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

Neural Radiance Fields (NeRFs) have shown remarkable novel view synthesiscapabilities even in large-scale, unbounded scenes, albeit requiring hundredsof views or introducing artifacts in sparser settings. Their optimizationsuffers from shape-radiance ambiguities wherever only a small visual overlap isavailable. This leads to erroneous scene geometry and artifacts. In this paper,we propose Re-Nerfing, a simple and general multi-stage approach that leveragesNeRF's own view synthesis to address these limitations. With Re-Nerfing, weincrease the scene's coverage and enhance the geometric consistency of novelviews as follows: First, we train a NeRF with the available views. Then, we usethe optimized NeRF to synthesize pseudo-views next to the original ones tosimulate a stereo or trifocal setup. Finally, we train a second NeRF with bothoriginal and pseudo views while enforcing structural, epipolar constraints viathe newly synthesized images. Extensive experiments on the mip-NeRF 360 datasetshow the effectiveness of Re-Nerfing across denser and sparser input scenarios,bringing improvements to the state-of-the-art Zip-NeRF, even when trained withall views.

Re-Nerfing: Enforcing Geometric Constraints on Neural Radiance Fields through Novel Views Synthesis