AI RESEARCH
Who Generated This 3D Asset? Learning Source Attribution for Generative 3D Models
arXiv CS.CV
•
ArXi:2605.18132v1 Announce Type: new Generative 3D models are deployed in gaming, robotics, and immersive creation, making source attribution critical: given a 3D asset, can we identify whether and which generative model created it? This problem faces two core challenges: dispersed attribution signals, where 3D fingerprints are distributed across multi-view, geometric, and frequency-domain cues; and realistic deployment constraints, where scarce labels, degraded prompts, and mixed real/synthetic assets undermine attribution reliability.