神经辐射场码本
Neural Radiance Field Codebooks
AI总结：
本研究提出神经辐射场码本（NRC），通过新视角重建学习以物体为中心的可迁移组合式表征，在物体导航、无监督分割、深度排序等任务上均取得优于现有方法的性能。
摘要：
世界的组合式表征是实现高层场景理解与高效迁移至下游任务的一条有前景的路径。针对复杂场景和任务学习此类表征仍是一个开放挑战。为实现这一目标，我们提出神经辐射场码本（Neural Radiance Field Codebooks, NRC），这是一种通过新视角重建学习以物体为中心的表征的可扩展方法。NRC 利用物体码本字典，通过体渲染器解码，实现从新视角重建场景，从而能够发现跨场景的可重复视觉与几何模式，这些模式可迁移至下游任务。我们的实验表明，NRC 表征在 THOR 环境中的物体导航任务上迁移效果良好，成功率较 2D 和 3D 表征学习方法高出 3.1%；在更复杂的合成场景（THOR）和真实场景（NYU Depth）的无监督分割任务上，性能优于现有方法（相对提升 29%）；此外，NRC 在 THOR 的深度排序任务上，准确率提升了 5.5%。
英文摘要：
Compositional representations of the world are a promising step towards enabling high-level scene understanding and efficient transfer to downstream tasks. Learning such representations for complex scenes and tasks remains an open challenge. Towards this goal, we introduce Neural Radiance Field Codebooks (NRC), a scalable method for learning object-centric representations through novel view reconstruction. NRC learns to reconstruct scenes from novel views using a dictionary of object codes which are decoded through a volumetric renderer. This enables the discovery of reoccurring visual and geometric patterns across scenes which are transferable to downstream tasks. We show that NRC representations transfer well to object navigation in THOR, outperforming 2D and 3D representation learning methods by 3.1% success rate. We demonstrate that our approach is able to perform unsupervised segmentation for more complex synthetic (THOR) and real scenes (NYU Depth) better than prior methods (29% relative improvement). Finally, we show that NRC improves on the task of depth ordering by 5.5% accuracy in THOR.
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。
