Get 3D scene using neural radiance fields from sparse and noisy poses with SPARF
Get 3D scene using neural radiance fields from sparse and noisy poses with SPARF
SPARF: Neural Radiance Fields from Sparse and Noisy Poses
arXiv paper abstract https://arxiv.org/abs/2211.11738
arXiv PDF paper https://arxiv.org/pdf/2211.11738.pdf
GitHub https://github.com/google-research/sparf
Project page https://prunetruong.com/sparf.github.io
Neural Radiance Field (NeRF) has … emerged as a powerful representation to synthesize photorealistic novel views.
… it relies on the availability of dense input views with highly accurate camera poses, thus limiting its application in real-world scenarios.
… introduce Sparse Pose Adjusting Radiance Field (SPARF), to address the challenge of novel-view synthesis given only few wide-baseline input images (as low as 3) with noisy camera poses.
… approach exploits multi-view geometry constraints in order to jointly learn the NeRF and refine the camera poses.
By relying on pixel matches extracted between the input views … multi-view correspondence objective enforces the optimized scene and camera poses to converge to a global and geometrically accurate solution.
… approach sets a new state of the art in the sparse-view regime on multiple challenging datasets.
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
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
