We introduce the problem of perpetual view generation - long-range generation of novel views corresponding to an arbitrarily long camera trajectory given a single image. This is a challenging problem that goes far beyond the capabilities of current view synthesis methods, which quickly degenerate when presented with large camera motions. Methods for video generation also have limited ability to produce long sequences and are often agnostic to scene geometry. We take a hybrid approach that integrates both geometry and image synthesis in an iterative `\emph{render}, \emph{refine} and \emph{repeat}' framework, allowing for long-range generation that cover large distances after hundreds of frames. Our approach can be trained from a set of monocular video sequences. We propose a dataset of aerial footage of coastal scenes, and compare our method with recent view synthesis and conditional video generation baselines, showing that it can generate plausible scenes for much longer time horizons over large camera trajectories compared to existing methods. Project page at https://infinite-nature.github.io/.
We present a method for learning to generate unbounded flythrough videos of natural scenes starting from a single view, where this capability is learned from a collection of single photographs, without requiring camera poses or even multiple views of each scene. To achieve this, we propose a novel self-supervised view generation training paradigm, where we sample and rendering virtual camera trajectories, including cyclic ones, allowing our model to learn stable view generation from a collection of single views. At test time, despite never seeing a video during training, our approach can take …
MoE Key Lab of Artificial Intelligence, School of Computer Science, SJTU（人工智能前沿实验室，计算机科学学院，上海交通大学）；Huawei Inc.（华为公司）；Huazhong University of Science and Technology（华中科技大学）
ETH Zürich（苏黎世联邦理工学院）；Max Planck Institute for Intelligent Systems, Tübingen（马克斯·普朗克智能系统研究所（蒂宾根））
The modeling of human motion using machine learning methods has been widely studied. In essence it is a time-series modeling problem involving predicting how a person will move in the future given how they moved in the past. Existing methods, however, typically have a short time horizon, predicting a only few frames to a few seconds of human motion. Here we focus on long-term prediction; that is, generating long sequences (potentially infinite) of human motion that is plausible. Furthermore, we do not rely on a long sequence of input motion for conditioning, but rather, can predict how someone…
We propose a method to estimate the uncertainty of the outcome of an image classifier on a given input datum. Deep neural networks commonly used for image classification are deterministic maps from an input image to an output class. As such, their outcome on a given datum involves no uncertainty, so we must specify what variability we are referring to when defining, measuring and interpreting uncertainty, and attributing "confidence" to the outcome. To this end, we introduce the Wellington Posterior, which is the distribution of outcomes that would have been obtained in response to data that c…
Yo'City: Personalized and Boundless 3D Realistic City Scene Generation via Self-Critic Expansion
School of Computer Science, Peking University（北京大学计算机科学学院）；Beihang University（北航）；Southeast University（东南大学）；ByteDance Seed（字节跳动种子）；Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)（广东省人工智能与数字经济实验室）；Beijing Normal University（北京师范大学）；Theta Labs（Theta实验室）
Our goal is to populate digital environments, in which digital humans have diverse body shapes, move perpetually, and have plausible body-scene contact. The core challenge is to generate realistic, controllable, and infinitely long motions for diverse 3D bodies. To this end, we propose generative motion primitives via body surface markers, or GAMMA in short. In our solution, we decompose the long-term motion into a time sequence of motion primitives. We exploit body surface markers and conditional variational autoencoder to model each motion primitive, and generate long-term motion by implemen…
University of Electronic Science and Technology of China（电子科技大学）
Recently, methods based on deep learning have dominated the field of text recognition. With a large number of training data, most of them can achieve the state-of-the-art performances. However, it is hard to harvest and label sufficient text sequence images from the real scenes. To mitigate this issue, several methods to synthesize text sequence images were proposed, yet they usually need complicated preceding or follow-up steps. In this work, we present a method which is able to generate infinite training data without any auxiliary pre/post-process. We tackle the generation task as an image-t…
Unsupervised image-to-image translation aims at learning a joint distribution of images in different domains by using images from the marginal distributions in individual domains. Since there exists an infinite set of joint distributions that can arrive the given marginal distributions, one could infer nothing about the joint distribution from the marginal distributions without additional assumptions. To address the problem, we make a shared-latent space assumption and propose an unsupervised image-to-image translation framework based on Coupled GANs. We compare the proposed framework with com…
We present a efficient multi-view inverse rendering method for large-scale real-world indoor scenes that reconstructs global illumination and physically-reasonable SVBRDFs. Unlike previous representations, where the global illumination of large scenes is simplified as multiple environment maps, we propose a compact representation called Texture-based Lighting (TBL). It consists of 3D mesh and HDR textures, and efficiently models direct and infinite-bounce indirect lighting of the entire large scene. Based on TBL, we further propose a hybrid lighting representation with precomputed irradiance, …
In this work we present a framework for the recognition of natural scene text. Our framework does not require any human-labelled data, and performs word recognition on the whole image holistically, departing from the character based recognition systems of the past. The deep neural network models at the centre of this framework are trained solely on data produced by a synthetic text generation engine -- synthetic data that is highly realistic and sufficient to replace real data, giving us infinite amounts of training data. This excess of data exposes new possibilities for word recognition model…
University of Pennsylvania（宾夕法尼亚大学）；University of California, Los Angeles（加州大学洛杉矶分校）；University of Massachusetts Boston（马萨诸塞大学波士顿分校）
We propose a systematic learning-based approach to the generation of massive quantities of synthetic 3D scenes and arbitrary numbers of photorealistic 2D images thereof, with associated ground truth information, for the purposes of training, benchmarking, and diagnosing learning-based computer vision and robotics algorithms. In particular, we devise a learning-based pipeline of algorithms capable of automatically generating and rendering a potentially infinite variety of indoor scenes by using a stochastic grammar, represented as an attributed Spatial And-Or Graph, in conjunction with state-of…
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Saarland Informatics Campus（萨尔兰信息学园区）；University of Freiburg（弗赖堡大学）；Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU)（埃尔朗根-纽伦堡弗里德里希-亚历山大大学（FAU））；EPFL（洛桑联邦理工学院）
3D reconstruction of deformable (or non-rigid) scenes from a set of monocular 2D image observations is a long-standing and actively researched area of computer vision and graphics. It is an ill-posed inverse problem, since -- without additional prior assumptions -- it permits infinitely many solutions leading to accurate projection to the input 2D images. Non-rigid reconstruction is a foundational building block for downstream applications like robotics, AR/VR, or visual content creation. The key advantage of using monocular cameras is their omnipresence and availability to the end users as we…
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…
A fundamental problem in computer vision is that of inferring the intrinsic, 3D structure of the world from flat, 2D images of that world. Traditional methods for recovering scene properties such as shape, reflectance, or illumination rely on multiple observations of the same scene to overconstrain the problem. Recovering these same properties from a single image seems almost impossible in comparison -- there are an infinite number of shapes, paint, and lights that exactly reproduce a single image. However, certain explanations are more likely than others: surfaces tend to be smooth, paint ten…
School of Electronic Information, Wuhan University（武汉大学电子信息学院）；School of Computer Science, Wuhan University（武汉大学计算机学院）；State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University（武汉大学测绘遥感信息工程国家重点实验室）；Zhongguancun Academy（中关村学院）
SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving
Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）；Tsinghua University（清华大学）；Tianjin University（天津大学）；PhiGent Robotics（鉴智机器人）
In this work, we develop a method to generate infinite high-resolution images with diverse and complex content. It is based on a perfectly equivariant generator with synchronous interpolations in the image and latent spaces. Latent codes, when sampled, are positioned on the coordinate grid, and each pixel is computed from an interpolation of the nearby style codes. We modify the AdaIN mechanism to work in such a setup and train the generator in an adversarial setting to produce images positioned between any two latent vectors. At test time, this allows for generating complex and diverse infini…
IIIT Hyderabad（印度海得拉巴国际信息技术学院）；TCS Innovation Labs（塔塔咨询服务公司创新实验室）；Mila（米拉研究所）；Universite de Montreal（蒙特利尔大学）
In this paper, we tackle the problem of multibody SLAM from a monocular camera. The term multibody, implies that we track the motion of the camera, as well as that of other dynamic participants in the scene. The quintessential challenge in dynamic scenes is unobservability: it is not possible to unambiguously triangulate a moving object from a moving monocular camera. Existing approaches solve restricted variants of the problem, but the solutions suffer relative scale ambiguity (i.e., a family of infinitely many solutions exist for each pair of motions in the scene). We solve this rather intra…
Code-as-Room: Generating 3D Rooms from Top-Down View Images via Agentic Code Synthesis
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Shanghai Innovation Institute（上海创新研究院）；Southern University of Science and Technology（南方科技大学）；University of Warwick（沃里克大学）
Neural Radiance Fields (NeRF) have recently demonstrated photo-realistic results for the task of novel view synthesis. In this paper, we propose to apply novel view synthesis to the robot relocalization problem: we demonstrate improvement of camera pose regression thanks to an additional synthetic dataset rendered by the NeRF class of algorithm. To avoid spawning novel views in irrelevant places we selected virtual camera locations from NeRF internal representation of the 3D geometry of the scene. We further improved localization accuracy of pose regressors using synthesized realistic and geom…
