Artemis

Author:

Luo Haimin1,Xu Teng1,Jiang Yuheng1,Zhou Chenglin1,Qiu Qiwei2,Zhang Yingliang3,Yang Wei4,Xu Lan1,Yu Jingyi1

Affiliation:

1. ShanghaiTech University, China

2. ShanghaiTech University and Deemos Technology Co., Ltd., China

3. DGene Digital Technology Co., Ltd., China

4. Huazhong University of Science and Technology, China

Abstract

We, humans, are entering into a virtual era and indeed want to bring animals to the virtual world as well for companion. Yet, computer-generated (CGI) furry animals are limited by tedious off-line rendering, let alone interactive motion control. In this paper, we present ARTEMIS, a novel neural modeling and rendering pipeline for generating ARTiculated neural pets with appEarance and Motion synthesIS. Our ARTEMIS enables interactive motion control, real-time animation, and photo-realistic rendering of furry animals. The core of our ARTEMIS is a neural-generated (NGI) animal engine, which adopts an efficient octree-based representation for animal animation and fur rendering. The animation then becomes equivalent to voxel-level deformation based on explicit skeletal warping. We further use a fast octree indexing and efficient volumetric rendering scheme to generate appearance and density features maps. Finally, we propose a novel shading network to generate high-fidelity details of appearance and opacity under novel poses from appearance and density feature maps. For the motion control module in ARTEMIS, we combine state-of-the-art animal motion capture approach with recent neural character control scheme. We introduce an effective optimization scheme to reconstruct the skeletal motion of real animals captured by a multi-view RGB and Vicon camera array. We feed all the captured motion into a neural character control scheme to generate abstract control signals with motion styles. We further integrate ARTEMIS into existing engines that support VR headsets, providing an unprecedented immersive experience where a user can intimately interact with a variety of virtual animals with vivid movements and photo-realistic appearance. Extensive experiments and showcases demonstrate the effectiveness of our ARTEMIS system in achieving highly realistic rendering of NGI animals in real-time, providing daily immersive and interactive experiences with digital animals unseen before. We make available our ARTEMIS model and dynamic furry animal dataset at https://haiminluo.github.io/publication/artemis/.

Funder

SHMEC

NSFC

STCSM

National Key Research and Development Program

Publisher

Association for Computing Machinery (ACM)

Subject

Computer Graphics and Computer-Aided Design

Reference103 articles.

1. Neural Point-Based Graphics

2. Pang Anqi , Chen Xin , Luo Haimin , Wu Minye , Yu Jingyi , and Xu Lan . 2021 . Few-shot Neural Human Performance Rendering from Sparse RGBD Videos . In Proceedings of the 30th International Joint Conference on Artificial Intelligence, IJCAI-21 . Pang Anqi, Chen Xin, Luo Haimin, Wu Minye, Yu Jingyi, and Xu Lan. 2021. Few-shot Neural Human Performance Rendering from Sparse RGBD Videos. In Proceedings of the 30th International Joint Conference on Artificial Intelligence, IJCAI-21.

3. Realistic hair modeling from a hybrid orientation field

4. Sai Bi , Zexiang Xu , Pratul Srinivasan , Ben Mildenhall , Kalyan Sunkavalli , Miloš Hašan , Yannick Hold-Geoffroy , David Kriegman , and Ravi Ramamoorthi . 2020. Neural reflectance fields for appearance acquisition. arXiv preprint arXiv:2008.03824 ( 2020 ). Sai Bi, Zexiang Xu, Pratul Srinivasan, Ben Mildenhall, Kalyan Sunkavalli, Miloš Hašan, Yannick Hold-Geoffroy, David Kriegman, and Ravi Ramamoorthi. 2020. Neural reflectance fields for appearance acquisition. arXiv preprint arXiv:2008.03824 (2020).

5. Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loop

Cited by 14 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Multi-frame Bitrate Allocation of Dynamic 3D Gaussian Splatting Streaming Over Dynamic Networks;Proceedings of the SIGCOMM Workshop on Emerging Multimedia Systems;2024-08-04

2. The Poses for Equine Research Dataset (PFERD);Scientific Data;2024-05-15

3. NeVRF: Neural Video-Based Radiance Fields for Long-Duration Sequences;2024 International Conference on 3D Vision (3DV);2024-03-18

4. VMesh: Hybrid Volume-Mesh Representation for Efficient View Synthesis;SIGGRAPH Asia 2023 Conference Papers;2023-12-10

5. SLoMo: A General System for Legged Robot Motion Imitation From Casual Videos;IEEE Robotics and Automation Letters;2023-11

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3