SAniHead: Sketching Animal-like 3D Character Heads Using a View-surface Collaborative Mesh Generative Network

Du, Dong; Han, Xiaoguang; Fu, Hongbo; Wu, Feiyang; Yu, Yizhou; Cui, Shuguang; Liu, Ligang

doi:10.1109/tvcg.2020.3030330

Cited by 8 publications

(10 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, researchers have also explored various schemes for interactive modeling from 2D sketch images [10], [16], [18], [19], [20], [38], [39]. In line with our work, DeepSketch2Face [10] proposed a sketch modeling system that allows users to create caricature heads from scratch.…”

Section: D Face From 2d Imagesupporting

confidence: 64%

“…However, since the 3D caricature shape is confined to the parametric caricature face model, DeepSketch2Face cannot faithfully reflect large deformations and wrinkle details presented in the sketch. To address this issue, SAni-Head [16] proposed a view-surface collaborative mesh generative network, which turns dual-view freehand sketches into animalmorphic heads. Nevertheless, it fails to synthesize novel shapes deviating from training datasets due to the restricted generalization ability of their network.…”

Section: D Face From 2d Imagementioning

confidence: 99%

“…Accuracy. Recent learning-based sketching systems [10], [11], [14], [15], [16] allow novice users to create visually-plausible 3D models with a few strokes. However, they are not capable of designing shapes with fine-grained details.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

SimpModeling: Sketching Implicit Field to Guide Mesh Modeling for 3D Animalmorphic Head Design

Luo

Zhou

Zhu

et al. 2021

The 34th Annual ACM Symposium on User Interface Software and Technology

View full text Add to dashboard Cite

Modeling 3D avatars benefits various application scenarios such as AR/VR, gaming, and filming. Character faces contribute significant diversity and vividity as a vital component of avatars. However, building 3D character face models usually requires a heavy workload with commercial tools, even for experienced artists. Various existing sketch-based tools fail to support amateurs in modeling diverse facial shapes and rich geometric details. In this paper, we present SketchMetaFace -a sketching system targeting amateur users to model high-fidelity 3D faces in minutes. We carefully design both the user interface and the underlying algorithm. First, curvature-aware strokes are adopted to better support the controllability of carving facial details. Second, considering the key problem of mapping a 2D sketch map to a 3D model, we develop a novel learning-based method termed "Implicit and Depth Guided Mesh Modeling" (IDGMM). It fuses the advantages of mesh, implicit, and depth representations to achieve high-quality results with high efficiency. In addition, to further support usability, we present a coarse-to-fine 2D sketching interface design and a data-driven stroke suggestion tool. User studies demonstrate the superiority of our system over existing modeling tools in terms of the ease to use and visual quality of results. Experimental analyses also show that IDGMM reaches a better trade-off between accuracy and efficiency.SketchMetaFace is available at https://zhongjinluo.github.io/SketchMetaFace/.

show abstract

Section: D Face From 2d Imagesupporting

confidence: 64%

Section: D Face From 2d Imagementioning

confidence: 99%

See 1 more Smart Citation

SimpModeling: Sketching Implicit Field to Guide Mesh Modeling for 3D Animalmorphic Head Design

Luo

Zhou

Zhu

et al. 2021

The 34th Annual ACM Symposium on User Interface Software and Technology

View full text Add to dashboard Cite

show abstract

“…In other words, such methods treat the inputs as hard constraints and generate shapes strictly corresponding to the inputs. Another group of methods adopt indirect reconstruction strategies: they generate shapes by deforming or refining intermediate shape proxies [Du et al 2020;Guillard et al 2021;Han et al 2017;Zhang et al 2021] to better approximate the geometric features contained in the input drawings. As mentioned earlier, the algorithm-generated line drawings strictly resemble the geometry features of source images or models.…”

Section: Granularitymentioning

confidence: 99%

DifferSketching: How Differently Do People Sketch 3D Objects?

Xiao¹,

Su²,

Liao³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

the existing datasets. We analyze the collected data at three levels, i.e., sketchlevel, stroke-level, and pixel-level, under both spatial and temporal characteristics, and within and across groups of creators. We found that the drawings by professionals and novices show significant differences at stroke-level, both intrinsically and extrinsically. We demonstrate the usefulness of our dataset in two applications: (i) freehand-style sketch synthesis, and (ii) posing it as a potential benchmark for sketch-based 3D reconstruction. Our dataset and code are available at https://chufengxiao.github.io/DifferSketching/.CCS Concepts: • Applied computing → Arts and humanities; • Humancentered computing → Interaction design; User studies; • Computing methodologies → Graphics systems and interfaces.

show abstract

“…Shape modeling from multi‐view sketches involves generating a 3D shape using sketches drawn from different viewpoints. Existing methods for shape modeling from multi‐view sketches often utilize multi‐branch inputs with fixed viewpoints [LGK*17,ZQG*20,DHF*20] or employ an iterative refinement strategy [DAI*18, CWC*22] to improve modeling quality. However, these methods still suffer from limitations such as the inability to retain faithful details depicted by input sketches [DAI*18, CWC*22] and the inefficiency of multi‐view interaction [LGK*17, LPL*18].…”

Section: Introductionmentioning

confidence: 99%

GA‐Sketching: Shape Modeling from Multi‐View Sketching with Geometry‐Aligned Deep Implicit Functions

Zhou,

Luo,

et al. 2023

Computer Graphics Forum

View full text Add to dashboard Cite

Sketch‐based shape modeling aims to bridge the gap between 2D drawing and 3D modeling by providing an intuitive and accessible approach to create 3D shapes from 2D sketches. However, existing methods still suffer from limitations in reconstruction quality and multi‐view interaction friendliness, hindering their practical application. This paper proposes a faithful and user‐friendly iterative solution to tackle these limitations by learning geometry‐aligned deep implicit functions from one or multiple sketches. Our method lifts 2D sketches to volume‐based feature tensors, which align strongly with the output 3D shape, enabling accurate reconstruction and faithful editing. Such a geometry‐aligned feature encoding technique is well‐suited to iterative modeling since features from different viewpoints can be easily memorized or aggregated. Based on these advantages, we design a unified interactive system for sketch‐based shape modeling. It enables users to generate the desired geometry iteratively by drawing sketches from any number of viewpoints. In addition, it allows users to edit the generated surface by making a few local modifications. We demonstrate the effectiveness and practicality of our method with extensive experiments and user studies, where we found that our method outperformed existing methods in terms of accuracy, efficiency, and user satisfaction. The source code of this project is available at https://github.com/LordLiang/GA‐Sketching.

show abstract

SAniHead: Sketching Animal-like 3D Character Heads Using a View-surface Collaborative Mesh Generative Network

Cited by 8 publications

References 56 publications

SimpModeling: Sketching Implicit Field to Guide Mesh Modeling for 3D Animalmorphic Head Design

SimpModeling: Sketching Implicit Field to Guide Mesh Modeling for 3D Animalmorphic Head Design

DifferSketching: How Differently Do People Sketch 3D Objects?

GA‐Sketching: Shape Modeling from Multi‐View Sketching with Geometry‐Aligned Deep Implicit Functions

Contact Info

Product

Resources

About