SharedNeRF: Leveraging Photorealistic and View-dependent Rendering for Real-time and Remote Collaboration
Abstract (excerpt):
When collaborators are remote, coordinating the sharing of views of their physical environment becomes challenging.
Video-conferencing tools often do not provide the desired viewpoints for a remote viewer. While RGB-D cameras offer 3D views, they lack the necessary fidelity.
We introduce SharedNeRF, designed to enhance synchronous remote collaboration by leveraging the photorealistic and view-dependent nature of Neural Radiance Field (NeRF). The system complements the higher visual quality of the NeRF rendering with the instantaneity of a point cloud and combines them through carefully accommodating the dynamic elements within the shared space, such as hand gestures and moving objects.
The system employs a head-mounted camera for data collection, creating a volumetric task space on the fly and updating it as the task space changes.
I’m thrilled to announce that I successfully completed my PhD at Cornell University in August and am starting an exciting new chapter as an HCI researcher at Fujitsu Research of America (@fujitsulabs) today! 😊
We will present SharedNeRF, a system that leverages both NeRFs and point clouds for synchronous remote collaboration, during "Learning and Working" session on Thursday #chi2024
PDF: https://t.co/YBpTntnCox
Video: https://t.co/jN2fILqdKz
ACMDL: https://t.co/j3KciE966r
🎉Very happy that our #CHI2024 paper, SharedNeRF, received an honorable mention award! 🏆
Extremely grateful to my amazing collaborators/mentors @bala_tk@nicmarquardt@thundercarrot during my intern @MSFTResearch 😊
Stay tuned for more details on the paper!
🎉Very happy that our #CHI2024 paper, SharedNeRF, received an honorable mention award! 🏆
Extremely grateful to my amazing collaborators/mentors @bala_tk@nicmarquardt@thundercarrot during my intern @MSFTResearch 😊
Stay tuned for more details on the paper!