← ArchivePaper2024
Creating Infinite Characters From a Single Template: How Automation May Give Super Powers to 3D Artists
Mariana Dias, Pedro Jaime de Coelho, Rui Figueiredo, R. M. Carvalho, Veronica Orvalho, Alexis Roche
Didimo's talk on generating an unbounded cast from a single template, automating the days of manual work one non-player character normally costs.
Abstract
Game character creation is a time-consuming and highly manual process that often requires several days to complete one non-player character. In addition, each game has unique character art style and technical specifications (mesh, rig, textures). This explains why game worlds with thousands of unique characters are rare. To address this problem, we propose an automated character generation pipeline that can produce a full-body, rigged, dressed, and accessorized 3D character in less than a minute from an initial template character, based on 2D pictures and/or facial text descriptors. This pipeline helps scale up character creation and populate games with unlimited variations at reduced cost, while ensuring consistency with the game art style.
How to read this
- Category
- SIGGRAPH talk from a company, on automating character creation in a production pipeline.
- Contributions
- A pipeline that generates an unbounded cast of characters from a single template model.
- The framing that one non-player character normally costs several days of manual work, which is the cost being attacked.
- An argument that automation extends what a small art team can produce rather than replacing it.
- Context
- This is Didimo's talk, and Orvalho co-authors it, which makes it the commercial endpoint of the academic line that starts with orvalho-rig-transfer-2008. The through line is the same one Orvalho has followed since 2006: author a rig once and let a machine adapt it to every character that follows. Read it as the industrial answer to the question the 2008 paper asked.Builds on: Transferring the Rig and Animations from a Character to Different Face Models
- Correctness
- A talk, so there is no evaluation to check and the numbers quoted are the company's own. Treat the days per character figure as a plausible order of magnitude rather than a measurement. The claim that deserves scrutiny is variety: generating from a single template makes the family resemblance the hard problem, and a talk is not going to show you the failure cases.
- Clarity
- Short and clearly aimed at practitioners. It tells you what the system does, not how it does it.
- How to read it
- Single pass. Read it for the pipeline shape and the production framing, then go to orvalho-rig-transfer-2008 if you want the method underneath. If you are evaluating the tool commercially, the talk is a pitch and should be read as one.
Built upon by
Nothing yet.
Related work
- Transferring a Labeled Generic Rig to Animate Face Models 2006 / AMDO
- Easy Rigging of Face by Automatic Registration and Transfer of Skinning Parameters 2010 / ICCVG
- Reusable Facial Rigging and Animation: Create Once, Use Many 2007 / PhD Thesis
- Example-Based Facial Rigging 2010 / SIGGRAPH
Keywords
This page summarises the entry and links to its original source. The archive never hosts or redistributes the publication itself.Show it in the full archive list →