Geometry-Consistent Neural Shape Representation with Implicit Displacement Fields
This work addresses the challenge of detailed 3D shape representation for computer graphics and vision applications, offering an incremental improvement over existing methods.
The paper tackles the problem of representing detailed 3D geometry by introducing implicit displacement fields, which decompose shapes into smooth base surfaces and high-frequency displacements, resulting in improved representational power, training stability, and generalizability in tasks like surface reconstruction and detail transfer.
We present implicit displacement fields, a novel representation for detailed 3D geometry. Inspired by a classic surface deformation technique, displacement mapping, our method represents a complex surface as a smooth base surface plus a displacement along the base's normal directions, resulting in a frequency-based shape decomposition, where the high frequency signal is constrained geometrically by the low frequency signal. Importantly, this disentanglement is unsupervised thanks to a tailored architectural design that has an innate frequency hierarchy by construction. We explore implicit displacement field surface reconstruction and detail transfer and demonstrate superior representational power, training stability and generalizability.