CS 148: Introduction to Computer Graphics and Imaging (stanford.edu)
PlankAssembly
| Title | PlankAssembly: Robust 3D Reconstruction from Three Orthographic Views with Learnt Shape Programs |
|---|---|
| Author | Wentao Hu Jia Zheng Zixin Zhang Xiaojun Yuan Jian Yin Zihan Zhou |
| Conf/Jour | ICCV |
| Year | 2023 |
| Project | PlankAssembly: Robust 3D Reconstruction from Three Orthographic Views with Learnt Shape Programs (manycore-research.github.io) |
| Paper | PlankAssembly: Robust 3D Reconstruction from Three Orthographic Views with Learnt Shape Programs (readpaper.com) |

贡献:
- 基于Transform的自注意力提出模型,用于将2D的三个orthographic的line drawing转化为3D模型,可以实现从图纸不完美的输入中生成正确的3D模型
- 输入的三个orthographic图纸被编码,输出的是3D模型程序的编码,最后解码后即3D模型对应的程序DSL
挑战:
- 应用于无法获得甚至不存在大规模CAD数据的领域,例如建筑物或复杂的机械设备
- 没有考虑图纸中的符号、图层等信息
A Critical Analysis of NeRF-Based 3D Reconstruction
| Title | A Critical Analysis of NeRF-Based 3D Reconstruction |
|---|---|
| Author | Fabio Remondino , Ali Karami , Ziyang Yan, Gabriele Mazzacca , Simone Rigon and Rongjun Qin |
| Conf/Jour | MDPI remote sensing |
| Year | 2023 |
| Project | A Critical Analysis of NeRF-Based 3D Reconstruction |
| Paper | A Critical Analysis of NeRF-Based 3D Reconstruction (readpaper.com) |

对比photogrammetry与NeRF在3D Reconstruction中的表现,提供数据集Github_NeRFBK
- photogrammetry(Colmap)
- 对无纹理物体重建效果很差(non-collaborative surfaces的3D测量),例如镜面反射物体
- 非协作表面: 反射、无纹理等
- 对无纹理物体重建效果很差(non-collaborative surfaces的3D测量),例如镜面反射物体
- NeRF(InstantNGP | NerfStudio | SDFstudio)
结论:
- 在传统摄影测量方法失败或产生嘈杂结果的情况下,例如无纹理、金属、高反射和透明物体,NeRF优于摄影测量
- 对于纹理良好和部分纹理的物体,摄影测量仍然表现更好
该研究为NeRF在不同现实场景中的适用性提供了有价值的见解,特别是在遗产和工业场景中,这些场景的表面可能特别具有挑战性,未来的研究可以探索NeRF和摄影测量的结合,以提高具有挑战性场景下三维重建的质量和效率
NeRFactor
11k 42 mins.
| Title | NeRFactor: Neural Factorization of Shape and Reflectance Under an Unknown Illumination |
|---|---|
| Author | Xiuming Zhang Pratul P. Srinivasan Boyang Deng Paul Debevec William T. Freeman Jonathan T. Barron |
| Conf/Jour | TOG 2021 (Proc. SIGGRAPH Asia) |
| Year | 2021 |
| Project | NeRFactor (xiuming.info) |
| Paper | NeRFactor: Neural Factorization of Shape and Reflectance Under an Unknown Illumination (readpaper.com) |

贡献:
- NeRFactor在未知光照条件下从图像中恢复物体形状和反射率
- 在没有任何监督的情况下,仅使用重渲染损失、简单的平滑先验和从真实世界BRDF测量中学习的数据驱动的BRDF先验,恢复了表面法线、光能见度、反照率和双向反射分布函数(BRDFs)的3D神经场
- 通过NeRFactor的分解,我们可以用点光或光探针图像重新照亮物体,从任意视点渲染图像,甚至编辑物体的反照率和BRDF
Ref-NeRF
7.6k 28 mins.
| Title | Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields |
|---|---|
| Author | Dor Verbin and Peter Hedman and Ben Mildenhall and Todd Zickler and Jonathan T. Barron and Pratul P. Srinivasan |
| Conf/Jour | CVPR 2022 (Oral Presentation, Best Student Paper Honorable Mention) |
| Year | 2022 |
| Project | Ref-NeRF (dorverbin.github.io) |
| Paper | Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields (readpaper.com) |

贡献:
- 借鉴Mip-NeRF的IPE,提出一种新的IDE来编码方向向量
- 表面法向通过Spatial MLP来预测,并通过$\mathcal{R}_{\mathrm{p}}=\sum_{i}w_{i}|\hat{\mathbf{n}}_{i}-\hat{\mathbf{n}}_{i}^{\prime}|^{2},$来正则化使得预测得到的法向量和进一步计算的反射更加平滑
- 这些MLP预测的法线往往比梯度密度法线更平滑
- $\hat{\mathbf{n}}(\mathbf{x})=-\frac{\nabla\tau(\mathbf{x})}{|\nabla\tau(\mathbf{x})|}.$Eq.3
- 计算反射光的新渲染方式$\mathbf{c}=\gamma(\mathbf{c}_d+\mathbf{s}\odot\mathbf{c}_s),$
- $\hat{\mathbf{\omega}}_r=2(\hat{\mathbf{\omega}}_o\cdot\hat{\mathbf{n}})\hat{\mathbf{n}}-\hat{\mathbf{\omega}}_o,$ Eq.4
- $L_{\mathrm{out}}(\hat{\mathbf{\omega}}_{o})\propto\int L_{\mathrm{in}}(\hat{\mathbf{\omega}}_{i})p(\hat{\mathbf{\omega}}_{r}\cdot\hat{\mathbf{\omega}}_{i})d\hat{\mathbf{\omega}}_{i}=F(\hat{\mathbf{\omega}}_{r}).$ 借鉴此BRDF,提出的Direction MLP 得出$c_s$
- 漫反射颜色$c_d$通过Spatial MLP预测得到
- s是高光色调
- 将空间MLP输出的瓶颈向量b传递到Direction MLP中,这样反射的亮度就可以随着3D位置的变化而变化。
- $\mathcal{R}_{\mathrm{o}}=\sum_{i}w_{i}\max(0,\hat{\mathbf{n}}_{i}^{\prime}\cdot\hat{\mathbf{d}})^{2}.$ 正则化项惩罚朝向远离相机的法线
局限:
- 编码导致的速度慢,和Spatial MLP的loss反向传播速度比Mip-NeRF慢
- 没有明确地模拟相互反射或非远距离照明
- 忽略互反射和自遮挡等现象
ShadowNeuS
7.1k 26 mins.
| Title | ShadowNeuS: Neural SDF Reconstruction by Shadow Ray Supervision |
|---|---|
| Author | Jingwang Ling and Zhibo Wang and Feng Xu |
| Conf/Jour | CVPR |
| Year | 2023 |
| Project | ShadowNeuS (gerwang.github.io) |
| Paper | ShadowNeuS: Neural SDF Reconstruction by Shadow Ray Supervision (readpaper.com) |

