Learning a Neural 3D Texture Space from 2D Exemplars

Niloy J. Mitra; Philipp Henzler; Tobias Ritschel

RECORD

Learning a Neural 3D Texture Space from 2D Exemplars

Philipp Henzler, Niloy J. Mitra, Tobias Ritschel

Computer Vision and Pattern Recognition · Submitted 9 Dec 2019

abstract compiled · 2026-09-23 · no language-model review

The authors' main claim We propose a generative model of 2D and 3D natural textures with diversity, visual fidelity and at high computational efficiency.

how it is stated · asserted 1.00 read the record →

Comment (0) Read on arXiv ↗

Cite ▾

Claim paper

The compiled record

The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.

Open the compiled record

Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-09-23: 1 request, 4,245 input tokens.

What the abstract itself states, as probabilities: claims first 0.04 · states limitation 0.07 · human participants 0.02 · controlled comparison 0.03 · randomized assignment 0.01 · states quantitative result 0.04 · compares with prior results 0.08 · mentions code or data availability 0.03.

The abstract, sentence by sentence

arXiv listing abstract v2. Results and the main claim are underlined; show every role.

We propose a generative model of 2D and 3D natural textures with diversity, visual fidelity and at high computational efficiency. This is enabled by a family of methods that extend ideas from classic stochastic procedural texturing (Perlin noise) to learned, deep, non-linearities. The key idea is a hard-coded, tunable and differentiable step that feeds multiple transformed random 2D or 3D fields into an MLP that can be sampled over infinite domains. Our model encodes all exemplars from a diverse set of textures without a need to be re-trained for each exemplar. Applications include texture interpolation, and learning 3D textures from 2D exemplars.

background contribution method result interpretation main claim

What the classifier reports for each sentence. The number is the probability it gave the label.
#	sentence	role	the authors' own work	states the main conclusion	strength
s0	We propose a generative model of 2D and 3D natural textures with diversity, visual fidelity and at high computational efficiency.	contribution 1.00	0.90	0.51	asserted 1.00
s1	This is enabled by a family of methods that extend ideas from classic stochastic procedural texturing (Perlin noise) to learned, deep, non-linearities.	method 0.95	0.41	0.07	asserted 1.00
s2	The key idea is a hard-coded, tunable and differentiable step that feeds multiple transformed random 2D or 3D fields into an MLP that can be sampled over infinite domains.	method 0.99	0.79	0.14	asserted 1.00
s3	Our model encodes all exemplars from a diverse set of textures without a need to be re-trained for each exemplar.	contribution 0.60	0.90	0.16	asserted 1.00
s4	Applications include texture interpolation, and learning 3D textures from 2D exemplars.	contribution 0.50	0.56	0.08	asserted 0.91

What kind of paper the classifier reports this is: method or tool 1.00 · evidence from simulation or computation 0.57.

What was examined, and what was not

sources read

arXiv listing abstract v2

not examined

full text
figures and tables
references and citing sentences
relations to other papers

levels run

P abstract

not run

S sections
T body sentences
C citations
R cross-paper relations

Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. Every number in the measurements table is the authors', checked by code. Record as JSON

The paper

Original abstract

We propose a generative model of 2D and 3D natural textures with diversity, visual fidelity and at high computational efficiency. This is enabled by a family of methods that extend ideas from classic stochastic procedural texturing (Perlin noise) to learned, deep, non-linearities. The key idea is a hard-coded, tunable and differentiable step that feeds multiple transformed random 2D or 3D fields into an MLP that can be sampled over infinite domains. Our model encodes all exemplars from a diverse set of textures without a need to be re-trained for each exemplar. Applications include texture interpolation, and learning 3D textures from 2D exemplars.

Human review

How Pith checks papers → · Full audit of this paper →

How the literature uses it

3 arXiv papers cite this in 3 sentences

Each citing sentence is taken from the citing paper's LaTeX source and typed by Pith's classifier. A label appears at probability 0.8 or more (0.95 for support), a contest at 0.7 or more; the quoted words are the citing authors'. How each label was checked · JSON

Papers citing it · 2 sentences without a confident label

Cites it as background 1 paper

Related applications include dynamic texture synthesis [ref] , texture inpainting [ref] , 3D texture mapping [ref] , texture interpolation [ref] , morphing [ref] , expansion [ref] or procedural generation [ref] .

A Generative Model for Texture Synthesis based on Optimal Transport between Feature Distributions · Introduction · 0.99

What it cites · 1 sentence without a confident label

Cites as background 1 paper

Some work has used adversarial training to capture the essence of textures [ref] , including the non-stationary case [ref] or even inside a single image [ref] .

Non-Stationary Texture Synthesis by Adversarial Expansion · Introduction · 0.93

Discussion

Know something about this paper? Leave a comment, or highlight any passage above to comment on it.