基于隐式场景表示的现场场景标注与理解
In-Place Scene Labelling and Understanding with Implicit Scene Representation
摘要：
语义标记与几何和辐射重建高度相关，因为具有相似形状和外观的场景实体更可能来自相似的类。最近的隐式神经重建技术是有吸引力的，因为它们不需要先前的训练数据，但同样的完全自监督的方法是不可能的语义，因为标签是人类定义的属性。我们扩展了神经辐射场（NeRF），共同编码语义与外观和几何形状，使完整和准确的2D语义标签可以实现使用少量的特定于场景的就地注释。NeRF内在的多视图一致性和平滑性通过使稀疏标签能够有效传播而使语义受益。我们展示了这种方法的好处时，标签是稀疏或非常嘈杂的房间规模的场景。我们展示了它在各种有趣的应用，如一个有效的场景标记工具，新的语义视图合成，标签去噪，超分辨率，标签插值和多视图语义标签融合视觉语义映射系统中的有利性能。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
