paper-with-me

Papers

Geometry-Consistent Neural Shape Representation with Implicit Displacement Fields

2021-06-09 · ICLR 2022 4 · Wang Yifan, Lukas Rahmann, Olga Sorkine-Hornung

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.

📄 PDF Abstract BibTeX arXiv:2106.05187

Code (1)

yifita/idf 공식 구현 pytorch

Tasks

3D geometryDisentanglementSurface Reconstruction

Similar Papers 제목 키워드 기반

Single-view 3D Body and Cloth Reconstruction under Complex Poses

2022-05-09 · Nicolas Ugrinovic, Albert Pumarola, Alberto Sanfeliu, Francesc Moreno-Noguer

Recent advances in 3D human shape reconstruction from single images have shown impressive results, leveraging on deep networks that model the so-called implicit function to learn the occupancy status of arbitrarily dense…

3D Reconstruction

QUADify: Extracting Meshes with Pixel-level Details and Materials from Images

2024-01-01 · CVPR 2024 1 · Maximilian Frühauf, Hayko Riemenschneider, Markus Gross, Christopher Schroers

Despite exciting progress in automatic 3D reconstruction from images excessive and irregular triangular faces in the resulting meshes still constitute a significant challenge when it comes to adoption in practical ar…

3D ReconstructionImage Reconstruction

High-Quality Mesh Blendshape Generation from Face Videos via Neural Inverse Rendering

2024-01-16 · Xin Ming, Jiawei Li, Jingwang Ling, Libo Zhang 외

Readily editable mesh blendshapes have been widely used in animation pipelines, while recent advancements in neural geometry and appearance representations have enabled high-quality inverse rendering. Building upon these…

Inverse Rendering

Reliable Modeling of Distribution Shifts via Displacement-Reshaped Optimal Transport

2026-05-06 · Philip Naumann, Jacob Kauffmann, Klaus-Robert Müller, Grégoire Montavon arxiv

Optimal transport (OT) is a central framework for modeling distribution shifts. Because OT compares distributions directly in input space, a well-designed ground metric between observations is essential to ensure that th…

FourierHandFlow: Neural 4D Hand Representation Using Fourier Query Flow

2023-07-16 · NeurIPS 2023 11

Recent 4D shape representations model continuous temporal evolution of implicit shapes by (1) learning query flows without leveraging shape and articulation priors or (2) decoding shape occupancies separately for each ti…

4D reconstruction