Zip-NeRF
Title | Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields |
---|---|
Author | Jonathan T. BarronBen MildenhallDor VerbinPratul P. SrinivasanPeter Hedman |
Conf/Jour | ICCV |
Year | 2023 |
Project | Zip-NeRF (jonbarron.info) |
Paper | Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields (readpaper.com) |
Zip-NeRF在抗混叠(包括NeRF从空间坐标到颜色和密度的学习映射的空间混叠,以及沿每条射线在线蒸馏过程中使用的损失函数的z-混叠)方面都取得了很好的效果,并且速度相比前作Mip-NeRF 360 提高了24X
mipNeRF 360+基于网格的模型(如Instant NGP)的技术
- 错误率下降8~77%,并且比Mip-NeRF360提速了24X
- 主要贡献:
- 多采样
- 预滤波
多采样:train左,test右


NeRO
9k 33 mins.
Title | NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Images |
---|---|
Author | Yuan Liu, Peng Wang, Cheng Lin, Xiaoxiao Long, Jiepeng Wang, Lingjie Liu, Taku Komura, Wenping Wang |
Conf/Jour | SIGGRAPH 2023 |
Year | 2023 |
Project | NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Images (liuyuan-pal.github.io) |
Paper | NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Images (readpaper.com) |
Reference
[PDF] NeRD: Neural Reflectance Decomposition From Image Collections
[PDF] SAMURAI: Shape And Material from Unconstrained Real-world Arbitrary Image collections
[PDF] Relighting4D: Neural Relightable Human from Videos
[PDF] Neural 3D Scene Reconstruction with the Manhattan-world Assumption
[PDF] NeROIC: Neural Rendering of Objects from Online Image Collections
对金属反光材质的物体重建效果很好
提出了一种新的光表示方法,颜色由漫反射和镜面反射两部分组成,通过两个阶段的方法来实现
- Stage1:使用集成方向编码来近似光积分,使用shadow MLP对直接光和间接光进行model,学习到了表面几何形状
- Stage2:蒙特卡罗采样固定几何形状,重建更精确的表面BRDF和环境光
- $\mathbf{c}_{\mathrm{diffuse}}=\frac{1}{N_{d}}\sum_{i}^{N_{d}}(1-m)\mathrm{a}L(\omega_{i}),$
- $\mathbf{c}_{\mathrm{specular}}=\frac{1}{N_{s}}\sum_{i}^{N_{s}}\frac{FG(\omega_{0}\cdot\mathbf{h})}{(\mathbf{n}\cdot\mathbf{h})(\mathbf{n}\cdot\omega_{\mathbf{0}})}L(\omega_{i}),$
Tri-MipRF
Title | Tri-MipRF: Tri-Mip Representation for Efficient Anti-Aliasing Neural Radiance Fields |
---|---|
Author | Wenbo Hu Yuling Wang |
Conf/Jour | ICCV |
Year | 2023 |
Project | Tri-MipRF: Tri-Mip Representation for Efficient Anti-Aliasing Neural Radiance Fields (wbhu.github.io) |
Paper | Tri-MipRF: Tri-Mip Representation for Efficient Anti-Aliasing Neural Radiance Fields (readpaper.com) |
2023.7.26 SOTA
like TensoRF: Tensorial Radiance Fields (apchenstu.github.io)+ Mip-NeRF + NGP
类似Mip-NeRF中的采样锥形方法,但是Tri-MipRF使用了与圆锥相切的采样球S=(x,r),代替Mip-NeRF中的多元高斯圆锥体
- 采样球的半径通过像素圆盘半径$\dot r$(由像素大小in world Coordinate),焦距f和$t_i$确定
类似TensoRF中的分解方法,将空间采样球分解到三个平面上,编码类似NGP中的HashGrid 使用2D平面来存取特征值,构建一个base level:$M^{L_{0}}$,通过downscaling来获得其他level的2D grid平面。
- 通过base level中interest space的AABB求出$\ddot r$,并联合采样球半径r得到采样球在平面投影的level,根据此level和投影到平面上的二维坐标,在相邻两level $\mathcal{M}_{XY}^{\lfloor l\rfloor}$和$\mathcal{M}_{XY}^{\lceil l\rceil}$的2D grid中采用3线性插值得到采样球的特征值,最后三个分解平面的特征值cat起来作为MLP的一个输入
一种更好的渲染视图方法:Hybrid Volume-Surface Rendering
- 通过在密度场中marching cubes和网格抽取来获得代理网格,粗略确定相机原点到物体表面的距离
- 对代理网格进行有效栅格化,以获得圆锥体中轴线表面上的命中点,然后我们在距圆锥体中轴线命中点∆t距离内均匀采样球体,这产生2∆t采样间隔。
- 优点:可以减少需要采样点的数量,且不会影响渲染出来图片的质量
优点:
- fine-grained details in close-up views
- and free of aliasing in distant views
- 5 minute and smaller model parameters
缺点:
- 需要使用multi-view segmentation methods将In-the-wildIn数据集中感兴趣的物体提取出来
