What is it about?
Artists often capture character poses via raster sketches then use these drawings as a reference while painstakingly posing a 3D character in a 3D animation software. We propose the first system for algorithmically inferring a 3D character pose from a single bitmap sketch, producing poses consistent with viewer expectations.
Featured Image
Photo by Lavi Perchik on Unsplash
Why is it important?
We hope that it can become a part of the animation pipeline and become a big time-saver. With a single natural bitmap sketch of a character, our algorithm allows the animator to automatically, with no additional input, apply the drawn 3D pose to a custom ‘rigged’ and ‘skinned’ 3D character. That essentially means that animators can now create a first rough draft of the animation right after the storyboarding stage, i.e., when they have just sketched the keyframes.
Perspectives
Read the Original
This page is a summary of: Sketch2Pose, ACM Transactions on Graphics, July 2022, ACM (Association for Computing Machinery),
DOI: 10.1145/3528223.3530106.
You can read the full text:
Resources
Sketch2Pose: Estimating a 3D Character Pose from a Bitmap Sketch
Project page
Sketch2Pose: Estimating a 3D Character Pose from a Bitmap Sketch
Presentation
Sketch2Pose: Estimating a 3D Character Pose from a Bitmap Sketch
Fast forward video
Sketch2Pose: Estimating a 3D Character Pose from a Bitmap Sketch
Open source code
Contributors
The following have contributed to this page