EGSA-PT: Edge-Guided Spatial Attention with Progressive Training for Monocular Depth Estimation and Segmentation of Transparent Objects

Gbenga Omotara, Ramy Farag, Seyed Mohamad Ali Tousi, Guilherme N. DeSouza

Abstract:

Transparent object perception remains a major challenge in computer vision research, as transparency
confounds both depth estimation and semantic segmentation. Recent work has explored multitask learning frameworks to improve robustness, yet negative cross-task interactions often hinder
performance. In this work, we introduce Edge-Guided Spatial Attention (EGSA), a fusion mechanism
designed to mitigate destructive interactions by incorporating boundary information into the fusion
between semantic and geometric features. On both Syn-TODD and ClearPose benchmarks, EGSA
consistently improved depth accuracy over the current state of the art method (MODEST), while
preserving competitive segmentation performance, with the largest improvements appearing in
transparent regions. Besides our fusion design, our second contribution is a multi-modal progressive
training strategy, where learning transitions from edges derived from RGB images to edges derived
from predicted depth images. This approach allows the system to bootstrap learning from the rich
textures contained in RGB images, and then switch to more relevant geometric content in depth maps,
while it eliminates the need for ground-truth depth at training time. Together, these contributions
highlight edge-guided fusion as a robust approach capable of improving transparent object perception.