RANRAC: Robust Neural Scene Representations via Random Ray Consensus

arXiv:2312.09780v2 Announce Type: replace
Abstract: Learning-based scene representations such as neural radiance fields or light field networks, that rely on fitting a scene model to image observations, commonly encounter challenges in the presence of inconsistencies within the images caused by occlusions, inaccurately estimated camera parameters or effects like lens flare. To address this challenge, we introduce RANdom RAy Consensus (RANRAC), an efficient approach to eliminate the effect of inconsistent data, thereby taking inspiration from classical RANSAC based outlier detection for …

arxiv consensus cs.cv random ray robust type via