Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟰𝟱𝟱 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers by Shanghai AI Laboratory Follow me for a similar post: Ashish Patel ------------------------------------------------------------------- 𝗜𝗻𝘁𝗲𝗿𝗲𝘀𝘁𝗶𝗻𝗴 𝗙𝗮𝗰𝘁𝘀 : 🔸 This paper is published cvpr2022. 🔸 Github: https://lnkd.in/gUE5YNBC ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 ➡️ 3D visual perception tasks, including 3D detection and map segmentation based on multi-camera images, are essential for autonomous driving systems. ➡️ In this work, we present a new framework termed BEVFormer, which learns unified BEV representations with spatiotemporal transformers to support multiple autonomous driving perception tasks. ➡️ In a nutshell, BEVFormer exploits both spatial and temporal information by interacting with spatial and temporal space through predefined grid-shaped BEV queries. ➡️ To aggregate spatial information, we design a spatial cross-attention that each BEV query extracts the spatial features from the regions of interest across camera views. ➡️ For temporal information, we propose a temporal self-attention to recurrently fuse the history BEV information. Our approach achieves the new state-of-the-art 56.9\% in terms of NDS metric on the nuScenes test set, which is 9.0 points higher than previous best arts and on par with the performance of LiDAR-based baselines. ➡️ We further show that BEVFormer remarkably improves the accuracy of velocity estimation and recall of objects under low visibility conditions. #computervision #artificialintelligence #deeplearning