English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

A critical obstacle preventing NeRF models from being deployed broadly in thewild is their reliance on accurate camera poses. Consequently, there is growinginterest in extending NeRF models to jointly optimize camera poses and scenerepresentation, which offers an alternative to off-the-shelf SfM pipelineswhich have well-understood failure modes. Existing approaches for unposed NeRFoperate under limited assumptions, such as a prior pose distribution or coarsepose initialization, making them less effective in a general setting. In thiswork, we propose a novel approach, LU-NeRF, that jointly estimates camera posesand neural radiance fields with relaxed assumptions on pose configuration. Ourapproach operates in a local-to-global manner, where we first optimize overlocal subsets of the data, dubbed mini-scenes. LU-NeRF estimates local pose andgeometry for this challenging few-shot task. The mini-scene poses are broughtinto a global reference frame through a robust pose synchronization step, wherea final global optimization of pose and scene can be performed. We show ourLU-NeRF pipeline outperforms prior attempts at unposed NeRF without makingrestrictive assumptions on the pose prior. This allows us to operate in thegeneral SE(3) pose setting, unlike the baselines. Our results also indicate ourmodel can be complementary to feature-based SfM pipelines as it comparesfavorably to COLMAP on low-texture and low-resolution images.

LU-NeRF: Scene and Pose Estimation by Synchronizing Local Unposed NeRFs