paper-with-me

홈 › Papers

Aligning Gradient and Hessian for Neural Signed Distance Function

2023-09-21 · NeurIPS 2023 11

The Signed Distance Function (SDF), as an implicit surface representation, provides a crucial method for reconstructing a watertight surface from unorganized point clouds. The SDF has a fundamental relationship with the principles of surface vector calculus. Given a smooth surface, there exists a thin-shell space in which the SDF is differentiable everywhere such that the gradient of the SDF is an eigenvector of its Hessian matrix, with a corresponding eigenvalue of zero. In this paper, we introduce a method to directly learn the SDF from point clouds in the absence of normals. Our motivation is grounded in a fundamental observation: aligning the gradient and the Hessian of the SDF provides a more efficient mechanism to govern gradient directions. This, in turn, ensures that gradient changes more accurately reflect the true underlying variations in shape. Extensive experimental results demonstrate its ability to accurately recover the underlying shape while effectively suppressing the presence of ghost geometry.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Neural-Singular-Hessian: Implicit Neural Representation of Unoriented Point Clouds by Enforcing Singular Hessian

2023-09-04 · Zixiong Wang, Yunxiao Zhang, Rui Xu, Fan Zhang 외

Neural implicit representation is a promising approach for reconstructing surfaces from point clouds. Existing methods combine various regularization terms, such as the Eikonal and Laplacian energy terms, to enforce the …

Towards More Robust Interpretation via Local Gradient Alignment

2022-11-29 · Sunghwan Joo, Seokhyeon Jeong, Juyeon Heo, Adrian Weller 외

Neural network interpretation methods, particularly feature attribution methods, are known to be fragile with respect to adversarial input perturbations. To address this, several methods for enhancing the local smoothnes…

Computational EfficiencyNetwork Interpretation

Understanding Hessian Alignment for Domain Generalization

2023-08-22 · ICCV 2023 1 · Sobhan Hemati, Guojun Zhang, Amir Estiri, Xi Chen

Out-of-distribution (OOD) generalization is a critical ability for deep learning models in many real-world scenarios including healthcare and autonomous vehicles. Recently, different techniques have been proposed to impr…

Autonomous VehiclesDomain GeneralizationFederated Learning

Neural Octahedral Field: Octahedral prior for simultaneous smoothing and sharp edge regularization

2024-08-01 · Ruichen Zheng, Tao Yu

Neural implicit representation, the parameterization of distance function as a coordinate neural field, has emerged as a promising lead in tackling surface reconstruction from unoriented point clouds. To enforce consiste…

Surface Reconstruction

HessianForge: Scalable LiDAR reconstruction with Physics-Informed Neural Representation and Smoothness Energy Constraints

2025-03-11 · Hrishikesh Viswanath, Md Ashiqur Rahman, Chi Lin, Damon Conover 외

Accurate and efficient 3D mapping of large-scale outdoor environments from LiDAR measurements is a fundamental challenge in robotics, particularly towards ensuring smooth and artifact-free surface reconstructions. Althou…