Animate your own image in the desired way with a batch run on VESSL.
In this paper, a new end-to-end unsupervised motion transfer framework is introduced to address the challenge of large pose gaps between source and driving images in image animation. The framework utilizes thin-plate spline motion estimation for flexible optical flow, incorporates multi-resolution occlusion masks to realistically restore missing regions, and employs additional auxiliary loss functions to ensure high-quality image generation. Experimental results demonstrate the superiority of this method over existing approaches, showcasing significant improvements in pose-related metrics across various objects such as talking faces, human bodies, and pixel animations.
name: Thin-Plate-Spline-Motion-Model
description: "Animate your own image in the desired way with a batch run on VESSL."
image: nvcr.io/nvidia/pytorch:21.05-py3
resources:
cluster: aws-apne2
preset: v1.v100-1.mem-52
run:
- workdir: /root/examples/thin-plate-spline-motion-model
command: |
pip install -r requirements.txt
python run.py --config config/vox-256.yaml --device_ids 0
import:
/root/examples: git://github.com/vessl-ai/examples
/root/examples/vox: s3://vessl-public-apne2/vessl_run_datasets/vox/
