𝗗𝗮𝘆-𝟰𝟱𝟬 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 AutoAvatar: Autoregressive Neural Fields for Dynamic Avatar Modeling by Reality Labs Research Follow me for a similar post: Ashish Patel  ------------------------------------------------------------------- 𝗜𝗻𝘁𝗲𝗿𝗲𝘀𝘁𝗶𝗻𝗴 𝗙𝗮𝗰𝘁𝘀 : 🔸 This paper is published arxiv2022. ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 ➡️ Neural fields such as implicit surfaces have recently enabled avatar modeling from raw scans without explicit temporal correspondences. ➡️ In this work, we exploit autoregressive modeling to further extend this notion to capture dynamic effects, such as soft-tissue deformations. ➡️ Although autoregressive models are naturally capable of handling dynamics, it is non-trivial to apply them to implicit representations, as explicit state decoding is infeasible due to prohibitive memory requirements. ➡️ In this work, for the first time, we enable autoregressive modeling of implicit avatars. ➡️ To reduce the memory bottleneck and efficiently model dynamic implicit surfaces, we introduce the notion of articulated observer points, which relate implicit states to the explicit surface of a parametric human body model. ➡️ We demonstrate that encoding implicit surfaces as a set of height fields defined on articulated observer points leads to significantly better generalization compared to a latent representation. ➡️ The experiments show that our approach outperforms the state of the art, achieving plausible dynamic deformations even for unseen motions. #computervision #artificialintelligence #technology