Towards Realistic 3D Emission Materials: Dataset, Baseline, and Evaluation for Emission Texture Generation

2026-04-13

AI Summary

Existing 3D texture generation methods are largely confined to non-emissive physically based rendering (PBR) materials and struggle to reproduce realistic LED emissive effects commonly seen in styles such as cyberpunk. To address this limitation, this work introduces the novel task of 3D emissive texture generation, presents Objaverse-Emission—a large-scale dataset comprising 40,000 high-quality emissive materials—and proposes EmissionGen as a baseline model alongside a comprehensive multi-dimensional evaluation framework. Experimental results demonstrate that the proposed approach can faithfully reconstruct emissive appearances on 3D objects from reference images, achieving high visual fidelity and confirming its practical viability and potential for industrial applications.

Technology Category

• Computer Vision: 3D Computer Vision
• Natural Language Processing: Generation
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Web Mining and Content Analysis: Web data generation and simulation
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

3D texture generation is receiving increasing attention, as it enables the creation of realistic and aesthetic texture materials for untextured 3D meshes. However, existing 3D texture generation methods are limited to producing only a few types of non-emissive PBR materials (e.g., albedo, metallic maps and roughness maps), making them difficult to replicate highly popular styles, such as cyberpunk, failing to achieve effects like realistic LED emissions. To address this limitation, we propose a novel task, emission texture generation, which enables the synthesized 3D objects to faithfully reproduce the emission materials from input reference images. Our key contributions include: first, We construct the Objaverse-Emission dataset, the first dataset that contains 40k 3D assets with high-quality emission materials. Second, we propose EmissionGen, a novel baseline for the emission texture generation task. Third, we define detailed evaluation metrics for the emission texture generation task. Our results demonstrate significant potential for future industrial applications. Dataset will be available at https://github.com/yx345kw/EmissionGen.

Problem

• emission texture generation
• 3D texture generation
• PBR materials
• realistic LED emissions
• cyberpunk style

Innovation

• emission texture generation
• 3D material synthesis
• Objaverse-Emission dataset
• EmissionGen
• PBR materials