Faithful human performance capture and free-view rendering from sparse RGB observations is a long-standing problem in Vision and Graphics. The main challenges are the lack of observations and the inherent ambiguities of the setting, e.g. occlusions and depth ambiguity. As a result, radiance fields, which have shown great promise in capturing high-frequency appearance and geometry details in dense setups, perform poorly when naively supervising them on sparse camera views, as the field simply overfits to the sparse-view inputs. To address this, we propose MetaCap, a method for efficient and high-quality geometry recovery and novel view synthesis given very sparse or even a single view of the human. Our key idea is to meta-learn the radiance field weights solely from potentially sparse multi-view videos, which can serve as a prior when fine-tuning them on sparse imagery depicting the human. This prior provides a good network weight initialization, thereby effectively addressing ambiguities in sparse-view capture. Due to the articulated structure of the human body and motion-induced surface deformations, learning such a prior is non-trivial. Therefore, we propose to meta-learn the field weights in a pose-canonicalized space, which reduces the spatial feature range and makes feature learning more effective. Consequently, one can fine-tune our field parameters to quickly generalize to unseen poses, novel illumination conditions as well as novel and sparse (even monocular) camera views. For evaluating our method under different scenarios, we collect a new dataset, WildDynaCap, which contains subjects captured in, both, a dense camera dome and in-the-wild sparse camera rigs, and demonstrate superior results compared to recent state-of-the-art methods on, both, public and WildDynaCap dataset.
MARTIAN: A Rendering Framework for Aerial Mars Imagery from HiRISE Orbital Data
Space Robotics Research Group, SnT, University of Luxembourg（卢森堡大学空间机器人研究组）；Jet Propulsion Laboratory, California Institute of Technology（加州理工学院喷气推进实验室）
University of Hong Kong（香港大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Stanford University（斯坦福大学）
We propose a method for generating video-realistic animations of real humans under user control. In contrast to conventional human character rendering, we do not require the availability of a production-quality photo-realistic 3D model of the human, but instead rely on a video sequence in conjunction with a (medium-quality) controllable 3D template model of the person. With that, our approach significantly reduces production cost compared to conventional rendering approaches based on production-quality 3D models, and can also be used to realistically edit existing videos. Technically, this is …
Google Research（谷歌研究院）；Cornell Tech Cornell University（康奈尔大学康奈尔科技校区）；Princeton University（普林斯顿大学）
We present a method that synthesizes novel views of complex scenes by interpolating a sparse set of nearby views. The core of our method is a network architecture that includes a multilayer perceptron and a ray transformer that estimates radiance and volume density at continuous 5D locations (3D spatial locations and 2D viewing directions), drawing appearance information on the fly from multiple source views. By drawing on source views at render time, our method hearkens back to classic work on image-based rendering (IBR), and allows us to render high-resolution imagery. Unlike neural scene re…
Brown University（布朗大学）；Carnegie Mellon University（卡内基梅隆大学）；University of Bath（巴斯大学）
We introduce a method to convert stereo 360° (omnidirectional stereo) imagery into a layered, multi-sphere image representation for six degree-of-freedom (6DoF) rendering. Stereo 360° imagery can be captured from multi-camera systems for virtual reality (VR), but lacks motion parallax and correct-in-all-directions disparity cues. Together, these can quickly lead to VR sickness when viewing content. One solution is to try and generate a format suitable for 6DoF rendering, such as by estimating depth. However, this raises questions as to how to handle disoccluded regions in dynamic scenes. Our a…
The size and geometry of the prostate are known to be pivotal quantities used by clinicians to assess the condition of the gland during prostate cancer screening. As an alternative to palpation, an increasing number of methods for estimation of the above-mentioned quantities are based on using imagery data of prostate. The necessity to process large volumes of such data creates a need for automatic segmentation tools which would allow the estimation to be carried out with maximum accuracy and efficiency. In particular, the use of transrectal ultrasound (TRUS) imaging in prostate cancer screeni…
