True2Form: 3D curve networks from 2D sketches via selective regularization
Baoxuan Xu,William S. C. Chang,Alla Sheffer,Adrien Bousseau,James McCrae,Karan Singh +5 more
- Vol. 33, Iss: 4, pp 131
Reads0
Chats0
TLDR
True2Form is a sketch-based modeling system that reconstructs 3D curves from typical design sketches by progressively detecting and enforcing applicable properties, accounting for their global impact on an evolving 3D curve network.Abstract:
True2Form is a sketch-based modeling system that reconstructs 3D curves from typical design sketches. Our approach to infer 3D form from 2D drawings is a novel mathematical framework of insights derived from perception and design literature. We note that designers favor viewpoints that maximally reveal 3D shape information, and strategically sketch descriptive curves that convey intrinsic shape properties, such as curvature, symmetry, or parallelism. Studies indicate that viewers apply these properties selectively to envision a globally consistent 3D shape. We mimic this selective regularization algorithmically, by progressively detecting and enforcing applicable properties, accounting for their global impact on an evolving 3D curve network. Balancing regularity enforcement against sketch fidelity at each step allows us to correct for inaccuracy inherent in free-hand sketching. We perceptually validate our approach by showing agreement between our algorithm and viewers in selecting applicable regularities. We further evaluate our solution by: reconstructing a range of 3D models from diversely sourced sketches; comparisons to prior art; and visual comparison to both ground-truth and 3D reconstructions by designers.read more
Citations
More filters
Journal ArticleDOI
Functional map networks for analyzing and exploring large shape collections
TL;DR: This paper shows how to rigorously formulate the consistency constraint in the functional map setting, and leads to a powerful tool for computing consistent functional maps, and also for discovering shared structures, such as meaningful shape parts.
Proceedings ArticleDOI
Structure-aware shape processing
TL;DR: This course organizes, summarizes, and presents the key concepts and methodological approaches towards efficient structure-aware shape processing, and attempts to list the key open problems and challenges to make it easier for new researchers to better explore and contribute to this topic.
Journal ArticleDOI
Interactive sketching of urban procedural models
TL;DR: This work uses a machine learning approach to solve the inverse problem of finding the procedural model that best explains a user sketch, and integrates its algorithm in a coarse-to-fine urban modeling system that allows users to create rich buildings by successively sketching the building mass, roof, facades, windows, and ornaments.
Proceedings ArticleDOI
3D Shape Reconstruction from Sketches via Multi-view Convolutional Networks
TL;DR: In this article, a deep, encoder-decoder network is proposed to reconstruct 3D shapes from 2D sketches in the form of line drawings, where the encoder converts the sketch into a compact representation encoding shape information and the decoder converts this representation into depth and normal maps capturing the underlying surface from several output viewpoints.
Proceedings ArticleDOI
Experimental Evaluation of Sketching on Surfaces in VR
TL;DR: A set of controlled studies to analyze the factors affecting human ability to sketch freely in a 3D VR environment indicate that the lack of a physical drawing surface is a major cause of inaccuracies in VR drawing, and that the effect is dependent on the orientation of the drawing surface.
References
More filters
Journal ArticleDOI
Three-dimensional object recognition from single two-dimensional images
TL;DR: It is argued that similar mechanisms and constraints form the basis for recognition in human vision.
Proceedings ArticleDOI
Teddy: a sketching interface for 3D freeform design
TL;DR: This work presents a sketching interface for quickly and easily designing freeform models such as stuffed animals and other rotund objects and shows that a first-time user typically masters the operations within 10 minutes, and can construct interesting 3D models within minutes.
Journal ArticleDOI
Mixed-integer quadrangulation
TL;DR: A novel method for quadrangulating a given triangle mesh by constructing an as smooth as possible symmetric cross field satisfying a sparse set of directional constraints and computed a seamless globally smooth parametrization whose iso-parameter lines follow the cross field directions.
Journal ArticleDOI
Technical Section: Sketch-based modeling: A survey
TL;DR: A categorization based on how a SBIM application chooses to interpret a sketch is presented, of which there are three primary methods: to create a 3D model, to add details to an existing model, or to deform and manipulate a model.
Proceedings ArticleDOI
FiberMesh: designing freeform surfaces with 3D curves
TL;DR: This system provides real-time algorithms for both control curve deformation and the subsequent surface optimization and it is shown that one can create sophisticated models using this system, which have not yet been seen in previous sketching or functional optimization systems.