以下整理是按照专题来排列的，如果你更习惯按照更新日期来看，可以跳转到这个链接：按日期更新列表
【NeRF神经辐射场】
----------------单场景NeRF----------------
● NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis (ECCV 2020)
视频链接：论文讲解
描述：第一篇NeRF原文
● Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields (ICCV 2021)
视频链接：论文讲解
描述：多尺度抗锯齿的NeRF
● NeRF++: Analyzing and Improving Neural Radiance Fields
视频链接：论文讲解
描述：NeRF++ 可处理远景的NeRF
● Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields (CVPR 2022)
视频链接：论文讲解
描述：Mip-NeRF360 抗锯齿超远景NeRF
● NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections (CVPR 2021)
视频链接：论文讲解
描述：NeRF-W 自然条件下的NeRF
● Block-NeRF: Scalable Large Scene Neural View Synthesis (CVPR 2022)
视频链接：论文讲解
描述：超大场景的NeRF
----------------泛化性NeRF----------------
● pixelNeRF: Neural Radiance Fields from One or Few Images (CVPR 2021)
视频链接：论文讲解
描述：具有泛化性的NeRF
● IBRNet: Learning Multi-View Image-Based Rendering (CVPR 2021)
视频链接：论文讲解
描述：IBRNet 利用NeRF做可泛化视角插值
● MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo (ICCV 2021)
视频链接：论文讲解
描述：MVSNeRF 基于Cost-volume的NeRF
----------------NeRF渲染加速----------------
● FastNeRF: High-Fidelity Neural Rendering at 200FPS (ICCV 2021)
视频链接：论文讲解
描述：FastNeRF 快速渲染辐射场
● SqueezeNeRF: Further factorized FastNeRF for memory-efficient inference
视频链接：论文讲解
描述：SqueezeNeRF 低内存快速渲染辐射场
----------------NeRF训练加速----------------
● Point-NeRF: Point-based Neural Radiance Fields (CVPR 2022)
视频链接：论文讲解
描述：用MVS及点云代理加速NeRF的训练
● Plenoxels: Radiance Fields without Neural Networks (CVPR 2022)
视频链接：论文讲解
描述：Plenoxels 神经辐射场，但是没有神经
● Instant Neural Graphics Primitives with a Multiresolution Hash Encoding (SIGGRAPH 2022)
视频链接：论文讲解
描述：Instant-NGP 基于哈希编码的MLP
----------------动态NeRF----------------
● D-NeRF: Neural Radiance Fields for Dynamic Scenes (CVPR 2020)
视频链接：论文讲解
描述：D-NeRF 可形变物体的NeRF
● Nerfies: Deformable Neural Radiance Fields (ICCV 2021)
视频链接：论文讲解
描述：Nerfies 简单自拍重建动态NeRF
● HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields (Siggraph Asian 2021)
视频链接：论文讲解
描述：HyperNeRF 拓扑可变的变形场
● D2NeRF: Self-Supervised Decoupling of Dynamic and Static Objects from a Monocular Video (NeurIPS 2022)
视频链接：论文讲解
描述：D2NeRF 视频中的动静物体分离
【3D重建】
----------------3D表示----------------
● DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation (CVPR 2019)
视频链接：论文讲解
描述：DeepSDF 符号距离场&三维重建
----------------多视角重建----------------
● NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction (NeurIPS 2021)
视频链接：论文讲解
描述：NeuS 基于体渲染的多视角重建
【GAN生成模型】
----------------图像GAN----------------
● Progressive growing of GANs for improved quality, stability, and variation (ICLR 2018)
视频链接：论文讲解
描述：PGGAN 递进生成网络
● A style-based generator architecture for generative adversarial networks (CVPR 2019)
视频链接：论文讲解
描述：StyleGAN 风格化可控图像生成
● Analyzing and Improving the Image Quality of StyleGAN (CVPR 2020)
视频链接：论文讲解
描述：StyleGAN2 更可控的图像生成
● StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery (ICCV 2021)
视频链接：论文讲解
描述：用文本编辑GAN图像
● Style Transformer for Image Inversion and Editing (CVPR 2022)