- 即需要mask
- 需要使用multi-view segmentation methods将In-the-wildIn数据集中感兴趣的物体提取出来
Mip-NeRF 360
Title | Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields |
---|---|
Author | Jonathan T. Barron Ben Mildenhall Dor Verbin Pratul P. Srinivasan Peter Hedman |
Conf/Jour | CVPR 2022 (Oral Presentation) |
Year | 2022 |
Project | mip-NeRF 360 (jonbarron.info) |
Paper | Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields (readpaper.com) |
- novel Kalman-like scene parameterization:将场景参数化,将单位球外背景采样的截头锥参数化到r=2的球体内,单位球内的截头锥不受影响
- efficient proposal-based coarse-to-fine distillation framework:一个提议网络用来获取权重,用来进行精采样,再通过精采样的点根据NeRF 的MLP得到密度和颜色值
- regularizer designed for mipNeRF ray intervals:可以有效消除floaters(体积密集空间中不相连的小区域)和背景塌陷(远处的表面被错误地模拟成靠近相机的密集内容的半透明云)
$\begin{gathered}\mathcal{L}_{\mathrm{dist}}(\mathbf{s},\mathbf{w}) =\sum_{i,j}w_iw_j\left|\frac{s_i+s_{i+1}}{2}-\frac{s_j+s_{j+1}}{2}\right| \+\frac13\sum_iw_i^2(s_{i+1}-s_i) \end{gathered}$
Mip-NeRF
Title | Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields |
---|---|
Author | Jonathan T. Barron and Ben Mildenhall and Matthew Tancik and Peter Hedman and Ricardo Martin-Brualla and Pratul P. Srinivasan |
Conf/Jour | 2021 IEEE/CVF International Conference on Computer Vision (ICCV) |
Year | 2021 |
Project | google/mipnerf (github.com) |
Paper | Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields (readpaper.com) |
- 一种新的采样方式:锥体采样conical frustums截头圆锥体
- 基于PE提出了IPE,可以平滑地编码空间体积的大小和形状
- 将NeRF的粗精采样MLP合并为一个MLP
IPE:当锥体区域较宽(正态分布很宽)时,会将高频的信息积分为0;当区域较窄时,保持原来的PEncoding
NeRF++
Title | NeRF++: Analyzing and Improving Neural Radiance Fields |
---|---|
Author | Kai Zhang, Gernot Riegler, Noah Snavely, Vladlen Koltun |
Conf/Jour | arXiv: Computer Vision and Pattern Recognition |
Year | 2020 |
Project | Kai-46/nerfplusplus: improves over nerf in 360 capture of unbounded scenes (github.com) |
Paper | NeRF++: Analyzing and Improving Neural Radiance Fields. (readpaper.com) arxiv.org/pdf/2010.07492 |
创新:一种前背景分离的方法
挑战:
- First, the training and testing of NeRF and NeRF++ on a single large-scale scene is quite time-consuming and memory-intensive —> NGP解决了耗时
- Second, small camera calibration errors may impede阻碍 photorealistic synthesis. Robust loss functions, such as the contextual loss (Mechrez et al., 2018), could be applied.
- Third, photometric effects such as auto-exposure and vignetting渐晕 can also be taken into account to increase image fidelity. This line of investigation is related to the lighting changes addressed in the orthogonal work of Martin-Brualla et al. (2020).
NeuDA
Title | NeuDA: Neural Deformable Anchor for High-Fidelity Implicit Surface Reconstruction |
---|---|
Author | Bowen Cai ,Jinchi Huang, Rongfei Jia ,Chengfei Lv, Huan Fu* |
Conf/Jour | CVPR |
Year | 2023 |
Project | NeuDA (3d-front-future.github.io) |
Paper | NeuDA: Neural Deformable Anchor for High-Fidelity Implicit Surface Reconstruction (readpaper.com) |
NeuDA变形后的grid距离Surface更近一些,即可以使采样点插值时更多依赖于表面,即渲染时也会更多地考虑到3D空间相邻的信息
创新:Deformable Anchors、HPE、$\mathcal{L}_{norm}$
- 改进了NGP中的grid表示,8个顶点存储feature—>存储锚点位置,锚点位置经过PE后输入进SDF网络
SparseNeuS
7.1k 26 mins.