方法:假设场景不发光,且忽略相互反射
- 从二值阴影图像中获得可见表面的入射亮度,然后处理更复杂的RGB图像
- 入射光辐射$C_\mathrm{in}(x,l)=L\prod_{i=1}^N(1-\alpha_i)$, 从单视图、多光源中重建出3D shape
- $\mathcal{L}_\mathrm{shadow}=|\widehat{C}_\mathrm{in}-I_\mathrm{s}|_1.$
- 出射光辐射$C(x,-\mathbf{v})=(\rho_d+\rho_s)C_{\mathrm{in}}(x,l)(l\cdot\mathbf{n})$
- $\mathcal{L}_\mathrm{rgb}=|\widehat{C}-I_\mathrm{r}|_1$
表现:outperforms the SOTAs in single-view reconstruction, and it has the power to reconstruct scene geometries out of the camera’s line of sight.
Strivec
| Title | Strivec: Sparse Tri-Vector Radiance Fields |
|---|---|
| Author | Quankai Gao and Qiangeng Xu and Hao su and Ulrich Neumann and Zexiang Xu |
| Conf/Jour | ICCV |
| Year | 2023 |
| Project | Zerg-Overmind/Strivec (github.com) |
| Paper | Strivec: Sparse Tri-Vector Radiance Fields (readpaper.com) |

- 局部CP分解,三向量
- 多尺度,占用网格方式
TensoRF
| Title | TensoRF: Tensorial Radiance Fields |
|---|---|
| Author | Anpei Chen*, Zexiang Xu*, Andreas Geiger, Jingyi Yu, Hao Su |
| Conf/Jour | ECCV |
| Year | 2022 |
| Project | TensoRF: Tensorial Radiance Fields (apchenstu.github.io) |
| Paper | TensoRF: Tensorial Radiance Fields (readpaper.com) |

UNISURF
| Title | UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction |
|---|---|
| Author | Michael Oechsle Songyou Peng Andreas Geiger |
| Conf/Jour | ICCV 2021 (oral) |
| Year | 2021 |
| Project | UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction (moechsle.github.io) |
| Paper | UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction (readpaper.com) |
使用$\hat{C}(\mathbf{r})=\sum_{i=1}^No(\mathbf{x}_i)\prod_{j<i}\bigl(1-o(\mathbf{x}_j)\bigr)c(\mathbf{x}_i,\mathbf{d})$ 占据o来代替NeRF中的$\alpha$
将VR与SR结合起来,首先根据占据场获取表面的点$t_s$,然后在$t_s$的一个区间内均匀采样点来进行颜色场的优化(如果光线没有穿过物体,则使用分层采样)

PAniC-3D
| Title | PAniC-3D: Stylized Single-view 3D Reconstruction from Portraits of Anime Characters |
|---|---|
| Author | Chen, Shuhong and Zhang, Kevin and Shi, Yichun and Wang, Heng and Zhu, Yiheng and Song, Guoxian and An, Sizhe and Kristjansson, Janus and Yang, Xiao and Matthias Zwicker |
| Conf/Jour | CVPR |
| Year | 2023 |
| Project | ShuhongChen/panic3d-anime-reconstruction: CVPR 2023: PAniC-3D Stylized Single-view 3D Reconstruction from Portraits of Anime Characters (github.com) |
| Paper | PAniC-3D: Stylized Single-view 3D Reconstruction from Portraits of Anime Characters (readpaper.com) |
基于EG3D无条件生成模型
PAniC-3D对比PixelNeRF、EG3D(+Img2stylegan or +PTI)、Pifu

FORGE
6.2k 23 mins.
| Title | Few-View Object Reconstruction with Unknown Categories and Camera Poses |
|---|---|
| Author | Hanwen Jiang Zhenyu Jiang Kristen Grauman Yuke Zhu |
| Conf/Jour | ArXiv |
| Year | 2022 |
| Project | FORGE (ut-austin-rpl.github.io) |
| Paper | Few-View Object Reconstruction with Unknown Categories and Camera Poses (readpaper.com) |
估计视图之间的相对相机姿态
贡献:
- 2D提取voxel特征 —> 相机姿态估计 —> 特征共享+融合 —> MLP神经隐式重建 —> 渲染已有相机位姿的图片,并计算与gt之间的loss
- 新的损失函数

NeRO-code
3.3k 12 mins.
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