视频链接：论文讲解
描述：用Transformer做图像风格编辑
----------------3维GAN----------------
● GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis (NIPS 2020)
视频链接：论文讲解
描述：用NeRF+GAN做三维生成
● pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis (CVPR 2021)
视频链接：论文讲解
描述：Pi-GAN 周期隐式三维GAN
● GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields (CVPR 2021最佳论文)
视频链接：论文讲解
描述：GIRAFEE CVPR2021最佳论文 可组合多物体的三维GAN
● StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generation (CVPR 2022)
视频链接：论文讲解
描述：StyleSDF 高分辨率图像与几何生成
● Disentangled3D: Learning a 3D Generative Model with Disentangled Geometry and Appearance from Monocular Images (Arxiv 2022-03-29)
视频链接：论文讲解
描述：Disentangled3D-GAN 将外观与几何解耦
----------------视频GAN----------------
● Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks (ICLR 2022)
视频链接：论文讲解
描述：隐式生成模型合成视频
【图像】
----------------图像分割----------------
● DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting (CVPR 2022)
视频链接：论文讲解
描述：DenseCLIP 用文本指导图像分割
----------------图像超分----------------
● Learning Continuous Image Representation with Local Implicit Image Function (CVPR 2021)
视频链接：论文讲解
描述：图像局部隐式表示
● Continuous Spectral Reconstruction from RGB Images via Implicit Neural Representation (ArXiv 2021-12-24)
视频链接：论文讲解
描述：从RGB图像重建高光谱图像
● PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models (CVPR 2020)
视频链接：论文讲解
描述：PULSE 用GAN巧解超分辨率
----------------视频超分----------------
● BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment (CVPR 2022)
视频链接：论文讲解
描述：BasicVSR++ SOTA的视频超分辨率算法
【人脸】
----------------人脸重建----------------
● Self-Supervised Robustifying Guidance for Monocular 3D Face Reconstruction (ArXiv 2021-12-29)
视频链接：论文讲解
描述：无监督RGB三维人脸重建
----------------人脸建模----------------
● Text and Image Guided 3D Avatar Generation and Manipulation (ArXiv 2021-12-22)
视频链接：论文讲解
描述：用文本语义控制三维人脸建模
----------------人脸风格化----------------
● JoJoGAN: One Shot Face Stylization (ArXiv 2022-01-12)
视频链接：论文讲解
描述：生成动漫风格的人脸图像
【点云】
----------------点云网络----------------
● PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation (CVPR 2017)
视频链接：论文讲解
描述：PointNet 点云网络开山之作
● PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space (NIPS 2017)
视频链接：论文讲解
描述：PointNet++ 层级点云特征学习
● Point Transformer (ICCV 2021)
视频链接：论文讲解
描述：点云上的Transformer
● Fast Point Transformer (ArXiv 2021-12-09)
视频链接：论文讲解
描述：快速点云Transformer
● PointCLIP: Point Cloud Understanding by CLIP (CVPR 2022)
视频链接：论文讲解
描述：用CLIP巧解点云分类
----------------点云降噪----------------
● Score-Based Point Cloud Denoising (ICCV 2021)
视频链接：论文讲解
描述：用极大似然法做点云降噪
【普适网络结构】
● Learning Transferable Visual Models From Natural Language Supervision (ICML 2021)
视频链接：论文讲解
描述：CLIP 文本和图像的跨模态匹配
【网格】
----------------泛函映射----------------
● Functional maps: A flexible representation of maps between shapes (TOG 2012)
视频链接：论文讲解
描述：Functional Maps 同构流形上的泛函映射
● Deep Functional Maps: Structured Prediction for Dense Shape Correspondence Emanuele (ICCV 2017)
视频链接：论文讲解
描述：Deep Functional Maps 深度泛函映射