Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Plane-based optimization for 3D object reconstruction from single line drawings.

Jianzhuang Liu1, Liangliang Cao, Zhenguo Li

  • 1Department of Information Engineering, The Chinese University of Hong Kong, Hong Kong. zliu@ie.cuhk.edu.hk

IEEE Transactions on Pattern Analysis and Machine Intelligence
|December 18, 2007
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Single-cell and multi-omics integration delineates the landscape of gene-wise intratumor heterogeneity and identifies prognostic biomarkers for immunotherapy in non-small cell lung cancer.

Cancer immunology, immunotherapy : CII·2026
Same author

SJD++: Improved Speculative Jacobi Decoding for Training-free Acceleration of Discrete Auto-regressive Text-to-Image Generation.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Effect of Nutrient Enrichment on Alpha and Beta Diversity of Macroinvertebrate Community in a Boreal River of Northern China.

Biology·2026
Same author

OutDreamer: Video Outpainting With a Diffusion Transformer.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

MagicSeg: Open-World Segmentation Pretraining via Counterfactural Diffusion-Based Auto-Generation.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Mixture of Cluster-Conditional LoRA Experts for Vision-Language Instruction Tuning.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

HardFlow: Hard-Constrained Sampling for Flow-Matching Models Via Trajectory Optimization.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Industrial Brain: Self-Evolving Neuro-Symbolic Autonomy with Causal Resilience for Cyber-Physical Systems.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Adaptive Hardness-Driven Dictionary Distillation for Incomplete Streaming View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Achieving Text-based Person Retrieval with Any Granularity.

IEEE transactions on pattern analysis and machine intelligence·2026
See all related articles

This study introduces a novel method for 3D object reconstruction from 2D line drawings by optimizing plane parameters, enabling efficient and robust reconstruction of complex objects.

Area of Science:

  • Computer Vision
  • Computer Graphics
  • Geometric Modeling

Background:

  • Previous optimization methods for 3D reconstruction from 2D line drawings struggle with complex objects due to high-dimensional, non-linear objective functions and local minima.
  • These methods often use vertex depths as variables, limiting their scalability and accuracy for intricate shapes.

Purpose of the Study:

  • To develop a more efficient and robust method for 3D planar-faced object reconstruction from single 2D line drawings.
  • To overcome the limitations of existing optimization-based approaches, particularly for complex objects.

Main Methods:

  • The proposed method utilizes the parameters of planes defining the object's faces as variables, establishing linear constraints.
  • This approach reduces the optimization problem's dimensionality, creating a lower-dimensional nullspace for easier optimization.

Related Experiment Videos

  • Singular value decomposition (SVD) of the projection matrix is employed to expand the nullspace, enhancing robustness for imperfect line drawings.

    • Main Results:

    • The dimension of the nullspace is proven to be equal to the minimum number of vertex depths required to define the 3D object.
    • The method successfully reconstructs more complex 3D objects compared to existing related techniques.
    • The approach demonstrates improved computational efficiency.

    Conclusions:

    • Reconstructing 3D objects from 2D line drawings is significantly improved by optimizing plane parameters over vertex depths.
    • The method offers a scalable and robust solution for 3D reconstruction, particularly for complex, planar-faced objects.
    • This technique provides a computationally efficient alternative for 3D reconstruction tasks.