Novel view synthesis from an in-the-wild video is difficult due to challenges like scene dynamics and lack of parallax. While existing methods have shown promising results with implicit neural radiance fields, they are slow to train and render. This paper revisits explicit video representations to synthesize high-quality novel views from a monocular video efficiently. We treat static and dynamic video content separately. Specifically, we build a global static scene model using an extended plane-based scene representation to synthesize temporally coherent novel video. Our plane-based scene representation is augmented with spherical harmonics and displacement maps to capture view-dependent effects and model non-planar complex surface geometry. We opt to represent the dynamic content as per-frame point clouds for efficiency. While such representations are inconsistency-prone, minor temporal inconsistencies are perceptually masked due to motion. We develop a method to quickly estimate such a hybrid video representation and render novel views in real time. Our experiments show that our method can render high-quality novel views from an in-the-wild video with comparable quality to state-of-the-art methods while being 100x faster in training and enabling real-time rendering.
We present an algorithm for generating novel views at arbitrary viewpoints and any input time step given a monocular video of a dynamic scene. Our work builds upon recent advances in neural implicit representation and uses continuous and differentiable functions for modeling the time-varying structure and the appearance of the scene. We jointly train a time-invariant static NeRF and a time-varying dynamic NeRF, and learn how to blend the results in an unsupervised manner. However, learning this implicit function from a single video is highly ill-posed (with infinitely many solutions that match…
Structure from motion (SfM) enables us to reconstruct a scene via casual capture from cameras at different viewpoints, and novel view synthesis (NVS) allows us to render a captured scene from a new viewpoint. Both are hard with casual capture and dynamic scenes: SfM produces noisy and spatio-temporally sparse reconstructed point clouds, resulting in NVS with spatio-temporally inconsistent effects. We consider SfM and NVS parts together to ease the challenge. First, for SfM, we recover stable camera poses, then we defer the requirement for temporally-consistent points across the scene and recon…
Representing and synthesizing novel views in real-world dynamic scenes from casual monocular videos is a long-standing problem. Existing solutions typically approach dynamic scenes by applying geometry techniques or utilizing temporal information between several adjacent frames without considering the underlying background distribution in the entire scene or the transmittance over the ray dimension, limiting their performance on static and occlusion areas. Our approach $\textbf{D}$istribution-$\textbf{D}$riven neural radiance fields offers high-quality view synthesis and a 3D solution to $\tex…
We present EgoNeRF, a practical solution to reconstruct large-scale real-world environments for VR assets. Given a few seconds of casually captured 360 video, EgoNeRF can efficiently build neural radiance fields which enable high-quality rendering from novel viewpoints. Motivated by the recent acceleration of NeRF using feature grids, we adopt spherical coordinate instead of conventional Cartesian coordinate. Cartesian feature grid is inefficient to represent large-scale unbounded scenes because it has a spatially uniform resolution, regardless of distance from viewers. The spherical parameter…
Inria（法国国家信息与自动化研究所）；Université Côte d’Azur（蔚蓝海岸大学）；Max-Planck-Institut für Informatik（马克斯·普朗克信息学研究所）；Ecole Polytechnique（巴黎综合理工学院）
View-dependent effects such as reflections pose a substantial challenge for image-based and neural rendering algorithms. Above all, curved reflectors are particularly hard, as they lead to highly non-linear reflection flows as the camera moves. We introduce a new point-based representation to compute Neural Point Catacaustics allowing novel-view synthesis of scenes with curved reflectors, from a set of casually-captured input photos. At the core of our method is a neural warp field that models catacaustic trajectories of reflections, so complex specular effects can be rendered using efficient …
AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views
University of Science and Technology of China（科学技术大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；The Chinese University of Hong Kong（香港中文大学）；Brown University（布朗大学）；Shanghai Jiao Tong University（交通大学）；The University of Hong Kong（香港大学）
LTGS: Long-Term Gaussian Scene Chronology From Sparse View Updates
Dept. of Electrical and Computer Engineering, Seoul National University（电子与计算机工程系，首尔国立大学）；Interdisciplinary Program in Artificial Intelligence and INMC, Seoul National University（人工智能跨学科项目及INMC，首尔国立大学）
NeVStereo: A NeRF-Driven NVS-Stereo Architecture for High-Fidelity 3D Tasks
University of Washington（华盛顿大学）；University of Southern California（南加州大学）；CUHK-Shenzhen（香港中文大学（深圳））；USC Institute for Creative Technologies（南加州大学创意技术研究所）
KAIST（韩国科学技术院）；National Taiwan University（国立台湾大学）；Meta；University of Maryland, College Park（马里兰大学帕克分校）
We present an algorithm for reconstructing the radiance field of a large-scale scene from a single casually captured video. The task poses two core challenges. First, most existing radiance field reconstruction approaches rely on accurate pre-estimated camera poses from Structure-from-Motion algorithms, which frequently fail on in-the-wild videos. Second, using a single, global radiance field with finite representational capacity does not scale to longer trajectories in an unbounded scene. For handling unknown poses, we jointly estimate the camera poses with radiance field in a progressive man…
Towards Real-World Document Parsing via Realistic Scene Synthesis and Document-Aware Training
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；Tencent（腾讯）；Nankai University（南开大学）；University of Chinese Academy of Sciences（中国科学院大学）；Nanjing University of Science and Technology（南京理工大学）
Meta Reality Labs Research（Meta现实实验室）；University of Oulu（奥卢大学）
Capturing and faithfully rendering photo-realistic humans from novel views is a fundamental problem for AR/VR applications. While prior work has shown impressive performance capture results in laboratory settings, it is non-trivial to achieve casual free-viewpoint human capture and rendering for unseen identities with high fidelity, especially for facial expressions, hands, and clothes. To tackle these challenges we introduce a novel view synthesis framework that generates realistic renders from unseen views of any human captured from a single-view and sparse RGB-D sensor, similar to a low-cos…
