Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟮𝟵𝟭 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗔𝘁𝘁𝗲𝗻𝘁𝗶𝗼𝗻 𝗺𝗲𝗲𝘁𝘀 𝗚𝗲𝗼𝗺𝗲𝘁𝗿𝘆: Geometry Guided Spatial-Temporal Attention for Consistent Self-Supervised Monocular Depth Estimation by Technical University of Munich Follow me for a similar post: 🇮🇳 Ashish Patel Interesting Facts : 🔸 This paper is published arxiv2021. ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/e_R9XXBB ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸Inferring geometrically consistent dense 3D scenes across a tuple of temporally consecutive images remains challenging for self-supervised monocular depth prediction pipelines. This paper explores how the increasingly popular transformer architecture, together with novel regularized loss formulations, can improve depth consistency while preserving accuracy.  🔸We propose a spatial attention module that correlates coarse depth predictions to aggregate local geometric information. A novel temporal attention mechanism further processes the local geometric information in a global context across consecutive images. Additionally, we introduce geometric constraints between frames regularized by photometric cycle consistency.  🔸By combining our proposed regularization and the novel spatial-temporal-attention module we fully leverage both the geometric and appearance-based consistency across monocular frames. This yields geometrically meaningful attention and improves temporal depth stability and accuracy compared to previous methods. #computervision #artificialintelligence #innovation