Neural Radiance Field (NeRF) has emerged as a compelling method to represent 3D objects and scenes for photo-realistic rendering. However, its implicit representation causes difficulty in manipulating the models like the explicit mesh representation. Several recent advances in NeRF manipulation are usually restricted by a shared renderer network, or suffer from large model size. To circumvent the hurdle, in this paper, we present an explicit neural field representation that enables efficient and convenient manipulation of models. To achieve this goal, we learn a hybrid tensor rank decomposition of the scene without neural networks. Motivated by the low-rank approximation property of the SVD algorithm, we propose a rank-residual learning strategy to encourage the preservation of primary information in lower ranks. The model size can then be dynamically adjusted by rank truncation to control the levels of detail, achieving near-optimal compression without extra optimization. Furthermore, different models can be arbitrarily transformed and composed into one scene by concatenating along the rank dimension. The growth of storage cost can also be mitigated by compressing the unimportant objects in the composed scene. We demonstrate that our method is able to achieve comparable rendering quality to state-of-the-art methods, while enabling extra capability of compression and composition. Code will be made available at \url{https://github.com/ashawkey/CCNeRF}.
翻译:神经辐射场( NERF) 已成为代表 3D 对象和场景的令人信服的方法, 代表了 3D 对象和场景, 以便进行摄影现实化的拍摄。 但是, 其隐含的表达方式在调控模型( 如明显的网格代表) 方面造成了困难。 最近NERF 操纵的一些进展通常受到共享的铸造者网络的限制, 或受到大型体大小的影响。 为了绕过障碍, 我们在本文件中展示了一个明确的神经外观代表方式, 从而能够高效和方便地操纵模型。 为了实现这一目标, 我们学习了一种混合式的 Exor 级分解场景, 但没有神经网络。 受 SVD 算法低端近似属性的驱动, 我们提出了一个级再生化学习策略, 以鼓励在较低级别上保存初级信息。 然后, 模型的大小可以动态地调整, 通过分级调整来控制详细程度, 实现近于最优化的压缩。 此外, 不同的模型可以任意转换, 并组成一个场景相匹配的场景层。 我们还能够实现可比较的代码质量。