel sensors.
The paper tackled the problem of removing fence occlusions from single images, which degrades visual quality and limits computer vision applications, by introducing Freq-DP Net, a dual-branch network that fuses geometric and structural priors, achieving a new state-of-the-art for single-image, DP-based fence removal.
Removing fence occlusions from single images is a challenging task that degrades visual quality and limits downstream computer vision applications. Existing methods often fail on static scenes or require motion cues from multiple frames. To overcome these limitations, we introduce the first framework to leverage dual-pixel (DP) sensors for this problem. We propose Freq-DP Net, a novel dual-branch network that fuses two complementary priors: a geometric prior from defocus disparity, modeled using an explicit cost volume, and a structural prior of the fence's global pattern, learned via Fast Fourier Convolution (FFC). An attention mechanism intelligently merges these cues for highly accurate fence segmentation. To validate our approach, we build and release a diverse benchmark with different fence varieties. Experiments demonstrate that our method significantly outperforms strong general-purpose baselines, establishing a new state-of-the-art for single-image, DP-based fence removal.