Shading-based refinement on volumetric signed distance functions

Michael Zollhöfer, Angela Dai, Matthias Innmann, Chenglei Wu, Marc Stamminger, Christian Theobalt, Matthias Nießner

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

109 Zitate (Scopus)


We present a novel method to obtain fine-scale detail in 3D reconstructions generated with low-budget RGB-D cameras or other commodity scanning devices. As the depth data of these sensors is noisy, truncated signed distance fields are typically used to regularize out the noise, which unfortunately leads to over-smoothed results. In our approach, we leverage RGB data to refine these reconstructions through shading cues, as color input is typically of much higher resolution than the depth data. As a result, we obtain reconstructions with high geometric detail, far beyond the depth resolution of the camera itself. Our core contribution is shading-based refinement directly on the implicit surface representation, which is generated from globally-aligned RGB-D images. We formulate the inverse shading problem on the volumetric distance field, and present a novel objective function which jointly optimizes for fine-scale surface geometry and spatially-varying surface reflectance. In order to enable the efficient reconstruction of sub-millimeter detail, we store and process our surface using a sparse voxel hashing scheme which we augment by introducing a grid hierarchy. A tailored GPU-based Gauss-Newton solver enables us to refine large shape models to previously unseen resolution within only a few seconds.

TitelProceedings of ACM SIGGRAPH 2015
Herausgeber (Verlag)Association for Computing Machinery
ISBN (elektronisch)9781450333313
PublikationsstatusVeröffentlicht - 27 Juli 2015
Extern publiziertJa
VeranstaltungACM Special Interest Group on Computer Graphics and Interactive Techniques Conference, SIGGRAPH 2015 - Los Angeles, USA/Vereinigte Staaten
Dauer: 9 Aug. 201513 Aug. 2015


KonferenzACM Special Interest Group on Computer Graphics and Interactive Techniques Conference, SIGGRAPH 2015
Land/GebietUSA/Vereinigte Staaten
OrtLos Angeles


Untersuchen Sie die Forschungsthemen von „Shading-based refinement on volumetric signed distance functions“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren