Real-time incremental learning of scene light field with novel model and multiple agent with NSLF-OL
Real-time incremental learning of scene light field with novel model and multiple agent with NSLF-OL
NSLF-OL: Online Learning of Neural Surface Light Fields alongside Real-time Incremental 3D Reconstruction
arXiv paper abstract https://arxiv.org/abs/2305.00282
arXiv PDF paper https://arxiv.org/pdf/2305.00282.pdf
Project page https://jarrome.github.io/NSLF-OL
... novel view generation is ... important ... in ... graphics and ... human-robot interaction.
... This limits the usage ... in the robotics ... since robots (1) usually only capture a very small range of view directions to surfaces that cause arbitrary predictions on unseen, novel direction, (2) requires real-time algorithms, and (3) work with growing scenes, e.g., in robotic exploration.
... proposes a novel Neural Surface Light Fields model that copes with the small range of view directions while producing a good result in unseen directions ... training of ... model is highly efficient.
... design Multiple Asynchronous Neural Agents (MANA), a universal framework to learn each small region in parallel for large-scale growing scenes.
... model learns online the Neural Surface Light Fields (NSLF) aside from real-time 3D reconstruction with a sequential data stream as the shared input ... provides real-time rendering ... for visualization.
... showing the high flexibility to embed ... model into real-time 3D reconstruction and demonstrating high-fidelity view synthesis for these scenes ...
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Comments