1) Like NeRF, our rendering time is slow, and in fact, our runtime increases linearly when given more input views. Further, some methods (e.g. [28, 21]) can recover a mesh from the image enabling fast rendering and manipulation afterwards, while NeRF based representations cannot be converted to meshes very reliably. Improving NeRF’s efficiency is an important re-search question that can enable real-time applications.
2) As in the vanilla NeRF, we manually tune ray sampling bounds tn,tf and a scale for the positional encoding. Making NeRF-related methods scale-invariant is a crucial challenge. 3) While we have demonstrated our method on real data from the DTU dataset, we acknowledge that this dataset was captured under controlled settings and has matching camera poses across all scenes with limited viewpoints. Ultimately,our approach is bottlenecked by the availability of largescale wide baseline multi-view datasets, limiting the applicability to datasets such as ShapeNet and DTU. Learning a general prior for 360◦ scenes in-the-wild is an exciting direction for future work
参考文献:
【1】Ben Mildenhall, Pratul P. Srinivasan, Matthew Tancik,Jonathan T. Barron, Ravi Ramamoorthi, and Ren Ng. Nerf: Representing scenes as neural radiance fields for view synthesis. In Eur. Conf. Comput. Vis., 2020
【2】Daeyun Shin, Charless Fowlkes, and Derek Hoiem. Pixels, voxels, and views: A study of shape representations for single view 3d object shape prediction. In IEEE Conf. Comput.Vis. Pattern Recog., 2018.
很显然,绝对位置编码的一个最朴素方案是不特意去设计什么,而是直接将位置编码当作可训练参数,比如最大长度为512,编码维度为768,那么就初始化一个512×768的矩阵作为位置向量,让它随着训练过程更新。现在的BERT、GPT等模型所用的就是这种位置编码,事实上它还可以追溯得更早,比如2017年Facebook的《Convolutional Sequence to Sequence Learning》就已经用到了它。
结合了NeRF和Multiplane Image(MPI),提出了一种新的三维空间表达方式MINE。MINE利用了NeRF的思路,将MPI扩展成了连续深度的形式。输入单张RGB图片,我们的方法会对source相机的视锥(frustum)做稠密的三维重建,同时对被遮挡的部分做inpainting,预测出相机视锥的三维表达。利用这个三维表达,给出target相机相对于source相机的在三维空间中的相对位置和角度变化(rotation and translation),我们可以方便且高效地渲染出在目标相机视图下的RGB图片以及深度图。
[1]. Tinghui Zhou, Richard Tucker, John Flynn, Graham Fyffe, Noah Snavely. Stereo Magnification: Learning View Synthesis using Multiplane Images. (SIGGRAPH 2018)
[2]. Ben Mildenhall, Pratul P. Srinivasan, Rodrigo Ortiz-Cayon, Nima Khademi Kalantari, Ravi Ramamoorthi, Ren Ng, Abhishek Kar. Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelines. (SIGGRAPH 2019)
[3]. Richard Tucker, Noah Snavely. Single-View View Synthesis with Multiplane Images. (CVPR 2020)
最近非常火的ChatGPT和今年年初公布的[1]是一对姐妹模型,是在GPT-4之前发布的预热模型,有时候也被叫做GPT3.5。ChatGPT和InstructGPT在模型结构,训练方式上都完全一致,即都使用了指示学习(Instruction Learning)和人工反馈的强化学习(Reinforcement Learning from Human Feedback,RLHF)来指导模型的训练,它们不同的仅仅是采集数据的方式上有所差异。所以要搞懂ChatGPT,我们必须要先读懂InstructGPT。
指示学习是谷歌Deepmind的Quoc V.Le团队在2021年的一篇名为《Finetuned Language Models Are Zero-Shot Learners》[5]文章中提出的思想。指示学习和提示学习的目的都是去挖掘语言模型本身具备的知识。不同的是Prompt是激发语言模型的补全能力,例如根据上半句生成下半句,或是完形填空等。Instruct是激发语言模型的理解能力,它通过给出更明显的指令,让模型去做出正确的行动。我们可以通过下面的例子来理解这两个不同的学习方式:
^Ouyang, Long, et al. “Training language models to follow instructions with human feedback.” *arXiv preprint arXiv:2203.02155* (2022). https://arxiv.org/pdf/2203.02155.pdf
^Wei, Jason, et al. “Finetuned language models are zero-shot learners.” *arXiv preprint arXiv:2109.01652* (2021). https://arxiv.org/pdf/2109.01652.pdf
^Christiano, Paul F., et al. “Deep reinforcement learning from human preferences.” *Advances in neural information processing systems* 30 (2017). https://arxiv.org/pdf/1706.03741.pdf