Exploring Active Learning for Label-Efficient Training of Semantic Neural Radiance Field
This work addresses the problem of expensive pixel-level labeling for researchers and practitioners in 3D scene understanding, offering an incremental improvement in efficiency.
The paper tackles the high annotation cost of training semantically-aware Neural Radiance Fields (NeRFs) by exploring active learning strategies, achieving over a 2x reduction in annotation cost compared to random sampling.
Neural Radiance Field (NeRF) models are implicit neural scene representation methods that offer unprecedented capabilities in novel view synthesis. Semantically-aware NeRFs not only capture the shape and radiance of a scene, but also encode semantic information of the scene. The training of semantically-aware NeRFs typically requires pixel-level class labels, which can be prohibitively expensive to collect. In this work, we explore active learning as a potential solution to alleviate the annotation burden. We investigate various design choices for active learning of semantically-aware NeRF, including selection granularity and selection strategies. We further propose a novel active learning strategy that takes into account 3D geometric constraints in sample selection. Our experiments demonstrate that active learning can effectively reduce the annotation cost of training semantically-aware NeRF, achieving more than 2X reduction in annotation cost compared to random sampling.