Publications – Graphics & Spatial Computing Lab at SMU

Research from the Graphics & Spatial Computing Lab spanning computer graphics, 3D vision, geometric deep learning, and spatial computing — from Delaunay-based reconstruction theory to large-scale LiDAR understanding of cities, forests, and the night sky.

Note: though my official name is Jiju Poovvancheri, I use my first name (‘Jiju’) followed by my father’s name (‘Peethambaran’) in some of my publications.

Journal Conference Preprint Tutorial Book

2026 11 entries

PreprintP5

Geometry-Guided Anisotropic Procedural Noise via Apollonian Domain Warping

Jack Greenlaw, Amr Ghoneim, Jiju Poovvancheri

Preprint

JournalJ42

A Persistent Homology Design Space for 3D Point Cloud Learning

Prachi Kudeshia, Jiju Poovvancheri, Amr Ghoneim, Dong Chen

Computers & Graphics, Elsevier

arXiv

JournalJ41

Learning Significant Persistent Homology Features for 3D Shape Understanding

Prachi Kudeshia, Jiju Poovvancheri

Computers & Graphics, Elsevier

Journal arXiv

JournalJ40

WDTS: Water Droplet Model-driven Entropy Optimization for Individual Tree Skeletonization from Terrestrial Laser Scanning Point Clouds

Tao Pu, Shenglan Du, Mingming Sui, Dong Chen, Yueqian Shen, Yanming Chen, Yiyang Kong, Ziyou Wang, Jiju Poovvancheri, Liqiang Zhang

ISPRS Journal of Photogrammetry and Remote Sensing, Elsevier

2026 11 entries

Geometry-Guided Anisotropic Procedural Noise via Apollonian Domain Warping

A Persistent Homology Design Space for 3D Point Cloud Learning

Learning Significant Persistent Homology Features for 3D Shape Understanding

WDTS: Water Droplet Model-driven Entropy Optimization for Individual Tree Skeletonization from Terrestrial Laser Scanning Point Clouds

RBF Weighted Hyper-Involution for RGB-D Object Detection

CWADE-net: A Deep Learning Framework for Vegetation Invasion and Brick Spalling Defect Detection on Nanjing Ming City Wall

Learning Disentangled Representations of LiDAR Scans via Alpha Complexes for Tree Species Classification

A Cyclic Reinforcement Learning Framework for Predicting Road Repairs from High Resolution Remote Sensing Imagery

DepGAN-RS: Depth Guided Object Placement for Realistic Remote Sensing Image Augmentation

Structure- and Semantics-Aware Mesh Simplification for Generating Lightweight 3D Building Models

Emerging Trends in Wildfire Detection through the Lens of Computer Vision and Wildfire Emission Quantification: A Comprehensive Survey

2025 4 entries

Public Building Geometric Models from Point Clouds: A Multidimensional Quality Evaluation Framework

Adaptive Isoline Interval Optimization for Precise Contour Segmentation and Instance Level Detection of Martian Impact Craters

Segmentation of Individual Trees in TLS Point Clouds via Graph Optimization

Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Clouds

2024 8 entries

Learning Geometric Complexes for 3D Shape Classification

DepGAN: Leveraging Depth Maps for Handling Occlusions and Transparency in Image Composition

Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Clouds

SatStreaks: Towards Supervised Learning for Delineating Satellite Streaks from Astronomical Images

Impact Crater Recognition Methods: A Review

Individual Tree Points Segmentation by Combining Marker Controlled Watershed Segmentation and Spectral Clustering Optimization

Semantic-aware Room-level Indoor Modeling from Point Clouds

Shape Preserving Mesh Decimation for 3D Building Modeling

2023 5 entries

Feature Preserving Decimation of Urban Meshes

GAGAT: A Global Aware Graph Attention Network for 3D Classification and Segmentation

Enhancing Satellite Trail Detection in Night Sky Imagery with Automatic Salience Thresholding

EDPNet: A Novel Encoding-Decoding Network with Pyramidal Representation for Semantic Image Segmentation

MC-UNet: Martian Crater Segmentation at Semantic and Instance Levels using U-Net-Based Convolutional Neural Network

2022 4 entries

Lightweight Reconstruction of Urban Buildings: Data Structures, Algorithms and Future Directions

Outline and Shape Reconstruction in 2D

A Graph Attention Network for Object Detection from Raw LiDAR Data

Shape Reconstruction in 2D: From Theory to Practice

2021 7 entries

AFGL-Net: Attentive Fusion of Global and Local Deep Features for Building Facade Parsing

Critical Points Extraction from Building Facades by Analyzing Gradient Structure Tensor

2D Points Curve Reconstruction Survey and Benchmark

Prime Gradient Noise

Point Cloud Inversion: A Novel Approach for the Localization of Trees in Forests from TLS Data

Tunnel Reconstruction with Block Level Precision via a Hybrid Approach Combining Data-driven Segmentation and Model-driven Assembly

A Sampling Type Discernment Approach towards Reconstruction of a Point Set in R²

2020 5 entries

Dynamic Edge Weights in Graph Neural Networks for 3D Object Detection

TCM-ICP: Transformation Compatibility Measure for Registering Multiple LiDAR Scans

Towards Video based Collective Motion Analysis through Shape Tracking and Matching

Maintaining the Spatial Proximities of Objects under Motion

Multi-view Features Joint Learning with Label and Local Distribution Consistency for Point Cloud Classification

2019 3 entries

LSMAT: Least Square Medial Axis Transform

A Novel Framework for 2.5D Building Contouring from Large-Scale Residential Scenes

Incremental Labeling of Voronoi Vertices for Shape Reconstruction

2018 4 entries

Multi-level Building Detection Framework in Remote Sensing Images Based on Convolutional Neural Networks

Joint Clusters and Iterative Graph Cuts for ALS Point Cloud Filtering

A Supervoxel-based Vegetation Classification via Decomposition and Modelling of Full-waveform Airborne Laser Scanning Data

LiDAR Point Clouds to 3D Urban Models: A Review

2017 2 entries

Topologically-aware Building Rooftop Reconstruction from Airborne Laser Scanning Point Clouds

Enhancing Urban Facades via LiDAR based Sculpting

2016 2 entries

An Empirical Study on Randomized Optimal Area Polygonization of Planar Point Sets

Automatic Reconstruction of Triangular Meshes from Point Sets

2015 5 entries

A Voronoi based Labeling Approach to Curve Reconstruction and Medial Axis Approximation

A Non-parametric Approach to Shape Reconstruction from Planar Point Sets through Delaunay Filtering

A Randomized Approach to Volume Constrained Polyhedronization Problem

A Graph-based Geometric Approach to Object Contour Extraction from Noisy Digital Binary Images

Reconstruction of Water-tight Surfaces through Delaunay Sculpting

Before 2014 3 entries

Volume Constrained Polyhedronization of Point Sets in 3-Space

A Graph Theoretic Approach for the Construction of Concave Hulls of Point Sets in R²

Petri Net based Verification of a Cooperative Workflow Model