Title | SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse Views |
---|---|
Author | Xiaoxiao Long Cheng Lin Peng Wang Taku Komura Wenping Wang |
Conf/Jour | ECCV |
Year | 2022 |
Project | SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse Views (xxlong.site) |
Paper | SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse views (readpaper.com) |
从仅2~3张的稀疏输入中重建表面
- 首先,我们提出了一个多层几何推理框架,以粗到细的方式恢复表面。
- 其次,我们采用了一种多尺度颜色混合方案,该方案联合评估局部和背景亮度一致性,以获得更可靠的颜色预测。
- 第三,采用一致性感知的微调方案,控制遮挡和图像噪声引起的不一致区域,得到准确、干净的重建。
PermutoSDF
Title | PermutoSDF: Fast Multi-View Reconstruction with Implicit Surfaces using Permutohedral Lattices |
---|---|
Author | Radu Alexandru Rosu, Sven Behnke |
Conf/Jour | CVPR |
Year | 2023 |
Project | PermutoSDF (radualexandru.github.io) |
Paper | PermutoSDF: Fast Multi-View Reconstruction with Implicit Surfaces using Permutohedral Lattices (readpaper.com) |
创新:用permutohedral lattice替换voxel hash encoding
simplex,3D中的单纯形就是正四面体
几何细节光滑,通过曲率损失来实现
- 带Lipschitz常数的颜色MLP来训练,使得高频颜色与高频几何特征相匹配
- ref : [PDF] Learning Smooth Neural Functions via Lipschitz Regularization-论文阅读讨论-ReadPaper
- $y=\sigma(\widehat{W}_ix+b_i),\quad\widehat{W}_i=m\left(W_i,\text{softplus}\left(k_i\right)\right)$
Neuralangelo
Title | Neuralangelo: High-Fidelity Neural Surface Reconstruction |
---|---|
Author | Zhaoshuo LiThomas MüllerAlex EvansRussell H. TaylorMathias UnberathMing-Yu LiuChen-Hsuan Lin |
Conf/Jour | IEEE Conference on Computer Vision and Pattern Recognition (CVPR) |
Year | 2023 |
Project | Neuralangelo: High-Fidelity Neural Surface Reconstruction (nvidia.com) |
Paper | Neuralangelo: High-Fidelity Neural Surface Reconstruction (readpaper.com) |
创新:新的计算梯度的方法——数值梯度、粗到精地逐步优化——数值梯度的补偿$\epsilon$,粗网格先激活,当$\epsilon$减小到精网格的空间大小时,逐步激活精网格
SR Issue: Current methods struggle to recover detailed structures of real-world scenes
To address : present Neuralangelo (combines the representation power of multi-resolution 3D hash grids with neural surface rendering)
- numerical gradients for computing higher-order derivatives as a smoothing operation
- coarse-to-fine optimization on the hash grids controlling different levels of details
even wo auxiliary inputs such as depth , Neuralangelo can effectively recover dense 3D surface structures from multi-view images with fidelity 保真 significantly surpassing previous methods, enabling detailed large-scale scene reconstruction from RGB video captures.
our future work to explore a more efficient sampling strategy to accelerate the training process.
NerfAcc
Title | NerfAcc: Efficient Sampling Accelerates NeRFs |
---|---|
Author | Li, Ruilong and Gao, Hang and Tancik, Matthew and Kanazawa, Angjoo |
Conf/Jour | arXiv preprint arXiv:2305.04966 |
Year | 2023 |
Project | NerfAcc Documentation — nerfacc 0.5.3 documentation |
Paper | NerfAcc: Efficient Sampling Accelerates NeRFs (readpaper.com) |
一种可以加速NeRF的高效采样策略
NerfAcc = Instant-NGP的Occupancy Grid + Mip-NeRF 360的Proposal Network
pip install nerfacc
Instant-NSR代码理解
