[IROS 2026] SILICA: Repurposing Diffusion Priors for Joint Glass Segmentation and Depth Estimation
SILICA is a unified, single-step latent regression model that repurposes text-to-image diffusion priors for joint glass segmentation and glass-aware monocular depth estimation.
Using task-specific CLIP text prompts injected into cross-attention layers, SILICA establishes a spatial hierarchy that resolves foreground-background visual ambiguities inherent to transparent surfaces.
This work has been accepted for publication at IROS 2026.
Project Links
- Project Page: silica-mirage.github.io
- Code & Deployment: GitHub Repository (rtarun1/Silica)
- Dataset: Mirage18k Dataset
Usage & ROS2 Deployment
For setup instructions, Python standalone inference, environment setup via uv/pip, and ROS2 (Humble) integration, please refer directly to the Official GitHub Repository.
- Downloads last month
- 52
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for rtarun1/silica-v1-0
Base model
CompVis/stable-diffusion-v1-4Dataset used to train rtarun1/silica-v1-0
Evaluation results
- mIoU on Mirage 18ktest set self-reported81.210
- Delta 1 on Mirage 18ktest set self-reported95.340