Enhancing Sketch Animation: Text-to-Video Diffusion Models with Temporal Consistency and Rigidity Constraints

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Rai, Gaurav, Sharma, Ojaswa
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912927149195264
author Rai, Gaurav
Sharma, Ojaswa
author_facet Rai, Gaurav
Sharma, Ojaswa
contents Animating hand-drawn sketches using traditional tools is challenging and complex. Sketches provide a visual basis for explanations, and animating these sketches offers an experience of real-time scenarios. We propose an approach for animating a given input sketch based on a descriptive text prompt. Our method utilizes a parametric representation of the sketch's strokes. Unlike previous methods, which struggle to estimate smooth and accurate motion and often fail to preserve the sketch's topology, we leverage a pre-trained text-to-video diffusion model with SDS loss to guide the motion of the sketch's strokes. We introduce length-area (LA) regularization to ensure temporal consistency by accurately estimating the smooth displacement of control points across the frame sequence. Additionally, to preserve shape and avoid topology changes, we apply a shape-preserving As-Rigid-As-Possible (ARAP) loss to maintain sketch rigidity. Our method surpasses state-of-the-art performance in both quantitative and qualitative evaluations.
format Preprint
id arxiv_https___arxiv_org_abs_2411_19381
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Enhancing Sketch Animation: Text-to-Video Diffusion Models with Temporal Consistency and Rigidity Constraints
Rai, Gaurav
Sharma, Ojaswa
Computer Vision and Pattern Recognition
Graphics
Animating hand-drawn sketches using traditional tools is challenging and complex. Sketches provide a visual basis for explanations, and animating these sketches offers an experience of real-time scenarios. We propose an approach for animating a given input sketch based on a descriptive text prompt. Our method utilizes a parametric representation of the sketch's strokes. Unlike previous methods, which struggle to estimate smooth and accurate motion and often fail to preserve the sketch's topology, we leverage a pre-trained text-to-video diffusion model with SDS loss to guide the motion of the sketch's strokes. We introduce length-area (LA) regularization to ensure temporal consistency by accurately estimating the smooth displacement of control points across the frame sequence. Additionally, to preserve shape and avoid topology changes, we apply a shape-preserving As-Rigid-As-Possible (ARAP) loss to maintain sketch rigidity. Our method surpasses state-of-the-art performance in both quantitative and qualitative evaluations.
title Enhancing Sketch Animation: Text-to-Video Diffusion Models with Temporal Consistency and Rigidity Constraints
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2411.19381