期刊
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
卷 -, 期 -, 页码 15818-15827出版社
IEEE
DOI: 10.1109/ICCV48922.2021.01554
关键词
-
资金
- Dyson Technology Ltd.
- China Scholarship Council-Imperial Scholarship
This study introduces a neural network-based approach that can encode appearance, geometry, and semantics simultaneously, achieving accurate semantic labels with a small amount of in-place annotation data, addressing the issues of sparse and noisy semantic labels.
Semantic labelling is highly correlated with geometry and radiance reconstruction, as scene entities with similar shape and appearance are more likely to come from similar classes. Recent implicit neural reconstruction techniques are appealing as they do not require prior training data, but the same fully self-supervised approach is not possible for semantics because labels are human-defined properties. We extend neural radiance fields (NeRF) to jointly encode semantics with appearance and geometry, so that complete and accurate 2D semantic labels can be achieved using a small amount of in-place annotations specific to the scene. The intrinsic multi-view consistency and smoothness of NeRF benefit semantics by enabling sparse labels to efficiently propagate. We show the benefit of this approach when labels are either sparse or very noisy in room-scale scenes. We demonstrate its advantageous properties in various interesting applications such as an efficient scene labelling tool, novel semantic view synthesis, label denoising, super-resolution, label interpolation and multi-view semantic label fusion in visual semantic mapping systems.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据