Collaborative Neural Rendering using Anime Character Sheets

TL;DR

This paper introduces CoNR, a neural rendering method that generates anime character images in specified poses from few reference images, overcoming the challenge of diverse character designs without universal models.

Contribution

The paper proposes a novel collaborative neural rendering approach that uses landmark encoding and multi-view feature warping, along with a large dataset of character sheets for anime pose synthesis.

Findings

CoNR effectively generates diverse anime character images in new poses.

Multi-reference images improve rendering quality significantly.

A new dataset of over 700,000 character images supports research in this area.

Abstract

Drawing images of characters with desired poses is an essential but laborious task in anime production. Assisting artists to create is a research hotspot in recent years. In this paper, we present the Collaborative Neural Rendering (CoNR) method, which creates new images for specified poses from a few reference images (AKA Character Sheets). In general, the diverse hairstyles and garments of anime characters defies the employment of universal body models like SMPL, which fits in most nude human shapes. To overcome this, CoNR uses a compact and easy-to-obtain landmark encoding to avoid creating a unified UV mapping in the pipeline. In addition, the performance of CoNR can be significantly improved when referring to multiple reference images, thanks to feature space cross-view warping in a carefully designed neural network. Moreover, we have collected a character sheet dataset containing over 700,000 hand-drawn and synthesized images of diverse poses to facilitate research in this area. Our code and demo are available at https://github.com/megvii-research/IJCAI2023-CoNR.