Make-it-Real: Unleashing Large Multimodal Model for Painting 3D Objects with Realistic Materials

TL;DR

This paper introduces Make-it-Real, a method leveraging GPT-4V to automatically recognize, describe, and apply realistic materials to 3D objects, significantly improving visual authenticity and streamlining 3D asset creation.

Contribution

It presents a novel use of multimodal large language models for automatic material recognition and application in 3D modeling, enhancing realism and workflow efficiency.

Findings

GPT-4V effectively recognizes and describes materials.

Materials are accurately aligned with 3D object components.

Enhanced visual authenticity of 3D assets through automated material application.

Abstract

Physically realistic materials are pivotal in augmenting the realism of 3D assets across various applications and lighting conditions. However, existing 3D assets and generative models often lack authentic material properties. Manual assignment of materials using graphic software is a tedious and time-consuming task. In this paper, we exploit advancements in Multimodal Large Language Models (MLLMs), particularly GPT-4V, to present a novel approach, Make-it-Real: 1) We demonstrate that GPT-4V can effectively recognize and describe materials, allowing the construction of a detailed material library. 2) Utilizing a combination of visual cues and hierarchical text prompts, GPT-4V precisely identifies and aligns materials with the corresponding components of 3D objects. 3) The correctly matched materials are then meticulously applied as reference for the new SVBRDF material generation according to the original albedo map, significantly enhancing their visual authenticity. Make-it-Real offers a streamlined integration into the 3D content creation workflow, showcasing its utility as an essential tool for developers of 3D assets.