Thingi10K: A Dataset of 10,000 3D-Printing Models
read the original abstract
Empirically validating new 3D-printing related algorithms and implementations requires testing data representative of inputs encountered \emph{in the wild}. An ideal benchmarking dataset should not only draw from the same distribution of shapes people print in terms of class (e.g., toys, mechanisms, jewelry), representation type (e.g., triangle soup meshes) and complexity (e.g., number of facets), but should also capture problems and artifacts endemic to 3D printing models (e.g., self-intersections, non-manifoldness). We observe that the contextual and geometric characteristics of 3D printing models differ significantly from those used for computer graphics applications, not to mention standard models (e.g., Stanford bunny, Armadillo, Fertility). We present a new dataset of 10,000 models collected from an online 3D printing model-sharing database. Via analysis of both geometric (e.g., triangle aspect ratios, manifoldness) and contextual (e.g., licenses, tags, classes) characteristics, we demonstrate that this dataset represents a more concise summary of real-world models used for 3D printing compared to existing datasets. To facilitate future research endeavors, we also present an online query interface to select subsets of the dataset according to project-specific characteristics. The complete dataset and per-model statistical data are freely available to the public.
This paper has not been read by Pith yet.
Forward citations
Cited by 31 Pith papers
-
FllumaOne: A Code-Native Multimodal CAD Dataset with Executable Programs and Kernel-Validated Feature Histories
FllumaOne releases 100,000 kernel-validated CAD models as executable Python programs with aligned multimodal data including feature histories and geometry exports.
-
Metric--Phase Fields: Decoupling Distance and Sign for Thin-Structure Reconstruction from Unoriented Point Clouds
Metric-Phase Fields decouple unsigned metric proximity from a smooth phase field with learnable sharpness to enable faithful reconstruction of thin and open structures from point clouds.
-
PolycubeNet: A Dual-latent Diffusion Model for Polycube-Based Hexahedral Mesh Generation
PolycubeNet applies a dual-latent diffusion architecture to generate polycube point clouds from input point clouds, enabling robust hexahedral mesh creation without surface segmentation or templates.
-
Tangent Blow-Ups for Processing Non-Manifold Geometry
Tangent blow-ups lift non-manifold geometry into a product space with the Grassmannian of tangent planes, enabling well-defined discretized differential operators on singular data.
-
Tangent Blow-Ups for Processing Non-Manifold Geometry
Tangent blow-ups lift non-manifold geometry into position-tangent space to enable differential operators at singularities.
-
Best Segmentation Buddies for Image-Shape Correspondence
The work defines Best Segmentation Buddies as vertices on a 3D shape whose nearest image pixel under distilled features falls inside a given 2D segment, then uses the same features to segment the shape in 3D.
-
OffsetAxis: UDF Mesh Reconstruction via Offset-Volume Medial Axis Extraction
OffsetAxis reconstructs meshes from unsigned distance fields by extracting the medial axis of the alpha-offset volume using ray casting and variational medial ball optimization.
-
Near-Linear Time Generalized Sinkhorn Algorithms for Bounded Genus Graphs
GenusSink delivers near-linear-time approximate generalized Sinkhorn algorithms for bounded-genus graphs via separator decompositions, computational geometry, and fast matrix-vector multiplies with generalized distanc...
-
Near-Linear Time Generalized Sinkhorn Algorithms for Bounded Genus Graphs
GenusSink achieves near-linear time approximate generalized Sinkhorn for bounded genus graphs via separator decompositions, computational geometry, and fast distance matrix operations.
-
Near-Linear Time Generalized Sinkhorn Algorithms for Bounded Genus Graphs
GenusSink achieves near-linear time approximate generalized Sinkhorn for geodesic optimal transport on bounded-genus graphs by combining separator-based decompositions with Fourier and low-displacement-rank matrix-vec...
-
Manifold k-NN: Accelerated k-NN Queries for Manifold Point Clouds
Manifold k-NN generalizes DP-NNS to k-NN queries on manifold point clouds via a recursive successor-list property, delivering 1-10x speedups and full dynamic support.
-
Generative Modeling with Orbit-Space Particle Flow Matching
OGPP is a particle flow-matching method using orbit-space canonicalization and geometric paths that achieves lower error and fewer steps than prior approaches on 3D benchmarks.
