New AI framework generates 3D dog models from single images

Researchers have developed CORGI, a new framework for creating 3D dog models from single images without requiring 3D supervision. The system uses a Canonical-Driven Orbital Generation (CDOG) strategy with LoRAs to normalize poses and create 360-degree views. It also incorporates a Consistency-aware Deformable 3DGS module that uses a D-SMAL prior and neural deformation fields to correct errors, and a self-supervised module for repairing structural distortions and adding detail. CORGI has demonstrated state-of-the-art performance in generating accurate, coherent, and animatable 3D dog assets. AI

IMPACT This framework could advance the creation of detailed 3D animal models for applications in animation, gaming, and virtual reality.

RANK_REASON The cluster contains a research paper detailing a new AI framework for 3D reconstruction. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• CORGI

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →