We present PersonNeRF, a method that takes a collection of photos of a subject (e.g. Roger Federer) captured across multiple years with arbitrary body poses and appearances, and enables rendering the subject with arbitrary novel combinations of viewpoint, body pose, and appearance. PersonNeRF builds a customized neural volumetric 3D model of the subject that is able to render an entire space spanned by camera viewpoint, body pose, and appearance. A central challenge in this task is dealing with sparse observations; a given body pose is likely only observed by a single viewpoint with a single appearance, and a given appearance is only observed under a handful of different body poses. We address this issue by recovering a canonical T-pose neural volumetric representation of the subject that allows for changing appearance across different observations, but uses a shared pose-dependent motion field across all observations. We demonstrate that this approach, along with regularization of the recovered volumetric geometry to encourage smoothness, is able to recover a model that renders compelling images from novel combinations of viewpoint, pose, and appearance from these challenging unstructured photo collections, outperforming prior work for free-viewpoint human rendering.
Personalized Image Filter: Mastering Your Photographic Style
State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University（国家通用人工智能重点实验室，智能科学与技术学院，北京大学）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）；State Key Laboratory of Multimedia Information Processing and National Engineering Research Center of Visual Technology, School of Computer Science, Peking University（多媒体信息处理国家重点实验室和视觉技术国家工程研究中心，计算机科学学院，北京大学）；School of Artificial Intelligence, Beijing University of Posts and Telecommunications（人工智能学院，北京邮电大学）
CusEnhancer: A Zero-Shot Scene and Controllability Enhancement Method for Photo Customization via ResInversion
College of Computer Science and Technology, East China University of Science and Technology（计算机科学与技术学院，东华大学）；Carnegie Mellon University（卡内基梅隆大学）；Microsoft（微软公司）
Learning to Aggregate and Personalize 3D Face from In-the-Wild Photo Collection
Tencent Youtu Lab（腾讯优图实验室）；Nanjing University of Science and Technology（南京理工大学）
非参数化人脸建模的目的是在不需要形状假设的情况下，仅从图像中重建三维人脸。虽然预测了可信的面部细节，但模型往往过度依赖于局部颜色外观，并受到模糊噪声的影响。为了解决这个问题，本文提出了一种新的学习聚合和个性化（Learning to Aggregate and Personalize）框架，用于无监督的鲁棒3D人脸建模。该方法不使用受控环境，而是隐式地从无约束的照片集中分离出ID一致的和场景特定的人脸。具体而言，学习身份一致的脸，自适应聚合的内在面孔因素的身份的基础上，一种新的课程学习方法与放松一致性损失。为了适应个性化场景的脸，我们提出了一种新的属性细化网络修改ID一致的脸与目标属性和细节。基于所提出的方法，我们使无监督三维人脸建模受益于有意义的图像面部结构和可能更高的分辨率。在基准上进行的大量实验表明，与有或没有先验和监督的最先进的（SOTA）方法相比，PSNR恢复了优越或有竞争力的面部形状和纹理。
PuzzleAvatar: Assembling 3D Avatars from Personal Albums
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Carnegie Mellon University（卡内基梅隆大学）；Mila, Université de Montréal（米拉-蒙特利尔大学）；University of Amsterdam（阿姆斯特丹大学）
