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

RotoTexture: automated tools for texturing raw video.

Hui Fang1, John C Hart

  • 1Google Inc, Mountain View, CA 94043, USA. cubicshining@gmail.com

IEEE Transactions on Visualization and Computer Graphics
|November 1, 2006
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

A Few-Shot Learning-Based Siamese Capsule Network for Intrusion Detection with Imbalanced Training Data.

Computational intelligence and neuroscience·2021
Same author

Impact of neoadjuvant chemoradiotherapy on the local recurrence and distant metastasis pattern of locally advanced rectal cancer: a propensity score-matched analysis.

Chinese medical journal·2021
Same author

PSD-93 up-regulates the synaptic activity of corticotropin-releasing hormone neurons in the paraventricular nucleus in depression.

Acta neuropathologica·2021
Same author

Abnormal B-cell development in TIMP-deficient bone marrow.

Blood advances·2021
Same author

Elevated reactivity of Apelin inhibited renal fibrosis induced by chronic intermittent hypoxia.

Archives of biochemistry and biophysics·2021
Same author

The Sunny Side of Negative Feedback: Negative Feedback Enhances One's Motivation to Win in Another Activity.

Frontiers in human neuroscience·2021
Same journal

Two-phase Impulse Fluid on Particle Flow Map.

IEEE transactions on visualization and computer graphics·2026
Same journal

FGO-SLAM++: Real-time Geometry-Aware Gaussian SLAM with Continuous Opacity Field.

IEEE transactions on visualization and computer graphics·2026
Same journal

Blue Noise Dithering for Reservoir-based Spatio-temporal Importance Resampling.

IEEE transactions on visualization and computer graphics·2026
Same journal

ROS-GS: Relightable Outdoor Scenes With Gaussian Splatting.

IEEE transactions on visualization and computer graphics·2026
Same journal

MesoSplats: Texture Synthesis with Gaussian Splatting.

IEEE transactions on visualization and computer graphics·2026
Same journal

GLLA: A Unified Force-Directed Graph Layout Framework Supporting Local Adjustments.

IEEE transactions on visualization and computer graphics·2026
See all related articles

This video editing system applies realistic textures to surfaces in raw video without 3D models. It uses recovered surface normals to deform textures, enabling plausible surface texture mapping and synthesis for diffuse surfaces.

Area of Science:

  • Computer Vision
  • Computer Graphics
  • Image Processing

Background:

  • Traditional video editing often requires complex 3D models for realistic texture application.
  • Applying textures to dynamic surfaces in uncalibrated video presents challenges in maintaining coherence and plausibility.

Purpose of the Study:

  • To develop a video editing system for applying time-coherent textures to surfaces in uncalibrated video.
  • To enable both texture mapping from an image and texture synthesis from a swatch without 3D reconstruction.

Main Methods:

  • Utilizes a recovered normal field to deform textures, adhering to surface undulations.
  • Employs nonlinear least-squares optimization with a spring model for texture mapping.
  • Uses coarse optical flow and a minimum advection tree for texture synthesis.

Related Experiment Videos

Main Results:

  • Achieves robust and plausible texture application on nearly diffuse surfaces like faces and t-shirts.
  • Demonstrates effective texture deformation guided by the evolving normal field.
  • Successfully synthesizes textures by advecting pixel clusters and managing dynamic visibility.

Conclusions:

  • The proposed system offers an effective method for time-coherent texture application in video editing without explicit 3D modeling.
  • The approach provides plausible results for diffuse surfaces, enhancing visual realism in video content.
  • The system's reliance on normal fields and optical flow offers a practical solution for texture manipulation in challenging video scenarios.