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

Training a Neural Radiance Field (NeRF) without pre-computed camera poses ischallenging. Recent advances in this direction demonstrate the possibility ofjointly optimising a NeRF and camera poses in forward-facing scenes. However,these methods still face difficulties during dramatic camera movement. Wetackle this challenging problem by incorporating undistorted monocular depthpriors. These priors are generated by correcting scale and shift parametersduring training, with which we are then able to constrain the relative posesbetween consecutive frames. This constraint is achieved using our proposednovel loss functions. Experiments on real-world indoor and outdoor scenes showthat our method can handle challenging camera trajectories and outperformsexisting methods in terms of novel view rendering quality and pose estimationaccuracy. Our project page is https://nope-nerf.active.vision.

NoPe-NeRF: Optimising Neural Radiance Field with No Pose Prior