Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟰𝟱𝟵 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 Pyramid Frequency Network with Spatial Attention Residual Refinement Module for Monocular Depth Estimation by Jiangnan University Follow me for a similar post: Ashish Patel ------------------------------------------------------------------- 𝗜𝗻𝘁𝗲𝗿𝗲𝘀𝘁𝗶𝗻𝗴 𝗙𝗮𝗰𝘁𝘀 : 🔸 This paper is published arxiv2022. 🔸 Github: https://lnkd.in/duC5ER7a ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 ➡️ Deep-learning-based approaches to depth estimation are rapidly advancing, offering superior performance over existing methods. ➡️ To estimate the depth in real-world scenarios, depth estimation models require the robustness of various noise environments. ➡️ In this work, a Pyramid Frequency Network(PFN) with Spatial Attention Residual Refinement Module(SARRM) is proposed to deal with the weak robustness of existing deep-learning methods. ➡️ To reconstruct depth maps with accurate details, the SARRM constructs a residual fusion method with an attention mechanism to refine the blur depth. ➡️ The frequency division strategy is designed, and the frequency pyramid network is developed to extract features from multiple frequency bands. ➡️ With the frequency strategy, PFN achieves better visual accuracy than state-of-the-art methods in both indoor and outdoor scenes on Make3D, KITTI depth, and NYUv2 datasets. ➡️ Additional experiments on the noisy NYUv2 dataset demonstrate that PFN is more reliable than existing deep-learning methods in high-noise scenes. #computervision #artificialintelligence #technology