Key papers in Computational Mechanics

Pofolia’s corpus holds 80 papers from the Computational Mechanics subfield (2012–2026). The list below starts with the most cited.

Most cited

Ranked by citation count. Because citations accumulate over time, this list naturally leans towards work published a few years ago; for where the field is now, see “recently added”.

  • PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

    2017 · 9,803 citations

    PointNet is a novel neural network architecture designed to directly process irregular 3D point cloud data, bypassing the need for computationally expensive transformations into voxel grids or images.

    Go to source

  • UMAP: Uniform Manifold Approximation and Projection

    The Journal of Open Source Software · 2018 · FWCI 391.51 · 9,692 citations · Open access

    UMAP is a new dimension reduction technique offering both visualization and general non-linear reduction capabilities, built on a rigorous mathematical foundation but with a user-friendly API.

    Go to source

  • Decoupled Weight Decay Regularization

    arXiv (Cornell University) · 2017 · 9,135 citations · Open access

    A new method decouples weight decay from gradient updates in adaptive optimization algorithms like Adam, improving generalization performance.

    Go to source

  • Dynamic Graph CNN for Learning on Point Clouds

    ACM Transactions on Graphics · 2019 · Q1 · SJR 5.00 · FWCI 461.40 · 6,795 citations · Open access

    A new neural network module, EdgeConv, is introduced for processing 3D point cloud data, dynamically computing graph structures in each layer to capture local neighborhood information and learn global shape properties.

    Go to source

  • Robust Recovery of Subspace Structures by Low-Rank Representation

    IEEE Transactions on Pattern Analysis and Machine Intelligence · 2012 · Q1 · SJR 4.00 · FWCI 144.98 · 3,666 citations

    A new method called Low-Rank Representation (LRR) can accurately identify underlying subspace structures in data, even when the data contains outliers or sparse errors.

    Go to source

  • SMPL

    ACM Transactions on Graphics · 2015 · Q1 · SJR 5.00 · FWCI 57.08 · 3,661 citations

    A new Skinned Multi-Person Linear (SMPL) model accurately represents diverse human body shapes and poses, outperforming previous methods.

    Go to source

  • Geometric Deep Learning: Going beyond Euclidean data

    IEEE Signal Processing Magazine · 2017 · Q1 · SJR 2.00 · FWCI 237.05 · 3,646 citations

    Geometric deep learning (GDL) extends deep neural networks to non-Euclidean data like graphs and manifolds, enabling analysis of complex, structured information.

    Go to source

  • New development in freefem++

    Journal of Numerical Mathematics · 2012 · Q1 · SJR 1.00 · FWCI 92.57 · 3,300 citations

    This abstract provides no specific findings or results regarding developments in freefem++.

    Go to source

  • Sparse Subspace Clustering: Algorithm, Theory, and Applications

    IEEE Transactions on Pattern Analysis and Machine Intelligence · 2013 · Q1 · SJR 4.00 · FWCI 173.72 · 3,155 citations

    A new algorithm, Sparse Subspace Clustering (SSC), is proposed to group high-dimensional data points that naturally reside in multiple lower-dimensional structures.

    Go to source

  • Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials

    arXiv (Cornell University) · 2012 · 2,980 citations · Open access

    A new approximate inference algorithm enables efficient computation for fully connected Conditional Random Fields (CRFs) with Gaussian edge potentials, allowing dense pixel-level connections in image segmentation.

    Go to source

  • PointRCNN: 3D Object Proposal Generation and Detection From Point Cloud

    2019 · 2,977 citations

    PointRCNN introduces a novel two-stage framework that directly generates 3D object proposals from raw point clouds, bypassing the need for RGB images or intermediate representations like bird's-eye view or voxels.

    Go to source

  • Introduction to the Finite Element Method

    Cambridge University Press eBooks · 2021 · FWCI 202.40 · 2,945 citations

    This innovative teaching package integrates theoretical learning with practical application of the Finite Element Method (FEM) using computational software like MATLAB®, PTC Creo Parametric, ANSYS APDL, ANSYS Workbench, and SolidWorks.

    Go to source

  • PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

    arXiv (Cornell University) · 2016 · 2,880 citations · Open access

    PointNet is a novel neural network architecture designed to directly process irregular 3D point cloud data, overcoming the limitations of converting it to voxel grids or images.

