用少量视角图实现快速高精度3D重建，适合实时应用。
Few TensoRF: Enhance the Few-shot on Tensorial Radiance Fields
- 结合张量表示与频率正则化，提升稀疏视角下的稳定性。
- 在合成数据上PSNR达24.52 dB，仅需10-15分钟训练时间。
- 八张图即可完成人体重建，性能媲美全量数据方法。
本文提出Few TensoRF，一种融合张量辐射场（TensorRF）高效张量表示与自由神经辐射场（FreeNeRF）频率驱动少样本正则化的3D重建框架。通过引入频率掩码和遮挡掩码，显著提升稀疏视角输入下的重建稳定性和质量。在Synthesis NeRF基准测试中，该方法将平均PSNR从21.45 dB提升至23.70 dB，微调版本达到24.52 dB，同时保持约10-15分钟的快速训练时间。在THuman 2.0数据集上，仅用八张输入图像即实现27.37-34.00 dB的重建质量，展现出在人体重建等复杂场景中的强竞争力。结果表明Few TensoRF是一种高效且数据高效的实时3D重建方案。
原文摘要 · Abstract (English)
This paper presents Few TensoRF, a 3D reconstruction framework that combines TensorRF's efficient tensor based representation with FreeNeRF's frequency driven few shot regularization. Using TensorRF to significantly accelerate rendering speed and introducing frequency and occlusion masks, the method improves stability and reconstruction quality under sparse input views. Experiments on the Synthesis NeRF benchmark show that Few TensoRF method improves the average PSNR from 21.45 dB (TensorRF) to 23.70 dB, with the fine tuned version reaching 24.52 dB, while maintaining TensorRF's fast \(\approx10-15\) minute training time. Experiments on the THuman 2.0 dataset further demonstrate competitive performance in human body reconstruction, achieving 27.37 - 34.00 dB with only eight input images. These results highlight Few TensoRF as an efficient and data effective solution for real-time 3D reconstruction across diverse scenes.
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。