Neural Bloom: A Deep Learning Approach to Real-Time Lighting

2025-09-07

AI Summary

Traditional bloom effects rely on multi-pass Gaussian blurring and conditional branching for texture sampling, resulting in high computational overhead and difficulty meeting real-time rendering requirements at high frame rates. This paper introduces, for the first time, deep learning into bloom mask generation, proposing Neural Bloom Layer (NBL) and its lightweight variant FastNBL—end-to-end neural networks that replace conventional image-processing pipelines. Our approach eliminates explicit blurring operations and conditional logic, significantly improving inference efficiency. Evaluated across diverse 3D scenes, FastNBL achieves a 28% speedup over the optimal traditional method, while NBL achieves a 12% speedup—all without perceptible degradation in visual quality. This work establishes an efficient, learnable paradigm for post-processing effects in real-time rendering, enabling high-fidelity bloom with substantially reduced computational cost.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Learning on the Edge & Model Compression
• Natural Language Processing: Generation

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

We propose a novel method to generate bloom lighting effect in real time using neural networks. Our solution generate brightness mask from given 3D scene view up to 30% faster than state-of-the-art methods. The existing traditional techniques rely on multiple blur appliances and texture sampling, also very often have existing conditional branching in its implementation. These operations occupy big portion of the execution time. We solve this problem by proposing two neural network-based bloom lighting methods, Neural Bloom Lighting (NBL) and Fast Neural Bloom Lighting (FastNBL), focusing on their quality and performance. Both methods were tested on a variety of 3D scenes, with evaluations conducted on brightness mask accuracy and inference speed. The main contribution of this work is that both methods produce high-quality bloom effects while outperforming the standard state-of-the-art bloom implementation, with FastNBL being faster by 28% and NBL faster by 12%. These findings highlight that we can achieve realistic bloom lighting phenomena faster, moving us towards more realism in real-time environments in the future. This improvement saves computational resources, which is a major bottleneck in real-time rendering. Furthermore, it is crucial for sustaining immersion and ensuring smooth experiences in high FPS environments, while maintaining high-quality realism.

Problem

• Real-time bloom lighting generation using neural networks
• Faster brightness mask creation than traditional methods
• Reducing computational bottlenecks in real-time rendering

Innovation

• Neural networks for real-time bloom lighting
• 30% faster brightness mask generation
• Two methods: NBL and FastNBL