对Instant-NSR代码的理解
基于Instant-nsr-pl创建项目
本项目yq010105/NeRF-Mine (github.com)基于Instant-nsr-pl(NSR,NGP,PytorchLightning)代码构建
- 保留 omegaconf、nerfacc、Mip-nerf_loss,类似文件结构
- 去除 pytorch-lightning 框架,使用 pytorch
NeRF 主要部分:
- 神经网络结构 —> 训练出来模型,即 3D 模型的隐式表达
- 网络类型一般为 MLP,相当于训练一个函数,输入采样点的位置,可以输出该点的信息(eg: density, sdf, color…)
- 采样方式:沿着光线进行采样获取采样点
- 位置编码:对采样点的位置 xyz 和方向 dir 进行编码,使得 MLP 的输入为高频的信息
- 数学相关:光线的生成、坐标变换、体渲染公式、BRDF……
- 体渲染函数:
- NeRF:$\mathrm{C}(r)=\int_{\mathrm{t}_{\mathrm{n}}}^{\mathrm{t}_{\mathrm{f}}} \mathrm{T}(\mathrm{t}) \sigma(\mathrm{r}(\mathrm{t})) \mathrm{c}(\mathrm{r}(\mathrm{t}), \mathrm{d}) \mathrm{dt} =\sum_{i=1}^{N} T_{i}\left(1-\exp \left(-\sigma_{i} \delta_{i}\right)\right) \mathbf{c}_{i}$
- 不透明度$\sigma$,累计透光率 —> 权重
- 颜色值
- Neus:$C(\mathbf{o},\mathbf{v})=\int_{0}^{+\infty}w(t)c(\mathbf{p}(t),\mathbf{v})\mathrm{d}t$
- sdf, dirs, gradients, invs —> $\alpha$ —> 权重
- 颜色值
- NeRO:$\mathbf{c}(\omega_{0})=\mathbf{c}_{\mathrm{diffuse}}+\mathbf{c}_{\mathrm{specular}} =\int_{\Omega}(1-m)\frac{\mathbf{a}}{\pi}L(\omega_{i})(\omega_{i}\cdot\mathbf{n})d\omega_{i} + \int_{\Omega}\frac{DFG}{4(\omega_{i}\cdot\mathbf{n})(\omega_{0}\cdot\mathbf{n})}L(\omega_{i})(\omega_{i}\cdot\mathbf{n})d\omega_{i}$
- 漫反射颜色:Light(直射光),金属度 m、反照率 a
- 镜面反射颜色:Light(直射光+间接光),金属度 m、反照率 a、粗糙度$\rho$ ,碰撞概率 occ_prob,间接光碰撞 human 的 human_light
- 详情见NeRO Code
- NeRF:$\mathrm{C}(r)=\int_{\mathrm{t}_{\mathrm{n}}}^{\mathrm{t}_{\mathrm{f}}} \mathrm{T}(\mathrm{t}) \sigma(\mathrm{r}(\mathrm{t})) \mathrm{c}(\mathrm{r}(\mathrm{t}), \mathrm{d}) \mathrm{dt} =\sum_{i=1}^{N} T_{i}\left(1-\exp \left(-\sigma_{i} \delta_{i}\right)\right) \mathbf{c}_{i}$
- 隐式模型导出(.stl、.obj、.ply 等)显式模型(Marching Cube):利用 trimesh,torchmcubes,mcubes 等库
- 根据 sdf 和 threshold,获取物体表面的 vertices 和 faces(如需还要生成 vertices 对应的 colors)。
- 然后根据 vertices、faces 和 colors,由 trimesh 生成 mesh 并导出模型为 obj 等格式
Future:
- [ ] 消除颜色 or 纹理与几何的歧义,Neus(X—>MLP—>SDF)的方法会将物体的纹理建模到物体的几何中
- [x] 只关注前景物体的建模,可以结合 SAM 将图片中的 interest object 分割出来: Rembg分割后效果也不好
Instant-NSR
Title | Human Performance Modeling and Rendering via Neural Animated Mesh |
---|---|
Author | Fuqiang Zhao, Yuheng Jiang, Kaixin Yao, Jiakai Zhang, Liao Wang, Haizhao Dai, Yuhui Zhong, Yingliang Zhang Minye Wu, Lan Xu, Jingyi Yu |
Conf/Jour | SIGGRAPH Asia 2022 |
Year | 2022 |
Project | Human Performance Modeling and Rendering via Neural Animated Mesh (zhaofuq.github.io) |
Paper | Human Performance Modeling and Rendering via Neural Animated Mesh (readpaper.com) |
可以理解为对Neus使用多分辨率哈希编码进行加速
- 使用TSDF代替SDF
- 有限差分函数计算SDF的梯度,在tiny-CUDAnn并未集成,公开了自己的CUDAC++代码
不足:
- 数据集需要手动mask
InstantNGP环境配置和tiny-cuda-nn用法
tiny-cuda-nn在python中的用法:NVlabs/tiny-cuda-nn: Lightning fast C++/CUDA neural network framework (github.com)
InstantNGP环境配置和使用,由于需要使用GUI,且笔记本GPU配置太低,因此没有具体训练的过程,只是进行了环境的配置。
Instant-nsr-pl的代码理解
Instant Neus的代码理解
参考了:
- ngp_pl: Great Instant-NGP implementation in PyTorch-Lightning! Background model and GUI supported.
- Instant-NSR: NeuS implementation using multiresolution hash encoding.