RoGUENeRF: A Robust Geometry-Consistent Universal Enhancer for NeRF

arXiv:2403.11909v1 Announce Type: new
Abstract: Recent advances in neural rendering have enabled highly photorealistic 3D scene reconstruction and novel view synthesis. Despite this progress, current state-of-the-art methods struggle to reconstruct high frequency detail, due to factors such as a low-frequency bias of radiance fields and inaccurate camera calibration. One approach to mitigate this issue is to enhance images post-rendering. 2D enhancers can be pre-trained to recover some detail but are agnostic to scene geometry and do not easily generalize to …

abstract advances art arxiv bias consistent cs.cv current fields geometry low nerf neural rendering novel photorealistic progress rendering robust state struggle synthesis type universal view