From NeRFLiX to NeRFLiX++: A General NeRF-Agnostic Restorer Paradigm
This addresses a key limitation in NeRF-based 3D scene reconstruction for computer vision applications, representing a significant incremental improvement over existing restoration methods.
The paper tackles the problem of rendering artifacts (noise, blur) in Neural Radiance Fields (NeRF) for novel view synthesis, proposing NeRFLiX++ as a general NeRF-agnostic restorer paradigm that achieves photo-realistic ultra-high-resolution outputs from low-quality NeRF-rendered views.
Neural radiance fields (NeRF) have shown great success in novel view synthesis. However, recovering high-quality details from real-world scenes is still challenging for the existing NeRF-based approaches, due to the potential imperfect calibration information and scene representation inaccuracy. Even with high-quality training frames, the synthetic novel views produced by NeRF models still suffer from notable rendering artifacts, such as noise and blur. To address this, we propose NeRFLiX, a general NeRF-agnostic restorer paradigm that learns a degradation-driven inter-viewpoint mixer. Specially, we design a NeRF-style degradation modeling approach and construct large-scale training data, enabling the possibility of effectively removing NeRF-native rendering artifacts for deep neural networks. Moreover, beyond the degradation removal, we propose an inter-viewpoint aggregation framework that fuses highly related high-quality training images, pushing the performance of cutting-edge NeRF models to entirely new levels and producing highly photo-realistic synthetic views. Based on this paradigm, we further present NeRFLiX++ with a stronger two-stage NeRF degradation simulator and a faster inter-viewpoint mixer, achieving superior performance with significantly improved computational efficiency. Notably, NeRFLiX++ is capable of restoring photo-realistic ultra-high-resolution outputs from noisy low-resolution NeRF-rendered views. Extensive experiments demonstrate the excellent restoration ability of NeRFLiX++ on various novel view synthesis benchmarks.