We present CD-NGP, which is a fast and scalable representation for 3D reconstruction and novel view synthesis in dynamic scenes. Inspired by continual learning, our method first segments input videos into multiple chunks, followed by training the model chunk by chunk, and finally, fuses features of the first branch and subsequent branches. Experiments on the prevailing DyNeRF dataset demonstrate that our proposed novel representation reaches a great balance between memory consumption, model size, training speed, and rendering quality. Specifically, our method consumes $85\%$ less training memory ($<14$GB) than offline methods and requires significantly lower streaming bandwidth ($<0.4$MB/frame) than other online alternatives.

翻译：我们提出CD-NGP，这是一种用于动态场景三维重建与新视角合成的快速可扩展表示方法。受持续学习启发，我们的方法首先将输入视频分割为多个片段，随后逐片段训练模型，最终融合首条分支与后续分支的特征。在主流DyNeRF数据集上的实验表明，我们提出的新型表示在内存消耗、模型大小、训练速度与渲染质量之间达到了良好平衡。具体而言，本方法的训练内存消耗较离线方法降低$85\%$（$<14$GB），且流式传输带宽（$<0.4$MB/帧）显著低于其他在线方案。