A-SHOJAEI/urban-occlusion-aware-depth-estimation
Multi-task learning system that jointly predicts monocular depth and occlusion boundaries in urban driving scenarios. Uses a novel edge-guided attention mechanism to handle challenging cases like transparent surfaces, reflections, and thin structures, addressing depth discontinuity prediction at object boundaries.
Stars
—
Forks
—
Language
Python
License
MIT
Category
Last pushed
Feb 21, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/A-SHOJAEI/urban-occlusion-aware-depth-estimation"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
cake-lab/HybridDepth
Official implementation for HybridDepth Model [WACV 2025, ISMAR 2024]
tinghuiz/SfMLearner
An unsupervised learning framework for depth and ego-motion estimation from monocular videos
ialhashim/DenseDepth
High Quality Monocular Depth Estimation via Transfer Learning
soubhiksanyal/RingNet
Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision
nianticlabs/monodepth2
[ICCV 2019] Monocular depth estimation from a single image