DrawingSpinUp: 3D Animation from Single Character Drawings
Jie Zhou, Chufeng Xiao, Miu-Ling Lam, Hongbo Fu
2024-09-16
Summary
This paper introduces DrawingSpinUp, a new system that transforms simple 2D character drawings into dynamic 3D animations, allowing characters to move and perform actions like dancing.
What's the problem?
Existing methods for animating character drawings are limited because they only create flat, 2D movements. When trying to make 3D models from amateur drawings, these methods often struggle with details and shapes, especially with thin or delicate parts like limbs. This leads to animations that don't look realistic or engaging.
What's the solution?
DrawingSpinUp solves these problems by using a two-step approach. First, it removes the confusing contour lines from the drawings that can distort how the character looks in 3D. Then, it rebuilds the character's appearance and adds back the contours after creating the animation. Additionally, it uses a special technique to refine thin parts of the character to ensure they look good in 3D. This allows characters to spin, jump, and dance in a lifelike way.
Why it matters?
This research is important because it makes it easier for artists and creators to bring their drawings to life in 3D without needing advanced skills or complex tools. By improving how we animate characters from simple drawings, it opens up new opportunities for storytelling and creative expression in fields like animation, gaming, and digital art.
Abstract
Animating various character drawings is an engaging visual content creation task. Given a single character drawing, existing animation methods are limited to flat 2D motions and thus lack 3D effects. An alternative solution is to reconstruct a 3D model from a character drawing as a proxy and then retarget 3D motion data onto it. However, the existing image-to-3D methods could not work well for amateur character drawings in terms of appearance and geometry. We observe the contour lines, commonly existing in character drawings, would introduce significant ambiguity in texture synthesis due to their view-dependence. Additionally, thin regions represented by single-line contours are difficult to reconstruct (e.g., slim limbs of a stick figure) due to their delicate structures. To address these issues, we propose a novel system, DrawingSpinUp, to produce plausible 3D animations and breathe life into character drawings, allowing them to freely spin up, leap, and even perform a hip-hop dance. For appearance improvement, we adopt a removal-then-restoration strategy to first remove the view-dependent contour lines and then render them back after retargeting the reconstructed character. For geometry refinement, we develop a skeleton-based thinning deformation algorithm to refine the slim structures represented by the single-line contours. The experimental evaluations and a perceptual user study show that our proposed method outperforms the existing 2D and 3D animation methods and generates high-quality 3D animations from a single character drawing. Please refer to our project page (https://lordliang.github.io/DrawingSpinUp) for the code and generated animations.