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

In this paper, we study the problem of 3D scene geometry decomposition andmanipulation from 2D views. By leveraging the recent implicit neuralrepresentation techniques, particularly the appealing neural radiance fields,we introduce an object field component to learn unique codes for all individualobjects in 3D space only from 2D supervision. The key to this component is aseries of carefully designed loss functions to enable every 3D point,especially in non-occupied space, to be effectively optimized even without 3Dlabels. In addition, we introduce an inverse query algorithm to freelymanipulate any specified 3D object shape in the learned scene representation.Notably, our manipulation algorithm can explicitly tackle key issues such asobject collisions and visual occlusions. Our method, called DM-NeRF, is amongthe first to simultaneously reconstruct, decompose, manipulate and rendercomplex 3D scenes in a single pipeline. Extensive experiments on three datasetsclearly show that our method can accurately decompose all 3D objects from 2Dviews, allowing any interested object to be freely manipulated in 3D space suchas translation, rotation, size adjustment, and deformation.

DM-NeRF: 3D Scene Geometry Decomposition and Manipulation from 2D Images