KillingFusion: Non-Rigid 3D Reconstruction Without Correspondences

2017-07-01 · CVPR 2017 7 · Miroslava Slavcheva, Maximilian Baust, Daniel Cremers, Slobodan Ilic

We introduce a geometry-driven approach for real-time 3D reconstruction of deforming surfaces from a single RGB-D stream without any templates or shape priors. To this end, we tackle the problem of non-rigid registration by level set evolution without explicit correspondence search. Given a pair of signed distance fields (SDFs) representing the shapes of interest, we estimate a dense deformation field that aligns them. It is defined as a displacement vector field of the same resolution as the SDFs and is determined iteratively via variational minimization. To ensure it generates plausible shapes, we propose a novel regularizer that imposes local rigidity by requiring the deformation to be a smooth and approximately Killing vector field, i.e. generating nearly isometric motions. Moreover, we enforce that the level set property of unity gradient magnitude is preserved over iterations. As a result, KillingFusion reliably reconstructs objects that are undergoing topological changes and fast inter-frame motion. In addition to incrementally building a model from scratch, our system can also deform complete surfaces. We demonstrate these capabilities on several public datasets and introduce our own sequences that permit both qualitative and quantitative comparison to related approaches.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

3D ReconstructionUnity

Neural Non-Rigid Tracking

2020-06-23 · NeurIPS 2020 12 · Aljaž Božič, Pablo Palafox, Michael Zollhöfer, Angela Dai 외

We introduce a novel, end-to-end learnable, differentiable non-rigid tracker that enables state-of-the-art non-rigid reconstruction by a learned robust optimization. Given two input RGB-D frames of a non-rigidly moving o…

Unsupervised Monocular Depth Reconstruction of Non-Rigid Scenes

2020-12-31 · Ayça Takmaz, Danda Pani Paudel, Thomas Probst, Ajad Chhatkuli 외

Monocular depth reconstruction of complex and dynamic scenes is a highly challenging problem. While for rigid scenes learning-based methods have been offering promising results even in unsupervised cases, there exists li…

Depth Estimation Motion Segmentation

To The Point: Correspondence-driven monocular 3D category reconstruction

2021-06-10 · NeurIPS 2021 12 · Filippos Kokkinos, Iasonas Kokkinos

We present To The Point (TTP), a method for reconstructing 3D objects from a single image using 2D to 3D correspondences learned from weak supervision. We recover a 3D shape from a 2D image by first regressing the 2D pos…

DeepDeform: Learning Non-rigid RGB-D Reconstruction with Semi-supervised Data

2019-12-09 · Aljaž Božič, Michael Zollhöfer, Christian Theobalt, Matthias Nießner

Applying data-driven approaches to non-rigid 3D reconstruction has been difficult, which we believe can be attributed to the lack of a large-scale training corpus. Unfortunately, this method fails for important cases suc…

3D Reconstruction RGB-D Reconstruction

DeepDeform: Learning Non-Rigid RGB-D Reconstruction With Semi-Supervised Data

2020-06-01 · CVPR 2020 6 · Aljaz Bozic, Michael Zollhofer, Christian Theobalt, Matthias Niessner