Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 24, 2025Open Access

From One Single Sketch to 3D Detailed Face Reconstruction

View Full Paper
Ask AI
Bookmark
Share

Authors

LWLiangjian WenChinese Academy of SciencesZYZhaohui YangUniversity of Alaska AnchorageXZXianlin ZhangBeijing University of Posts and Telecommunications

Discussion

Loading...

Member takes

Implication

Proposed framework enhances geometric contours and textures in 3D face reconstruction, indicating significant advances in sketch-based modeling.

Key Points

  • Sketch-1-to-3 achieves state-of-the-art performance in 3D face reconstruction from sketches, addressing key challenges.
  • The framework utilizes a Geometric Contour and Texture Detail module to accurately improve detail extraction and alignment.
  • Deep learning architecture with domain adaptation enhances robustness against data limitations, ensuring high-fidelity outputs.
  • Construction of real and synthetic datasets promotes evaluation of sketch-based reconstruction techniques in advancing this field.

Cite This Study

Wen et al. (2025) studied this question.

synapsesocial.com/papers/68d6e16f8b2b6861e4c3ff44https://doi.org/10.48550/arxiv.2502.17852
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1S2TD-Face: Reconstruct a Detailed 3D Face with Controllable Texture from a Single Sketch2024
  2. 2SketchBodyNet++: Sketch-Based 3D Human Mesh Reconstruction via Hybrid Parametric Networks2026
  3. 33D Reconstruction From a Single Sketch via View-Dependent Depth Sampling2024 · 10 citations
  4. 4Robust Differentiable Sketch Rendering for Single‐View 3D Reconstruction2025
  5. 53D Hair Reconstruction From Sketches Using Strand and Depth Maps2026