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

arXiv: https://arxiv.org/abs/2511.14970 · HTML: https://mlsanity.com/paper/2511.14970/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 25 references that are in the map.
- First posted on arXiv 18 Nov 2025.

## Builds on (most cited first, 22 of 22)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks](https://mlsanity.com/paper/1711.02257/) (2017)
- [AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles](https://mlsanity.com/paper/1705.05065/) (2017)
- [Depth Pro: Sharp Monocular Metric Depth in Less Than a Second](https://mlsanity.com/paper/2410.02073/) (2024)
- [RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching](https://mlsanity.com/paper/2109.07547/) (2021)
- [ClearGrasp: 3D Shape Estimation of Transparent Objects for Manipulation](https://mlsanity.com/paper/1910.02550/) (2019)
- [Segmenting Transparent Objects in the Wild](https://mlsanity.com/paper/2003.13948/) (2020)
- [Robust Monocular Depth Estimation under Challenging Conditions](https://mlsanity.com/paper/2308.09711/) (2023)
- [Open Challenges in Deep Stereo: the Booster Dataset](https://mlsanity.com/paper/2206.04671/) (2022)
- [ClearPose: Large-scale Transparent Object Dataset and Benchmark](https://mlsanity.com/paper/2203.03890/) (2022)
- [Learning Depth Estimation for Transparent and Mirror Surfaces](https://mlsanity.com/paper/2307.15052/) (2023)
- [Booster: a Benchmark for Depth from Images of Specular and Transparent Surfaces](https://mlsanity.com/paper/2301.08245/) (2023)
- [Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditions](https://mlsanity.com/paper/2407.16698/) (2024)
- [Robotic Perception of Transparent Objects: A Review](https://mlsanity.com/paper/2304.00157/) (2023)
- [A4T: Hierarchical Affordance Detection for Transparent Objects Depth Reconstruction and Manipulation](https://mlsanity.com/paper/2207.04907/) (2022)
- [SimNet: Enabling Robust Unknown Object Manipulation from Pure Synthetic Data via Stereo](https://mlsanity.com/paper/2106.16118/) (2021)
- [MVTrans: Multi-View Perception of Transparent Objects](https://mlsanity.com/paper/2302.11683/) (2023)

## Built on by (most cited first, 1 of 1)

- [GHOST: Geometry-Guided Hallucination of Opaque Surface Textures](https://mlsanity.com/paper/2607.11118/) (2026)

## Abstract (arXiv)

Transparent object perception remains a major challenge in computer vision research, as transparency confounds both depth estimation and semantic segmentation. Recent work has explored multi-task 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.