paper-with-me

Papers

Learning Geometry-Dependent and Physics-Based Inverse Image Reconstruction

2020-07-18 · Xiajun Jiang, Sandesh Ghimire, Jwala Dhamala, Zhiyuan Li, Prashnna Kumar Gyawali, Linwei Wang

Deep neural networks have shown great potential in image reconstruction problems in Euclidean space. However, many reconstruction problems involve imaging physics that are dependent on the underlying non-Euclidean geometry. In this paper, we present a new approach to learn inverse imaging that exploit the underlying geometry and physics. We first introduce a non-Euclidean encoding-decoding network that allows us to describe the unknown and measurement variables over their respective geometrical domains. We then learn the geometry-dependent physics in between the two domains by explicitly modeling it via a bipartite graph over the graphical embedding of the two geometry. We applied the presented network to reconstructing electrical activity on the heart surface from body-surface potential. In a series of generalization tasks with increasing difficulty, we demonstrated the improved ability of the presented network to generalize across geometrical changes underlying the data in comparison to its Euclidean alternatives.

📄 PDF Abstract BibTeX arXiv:2007.09522

Code (0)

등록된 구현이 없습니다.

Tasks

Image Reconstruction

Similar Papers 제목 키워드 기반

PBR-NeRF: Inverse Rendering with Physics-Based Neural Fields

2024-12-12 · CVPR 2025 1 · Sean Wu, Shamik Basu, Tim Broedermann, Luc van Gool 외

We tackle the ill-posed inverse rendering problem in 3D reconstruction with a Neural Radiance Field (NeRF) approach informed by Physics-Based Rendering (PBR) theory, named PBR-NeRF. Our method addresses a key limitation …

3D ReconstructionInverse RenderingNeRFNeural Rendering+1

Diffusion-Based Material Regularization for Physics-Based Inverse Rendering

2026-06-30 · Jingwang Ling, Lifan Wu, Feng Xu, Shuang Zhao arxiv

Reconstructing physics-based 3D assets -- geometry, materials, and illumination -- from multi-view images is a core problem in computer graphics and vision, and a prerequisite for realistic relighting and editing. Physic…

Inverse Rendering

PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relighting

2021-04-01 · CVPR 2021 1 · Kai Zhang, Fujun Luan, Qianqian Wang, Kavita Bala 외

We present PhySG, an end-to-end inverse rendering pipeline that includes a fully differentiable renderer and can reconstruct geometry, materials, and illumination from scratch from a set of RGB input images. Our framewor…

Depth PredictionImage RelightingInverse RenderingSurface Normals Estimation+1

Training Adaptive Reconstruction Networks for Blind Inverse Problems

2022-02-23 · Alban Gossard, Pierre Weiss

Neural networks allow solving many ill-posed inverse problems with unprecedented performance. Physics informed approaches already progressively replace carefully hand-crafted reconstruction algorithms in real application…

DeblurringImage Deblurring

No-Harm Physics-Informed Inverse Learning with Residual-Calibrated Uncertainty

2026-06-05 · Ronald Katende arxiv

Physics-informed learning is increasingly used for partial differential equation (PDE)-governed inverse problems, but its reliability remains difficult to certify. This paper develops a no-harm certification-and-selectio…