    Go to source

  • PIVlab – Towards User-friendly, Affordable and Accurate Digital Particle Image Velocimetry in MATLAB

    Journal of Open Research Software · 2014 · Q3 · FWCI 76.81 · 2,420 citations

    A new open-source MATLAB tool, PIVlab, has been developed to address challenges in Digital Particle Image Velocimetry (DPIV) for accurate flow field mapping.

    Go to source

  • Thermal Radiation Heat Transfer

    2020 · FWCI 126.68 · 2,377 citations

    The seventh edition of this textbook updates fundamental principles and analytical/numerical techniques for thermal radiation heat transfer, incorporating expanded sections on surface properties, electromagnetic theory, scattering, absorption, near-field transfer, and connections to thermodynamics.

    Go to source

  • Deep Learning for 3D Point Clouds: A Survey

    IEEE Transactions on Pattern Analysis and Machine Intelligence · 2020 · Q1 · SJR 4.00 · FWCI 180.65 · 2,272 citations

    This paper surveys recent deep learning methods for 3D point cloud processing, covering classification, object detection/tracking, and segmentation.

    Go to source

  • Weighted Nuclear Norm Minimization with Application to Image Denoising

    2014 · 2,271 citations

    This paper introduces Weighted Nuclear Norm Minimization (WNNM), a novel approach that assigns different weights to singular values, enhancing flexibility over standard nuclear norm minimization. Applied to image denoising, WNNW significantly outperforms existing methods like BM3D.

    Go to source

  • Point Transformer

    2021 IEEE/CVF International Conference on Computer Vision (ICCV) · 2021 · 2,219 citations

    A novel 'Point Transformer' architecture leverages self-attention mechanisms for 3D point cloud processing, achieving state-of-the-art results in tasks like semantic scene segmentation.

    Go to source

  • Proximal Algorithms

    Foundations and Trends® in Optimization · 2014 · FWCI 217.11 · 2,166 citations

    Proximal algorithms are presented as a powerful, general-purpose tool analogous to Newton's method, specifically designed for complex optimization problems like nonsmooth, constrained, large-scale, or distributed versions.

    Go to source

  • Multiphase Flow And Fluidization: Continuum And Kinetic Theory Descriptions

    2012 · 2,115 citations

    This book bridges theoretical multiphase flow with practical, predictive solutions for industrial fluidization problems, advancing the emerging science of multiphase flow.

    Go to source

Recently added

  • Elemente der Mathematik

    Elemente der Mathematik · 2026 · 40 citations

    This publication is a journal and does not contain research findings or specific results.

    Go to source

  • Interfaces and Free Boundaries, Mathematical Analysis, Computation and Applications

    Interfaces and Free Boundaries Mathematical Analysis Computation and Applications · 2026 · Q1 · 24 citations

    This paper analyzes a finite difference scheme for approximating level set solutions to mean curvature flow, proving an L-infinity error bound under specific conditions.

    Go to source

  • Investigating Non-Newtonian Fluid Behavior in Hydrocyclones Via Computational Fluid Dynamics

    International Journal of Innovative Science and Research Technology (IJISRT) · 2024 · FWCI 314.54 · 958 citations

    A CFD study of viscoelastic food in hydrocyclones reveals how viscosity fluctuations impact particle separation efficiency, providing insights for optimizing food processing technology.

    Go to source

  • ShapeNet: An Information-Rich 3D Model Repository

    2023 · FWCI 14.38 · 1,999 citations

    ShapeNet is a new large-scale repository of 3D CAD models, organized by semantic categories and annotated with detailed information like alignments, parts, and symmetry planes.

    Go to source

  • Point Transformer

    2021 IEEE/CVF International Conference on Computer Vision (ICCV) · 2021 · 2,219 citations

    A novel 'Point Transformer' architecture leverages self-attention mechanisms for 3D point cloud processing, achieving state-of-the-art results in tasks like semantic scene segmentation.

    Go to source

Add this field to your daily feed

Pick your interests and new work in your area arrives every day, summarised. Full summaries live in the app.

Open the app

Other subfields in the same field

All fields