Few TensoRF: Enhance the Few-shot on Tensorial Radiance Fields
It provides an efficient and data-effective solution for real-time 3D reconstruction across diverse scenes, though it is incremental as it builds on existing methods.
The paper tackles the problem of 3D reconstruction from sparse input views by combining TensorRF's efficient representation with FreeNeRF's few-shot regularization, improving average PSNR from 21.45 dB to 23.70 dB on a benchmark and achieving 27.37-34.00 dB with only eight images on a human dataset.
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.