-
SpUDD: Superpower Contouring of Unsigned Distance Data
SpUDD defines superpower contours from power diagrams of unsigned distance samples, proves convergence to the true surface, and uses them to generate approximating polygonal meshes that outperform prior strategies.
-
SpUDD: Superpower Contouring of Unsigned Distance Data
SpUDD defines superpower contours on power diagrams of unsigned distance samples, proves their convergence to the true surface, and uses them to generate approximating meshes that outperform other strategies for this ...
-
Objaverse-XL: A Universe of 10M+ 3D Objects
Objaverse-XL supplies over 10 million diverse 3D objects that, when used to render 100 million views, improve zero-shot novel-view synthesis in models such as Zero123.
-
Continuous Neural Reparameterization as a Deep Geometric Prior for Robust Fixed-Chart UV Repair
A neural reparameterization method using untrained SIREN achieves zero-flip UV charts on all compact pre-cut meshes and 42/47 valid solves on a 47-chart stratified benchmark.
-
Monte Carlo Steklov Operators for Large-Scale Geometry Processing in the Wild
Monte Carlo estimation of volumetric Steklov operators enables robust spectral geometry processing at the scale of hundreds of thousands of in-the-wild meshes and supports contrastive 3D representation learning.
-
BijectiveRemesh: Maintaining Bijective Mappings for Data Transfer Across Remeshed Manifolds
BijectiveRemesh maintains continuous bijective mappings across remeshing sequences by composing local bijective atlases for operations including edge collapses, splits, swaps, and smoothing.
-
FreeForm: Reduced-Order Deformable Simulation from Particle-Based Skinning Eigenmodes
FreeForm derives reduced-order skinning weights for particle-based hyperelastic simulation by solving a generalized eigensystem on the elastic energy Hessian, achieving faster training and lower error than neural fields.
-
Structural MAT: Clean and Scalable Medial Axis Simplification via Explicit Surface Correspondence
A new MAT simplification algorithm uses explicit surface correspondence tracking and priority-controlled edge collapses to preserve structural features like fillet alignments on discrete meshes.
-
FILTR: Extracting Topological Features from Pretrained 3D Models
FILTR predicts persistence diagrams from pretrained 3D encoders on the new DONUT benchmark, showing limited topological signals in encoders but successful approximation via learnable feed-forward.
-
Shape: A Self-Supervised 3D Geometry Foundation Model for Industrial CAD Analysis
A 10.9M-parameter self-supervised model pretrained on 61k CAD meshes achieves R²=0.729 reconstruction and 98.1% top-1 retrieval on held-out data via masked normalized geometry reconstruction and multi-resolution contr...
-
Medial Axis Aware Learning of Signed Distance Functions
A higher-order variational formulation with Ambrosio-Tortorelli phase fields learns global signed distance functions from point clouds by enforcing medial axis properties and the eikonal equation.
-
Patchwork: A compact representation for 3D polygonal shapes
Patchwork is a new compact shape representation for 2D and 3D geometry that approximates arbitrary shapes with arbitrary precision using a small number of parameters, provable bounds, and gradient-based optimization w...
-
MEBench: A Novel Benchmark for Understanding Mutual Exclusivity Bias in Vision-Language Models
MEBench is a new benchmark and data-generation pipeline that measures mutual exclusivity bias in VLMs, finding weak bias but some use of spatial context to resolve novel-object ambiguity.
-
From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation
The paper surveys 3D asset generation methods and organizes them around the full production pipeline to assess which outputs meet engine-level requirements for interactive applications.
-
Linkify: Learning from Interface-Augmented Assembly Graphs
Linkify augments assembly graphs with corrected interface point clouds and trains GATv2 for masked part prediction, outperforming non-graph baselines on Fusion 360 data.
-
From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation
The paper surveys 3D content generation literature using a taxonomy of asset types and production stages to evaluate progress toward engine-ready assets.
-
Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation
Hunyuan3D 2.0 scales flow-based diffusion transformers and texture synthesis models to generate high-resolution textured 3D assets that outperform prior state-of-the-art in geometry, alignment, and texture quality.
-
A Cookbook of 3D Vision: Data, Learning Paradigms, and Application
A survey paper that constructs a taxonomy linking 3D geometric representations, acquisition, datasets, supervision regimes, and applications in reconstruction, generation, and 4D modeling.
-
Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material
Hunyuan3D 2.1 is a two-part system with DiT for shape generation and Paint for texture synthesis that produces high-fidelity 3D assets with PBR materials.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.