NeuS introduces a bias-free volume rendering method for signed distance function representations to reconstruct accurate surfaces from 2D images.
Mescheder, Marc Pollefeys, and Andreas Geiger
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2representative citing papers
SubdivAR reformulates neural mesh subdivision as autoregressive next-scale vertex-offset prediction, reporting 18.8% lower Hausdorff and 14.2% lower Chamfer distance than NMR on closed meshes.
citing papers explorer
-
NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction
NeuS introduces a bias-free volume rendering method for signed distance function representations to reconstruct accurate surfaces from 2D images.
-
SubdivAR: Autoregressive Next-Scale Prediction for Neural Mesh Subdivision
SubdivAR reformulates neural mesh subdivision as autoregressive next-scale vertex-offset prediction, reporting 18.8% lower Hausdorff and 14.2% lower Chamfer distance than NMR on closed meshes.