SSD: Smooth Signed Distance Surface Reconstruction

By Fatih Calakli, Gabriel Taubin. 2011

269 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Graphics and Computer-Aided Design, 3D Vision & Pose

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Graphics and Computer-Aided Design

In 3D Vision & Pose

Citations in the corpus

Occupancy Networks: Learning 3D Reconstruction in Function Space (2018, background): “However, unlike other representations, this approach requires additional non-trivial post-processing steps [3,6,37,38] to generate the ﬁnal 3D mesh.”
Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs (2017, background): “Octrees have a long history in classical 3D reconstruction and depth map fusion [21, 1, 11, 34, 6, 31].”
Deep Marching Cubes: Learning Explicit Surface Representations (2018, methodology): “In contrast to the method proposed in this paper, an additional post-processing step [4,25] is required to “lift” the 3D point cloud to a dense surface mesh.”
Large-Scale Semantic 3D Reconstruction: An Adaptive Multi-resolution Model for Multi-class Volumetric Labeling (2016, methodology): “Contrary to prior work [21, 5, 10], our octree structure is not predetermined by the input data, but refined adaptively, such that we can exploit the per-class probabilities rather than only a minimal energy solution.”
ARCH: Animatable Reconstruction of Clothed Humans (2020, methodology): “Holes are then filled up using Smooth Signed Distance Surface reconstruction [8] (see Fig.”
A Survey of Surface Reconstruction from Point Clouds (2017, unknown): “The main difference be-tween the approaches is that [KH13] solves the problem via a ﬁnite-element multi-grid formulation, whereas [CT11] use ﬁnite-differences, due to the complexity in discretizing the Hessian term; In particular, the screened Poisson formulation [KH13] is up to two orders of…”
Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion (2020, methodology): “Unlike voxels or meshes, point clouds need to be non-trivially post-processed using classical methods [6, 30, 31, 8] to obtain renderable surfaces.”
Global, Dense Multiscale Reconstruction for a Billion Points (2015, methodology): “We also compare with the marching cubes implementation of Kazhdan et al. [11], which is used by the PSR and FSSR algorithm, and with the dual marching cubes algorithm by Schaefer and Warren [17] used by SSD.”
An Octree-Based Approach towards Efficient Variational Range Data Fusion (2016, background): “accelerating point/surface look-ups, [4, 15]) and get discarded or recomputed after each iteration.”
Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction (2020, methodology): “Methods such as PSR [29], SSD [7] and PFS [51] fit global implicit function to represent shapes.”
Simple, Accurate, and Robust Projector-Camera Calibration (2012, methodology): “Finally, we scanned a statue from six different viewpoints and, after manual alignment and merging, we created a complete 3D model using Smooth Signed Distance (SSD) surface reconstruction ([23], [24]).”
Image-Based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era (2019, methodology): “However, they require a post processing step, e.g., Poisson surface reconstruction [89] or SSD [90], to retrieve the 3D surface mesh, which is the quantity of interest.”