Local Non-Rigid Structure-From-Motion From Diffeomorphic Mappings
Shaifali Parashar, Mathieu Salzmann, Pascal Fua
摘要
We propose a new formulation to non-rigid structurefrom-motion that only requires the deforming surface to preserve its differential structure. This is a much weaker assumption than the traditional ones of isometry or conformality. We show that it is nevertheless sufficient to establish local correspondences between the surface in two different images and therefore to perform point-wise reconstruction using only first-order derivatives. To this end, we formulate differential constraints and solve them algebraically using the theory of resultants. We will demonstrate that our approach is more widely applicable, more stable in noisy and sparse imaging conditions and much faster than earlier ones, while delivering similar accuracy. The code is available at https://github.com/ cvlab-epfl/diff-nrsfm/.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper6
- -SfT: Shape-from-Template with a Physics-Based Deformation ModelNavami Kairanda, Edith Tretschk, Mohamed A. Elgharib, Christian Theobalt 等CVPR 2022 · 被引用 20 次
- Neural Prior for Trajectory EstimationChaoyang Wang, Xueqian Li, Jhony Kaesemodel Pontes, Simon LuceyCVPR 2022 · 被引用 19 次
- Physics-guided Shape-from-Template: Monocular Video Perception through Neural Surrogate ModelsDavid Stotko, Nils Wandel, Reinhard KleinCVPR 2024 · 被引用 6 次
- Deep Non-Rigid Structure-from-Motion Revisited: Canonicalization and Sequence ModelingHui Deng, Jiawei Shi, Zhen Qin, Yiran Zhong 等AAAI 2025 · 被引用 1 次
- SAFT: Shape and Appearance of Fabrics from Template via Differentiable Physical Simulations from Monocular VideoDavid Stotko, Reinhard KleinICCV 2025 · 被引用 1 次
相关 Paper
- Non-rigid Structure-from-Motion: Temporally-smooth Procrustean Alignment and Spatially-variant Deformation ModelingJiawei Shi, Hui Deng, Yuchao DaiCVPR 2024 · 被引用 1 次
- PR-RRN: Pairwise-Regularized Residual-Recursive Networks for Non-rigid Structure-from-MotionHaitian Zeng, Yuchao Dai, Xin Yu, Xiaohan Wang 等ICCV 2021 · 被引用 12 次
- Distill Knowledge From NRSfM for Weakly Supervised 3D Pose LearningChaoyang Wang, Chen Kong, Simon LuceyICCV 2019 · 被引用 52 次
- Polarimetric Relative Pose EstimationZhaopeng Cui, Viktor Larsson, Marc PollefeysICCV 2019 · 被引用 24 次
- Deep Non-Rigid Structure From MotionChen Kong, Simon LuceyICCV 2019 · 被引用 72 次
