Topology-Based Failure Modes in AI-Generated 3D Assets for Production Rigging Pipelines: A Practitioner-Informed Benchmarking Framework

Description This repository contains the research materials supporting the manuscript "Topology-Based Failure Modes in AI-Generated 3D Assets for Production Rigging Pipelines: A Practitioner-Informed Benchmarking Framework." The repository includes: Raw survey dataset (CSV) containing anonymized responses from 105 participants. High-resolution publication figures (TIFF/PNG) used in the manuscript. The survey investigated practitioner-reported topology defects in AI-generated 3D assets used within professional production pipelines, including rigging, animation, UV mapping, and subdivision workflows. The study proposes a practitioner-informed Topological Integrity Score (TIS) framework for benchmarking production readiness of AI-generated 3D assets. The dataset has been fully anonymized and contains no personally identifiable information. It is provided to support transparency, reproducibility, and future research on topology quality assessment in generative AI for 3D content creation. Researchers are encouraged to reuse the data with appropriate citation of the associated publication. Keywords: Generative AI, Text-to-3D, 3D Animation, Topology, Rigging, Mesh Quality, Production Pipeline, Benchmarking, Topological Integrity Score (TIS), Survey Dataset, Computer Graphics.