根据场景复杂度动态调整模型参数位宽，提升渲染效率。
Content-Aware Radiance Fields: Aligning Model Complexity with Scene Intricacy Through Learned Bitwidth Quantization
- 通过可学习的位宽量化，让模型参数随场景复杂度自适应变化。
- 在保持高质量渲染的同时，计算量显著降低。
- 适合需要高效部署的3D重建与实时渲染场景。
近期流行的辐射场模型（如NeRF、Instant-NGP和3D高斯泼溅）通过为每个独立场景单独训练模型来表示三维内容。这种按场景训练的独特性使得复杂场景需要更高表达能力的模型，而简单场景则无需。本文提出内容感知辐射场，通过对抗式内容感知量化（A-CAQ）将模型复杂度与场景细节对齐。具体地，使参数的位宽可微且可训练，以适配特定场景特征与需求。该框架在Instant-NGP（一种知名NeRF变体）上评估，使用多个数据集验证。实验表明，在保持必要重建与渲染质量的同时，显著降低计算复杂度，有利于辐射场模型的实际部署。代码已公开于https://github.com/WeihangLiu2024/Content_Aware_NeRF。
原文摘要 · Abstract (English)
The recent popular radiance field models, exemplified by Neural Radiance Fields (NeRF), Instant-NGP and 3D Gaussian Splatting, are designed to represent 3D content by that training models for each individual scene. This unique characteristic of scene representation and per-scene training distinguishes radiance field models from other neural models, because complex scenes necessitate models with higher representational capacity and vice versa. In this paper, we propose content-aware radiance fields, aligning the model complexity with the scene intricacies through Adversarial Content-Aware Quantization (A-CAQ). Specifically, we make the bitwidth of parameters differentiable and trainable, tailored to the unique characteristics of specific scenes and requirements. The proposed framework has been assessed on Instant-NGP, a well-known NeRF variant and evaluated using various datasets. Experimental results demonstrate a notable reduction in computational complexity, while preserving the requisite reconstruction and rendering quality, making it beneficial for practical deployment of radiance fields models. Codes are available at https://github.com/WeihangLiu2024/Content_Aware_NeRF.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。