TriNeRFLet: A Wavelet Based Triplane NeRF Representation
This work addresses the performance limitations of triplane NeRF representations for 3D scene reconstruction, offering a solution that could benefit applications in computer vision and graphics, though it appears incremental as it builds upon existing triplane frameworks.
The authors tackled the problem of improving 3D recovery quality in triplane-based neural radiance fields (NeRF) by proposing TriNeRFLet, a wavelet-based multiscale representation that closes the performance gap and is competitive with state-of-the-art methods, and they also introduced a super-resolution technique combining a diffusion model with TriNeRFLet to enhance resolution.
In recent years, the neural radiance field (NeRF) model has gained popularity due to its ability to recover complex 3D scenes. Following its success, many approaches proposed different NeRF representations in order to further improve both runtime and performance. One such example is Triplane, in which NeRF is represented using three 2D feature planes. This enables easily using existing 2D neural networks in this framework, e.g., to generate the three planes. Despite its advantage, the triplane representation lagged behind in its 3D recovery quality compared to NeRF solutions. In this work, we propose TriNeRFLet, a 2D wavelet-based multiscale triplane representation for NeRF, which closes the 3D recovery performance gap and is competitive with current state-of-the-art methods. Building upon the triplane framework, we also propose a novel super-resolution (SR) technique that combines a diffusion model with TriNeRFLet for improving NeRF resolution.