BungeeNeRF: Progressive Neural Radiance Field for Extreme Multi-scale Scene Rendering
The Chinese University of Hong Kong（香港中文大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；University of Bath（巴斯大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
DEAR: Dataset for Evaluating the Aesthetics of Rendering
Color Reproduction and Synthesis Institute（颜色再现与合成研究所）；Moscow Independent Research Institute of Artificial Intelligence（莫斯科独立人工智能研究 institute）；Computational color photography Laboratory（计算色彩摄影实验室）；University of Milano-Bicocca（米兰-比科卡大学）
Motivated by augmented and virtual reality applications such as telepresence, there has been a recent focus in real-time performance capture of humans under motion. However, given the real-time constraint, these systems often suffer from artifacts in geometry and texture such as holes and noise in the final rendering, poor lighting, and low-resolution textures. We take the novel approach to augment such real-time performance capture systems with a deep architecture that takes a rendering from an arbitrary viewpoint, and jointly performs completion, super resolution, and denoising of the imager…
EOGS++: Earth Observation Gaussian Splatting with Internal Camera Refinement and Direct Panchromatic Rendering
Universite Paris-Saclay, CNRS, ENS Paris-Saclay, Centre Borelli（巴黎萨克雷大学，法国国家科学研究中心，巴黎萨克雷高等师范学校，博雷利中心）；Politecnico di Torino（都灵理工大学）；AMIAD, Pôle Recherche（AMIAD，研究部）；Institut Universitaire de France（法兰西大学研究院）
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Facebook AI Research（Facebook人工智能研究院）；National University of Singapore（新加坡国立大学）
Photo-realistic free-viewpoint rendering of real-world scenes using classical computer graphics techniques is challenging, because it requires the difficult step of capturing detailed appearance and geometry models. Recent studies have demonstrated promising results by learning scene representations that implicitly encode both geometry and appearance without 3D supervision. However, existing approaches in practice often show blurry renderings caused by the limited network capacity or the difficulty in finding accurate intersections of camera rays with the scene geometry. Synthesizing high-reso…
Shanghai Jiao Tong University（上海交通大学）；New York University（纽约大学）；UNC Chapel Hill（北卡罗来纳大学教堂山分校）；Peng Cheng Laboratory（鹏城实验室）
Virtual Reality (VR) is becoming ubiquitous with the rise of consumer displays and commercial VR platforms. Such displays require low latency and high quality rendering of synthetic imagery with reduced compute overheads. Recent advances in neural rendering showed promise of unlocking new possibilities in 3D computer graphics via image-based representations of virtual or physical environments. Specifically, the neural radiance fields (NeRF) demonstrated that photo-realistic quality and continuous view changes of 3D scenes can be achieved without loss of view-dependent effects. While NeRF can s…
University College London（伦敦大学学院）；Google Research（谷歌研究院）
Some forms of novel visual media enable the viewer to explore a 3D scene from arbitrary viewpoints, by interpolating between a discrete set of original views. Compared to 2D imagery, these types of applications require much larger amounts of storage space, which we seek to reduce. Existing approaches for compressing 3D scenes are based on a separation of compression and rendering: each of the original views is compressed using traditional 2D image formats; the receiver decompresses the views and then performs the rendering. We unify these steps by directly compressing an implicit representatio…
DentalSplat: Dental Occlusion Novel View Synthesis from Sparse Intra-Oral Photographs
School of AI and Advanced Computing, Xi'an Jiaotong Liverpool University（人工智能与先进计算学院，西安交通大学利物浦大学）；School of Advanced Technology, Xi'an Jiaotong Liverpool University（先进技术学院，西安交通大学利物浦大学）；School of Physical Sciences, University of Liverpool（物理科学学院，利物浦大学）；College of Computer Science and Technology, Zhejiang University（计算机科学与技术学院，浙江大学）
SwiftGS: Episodic Priors for Immediate Satellite Surface Recovery
University of Macau（澳门大学）；Juntendo University（顺天堂大学）；Tongji University（同济大学）；Zhejiang University（浙江大学）；University of Florida（佛罗里达大学）；Tsinghua University（清华大学）；Wuhan University（武汉大学）；Juniata College（朱尼亚塔学院）
MrGS: Multi-modal Radiance Fields with 3D Gaussian Splatting for RGB-Thermal Novel View Synthesis
Minnesota Robotics Institute (MnRI), University of Minnesota, Twin Cities（明尼苏达大学罗学院（MnRI）、明尼苏达大学双城分校）；Department of Information Convergence Engineering (Artificial Intelligence Major), Pusan National University（信息融合工程系（人工智能专业），釜山国立大学）；Department of Energy Engineering, Korea Institute of Energy Technology (KENTECH)（能源工程系，韩国能源技术研究所（KENTECH））；School of Computer Science and Engineering, Pusan National University（计算机科学与工程学院，釜山国立大学）
