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

Recovery of an underlying scene geometry from multiview images stands as along-time challenge in computer vision research. The recent promise leveragesneural implicit surface learning and differentiable volume rendering, andachieves both the recovery of scene geometry and synthesis of novel views,where deep priors of neural models are used as an inductive smoothness bias.While promising for object-level surfaces, these methods suffer when copingwith complex scene surfaces. In the meanwhile, traditional multi-view stereocan recover the geometry of scenes with rich textures, by globally optimizingthe local, pixel-wise correspondences across multiple views. We are thusmotivated to make use of the complementary benefits from the two strategies,and propose a method termed Helix-shaped neural implicit Surface learning orHelixSurf; HelixSurf uses the intermediate prediction from one strategy as theguidance to regularize the learning of the other one, and conducts suchintertwined regularization iteratively during the learning process. We alsopropose an efficient scheme for differentiable volume rendering in HelixSurf.Experiments on surface reconstruction of indoor scenes show that our methodcompares favorably with existing methods and is orders of magnitude faster,even when some of existing methods are assisted with auxiliary training data.The source code is available at https://github.com/Gorilla-Lab-SCUT/HelixSurf.

HelixSurf: A Robust and Efficient Neural Implicit Surface Learning of Indoor Scenes with Iterative Intertwined Regularization