Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟰𝟬𝟭 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 NeuralFusion: Online Depth Fusion in Latent Space by Microsoft Mixed Reality and AI Zurich Lab Follow me for a similar post: Ashish Patel  ------------------------------------------------------------------- 𝗜𝗻𝘁𝗲𝗿𝗲𝘀𝘁𝗶𝗻𝗴 𝗙𝗮𝗰𝘁𝘀 : 🔸 Paper: NeuralFusion: Online Depth Fusion in Latent Space 🔸 This paper is published arxiv2022. 🔸 Presented a novel approach to online depth map fusion with real-time capability. The key idea is to perform the fusion operation in a learned latent space that allows to encode additional information about undesired outliers and super-resolution complex shape information. ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 We present a novel online depth map fusion approach that learns depth map aggregation in a latent feature space. 🔸While previous fusion methods use an explicit scene representation like signed distance functions (SDFs), we propose a learned feature representation for the fusion. 🔸The key idea is a separation between the scene representation used for the fusion and the output scene representation, via an additional translator network. 🔸Our neural network architecture consists of two main parts: a depth and feature fusion sub-network, which is followed by a translator sub-network to produce the final surface representation (e.g. TSDF) for visualization or other tasks. 🔸Our approach is an online process, handles high noise levels, and is particularly able to deal with gross outliers common for photometric stereo-based depth maps. Experiments on real and synthetic data demonstrate improved results compared to the state of the art, especially in challenging scenarios with large amounts of noise and outliers. #computervision #artificialintelligence #technology