We introduce 3inGAN, an unconditional 3D generative model trained from 2D images of a single self-similar 3D scene. Such a model can be used to produce 3D "remixes" of a given scene, by mapping spatial latent codes into a 3D volumetric representation, which can subsequently be rendered from arbitrary views using physically based volume rendering. By construction, the generated scenes remain view-consistent across arbitrary camera configurations, without any flickering or spatio-temporal artifacts. During training, we employ a combination of 2D, obtained through differentiable volume tracing, and 3D Generative Adversarial Network (GAN) losses, across multiple scales, enforcing realism on both its 3D structure and the 2D renderings. We show results on semi-stochastic scenes of varying scale and complexity, obtained from real and synthetic sources. We demonstrate, for the first time, the feasibility of learning plausible view-consistent 3D scene variations from a single exemplar scene and provide qualitative and quantitative comparisons against recent related methods.
The Weizmann Institute of Science（魏茨曼科学研究所）；Massachusetts Institute of Technology（麻省理工学院）
Generative Adversarial Networks (GANs) typically learn a distribution of images in a large image dataset, and are then able to generate new images from this distribution. However, each natural image has its own internal statistics, captured by its unique distribution of patches. In this paper we propose an "Internal GAN" (InGAN) - an image-specific GAN - which trains on a single input image and learns its internal distribution of patches. It is then able to synthesize a plethora of new natural images of significantly different sizes, shapes and aspect-ratios - all with the same internal patch-…
3D generative models of objects enable photorealistic image synthesis with 3D control. Existing methods model the scene as a global scene representation, ignoring the compositional aspect of the scene. Compositional reasoning can enable a wide variety of editing applications, in addition to enabling generalizable 3D reasoning. In this paper, we present a compositional generative model, where each semantic part of the object is represented as an independent 3D representation learned from only in-the-wild 2D data. We start with a global generative model (GAN) and learn to decompose it into diffe…
Department of Information Engineering, The Chinese University of Hong Kong（香港中文大学信息工程学系）
Despite the success of Generative Adversarial Networks (GANs) in image synthesis, there lacks enough understanding on what generative models have learned inside the deep generative representations and how photo-realistic images are able to be composed of the layer-wise stochasticity introduced in recent GANs. In this work, we show that highly-structured semantic hierarchy emerges as variation factors from synthesizing scenes from the generative representations in state-of-the-art GAN models, like StyleGAN and BigGAN. By probing the layer-wise representations with a broad set of semantics at di…
MIT Interdisciplinary Center, Herzliya（赫兹利亚跨学科中心（MIT））；Stanford University（斯坦福大学）
Learning 3D generative models from a dataset of monocular images enables self-supervised 3D reasoning and controllable synthesis. State-of-the-art 3D generative models are GANs which use neural 3D volumetric representations for synthesis. Images are synthesized by rendering the volumes from a given camera. These models can disentangle the 3D scene from the camera viewpoint in any generated image. However, most models do not disentangle other factors of image formation, such as geometry and appearance. In this paper, we design a 3D GAN which can learn a disentangled model of objects, just from …
Existing 3D-aware image synthesis approaches mainly focus on generating a single canonical object and show limited capacity in composing a complex scene containing a variety of objects. This work presents DisCoScene: a 3Daware generative model for high-quality and controllable scene synthesis. The key ingredient of our method is a very abstract object-level representation (i.e., 3D bounding boxes without semantic annotation) as the scene layout prior, which is simple to obtain, general to describe various scene contents, and yet informative to disentangle objects and background. Moreover, it s…
Dwarkadas J. Sanghvi College of Engineering（德瓦卡达斯·J·桑格维工程学院）；University of Mumbai（孟买大学）
3D multi object generative models allow us to synthesize a large range of novel 3D multi object scenes and also identify objects, shapes, layouts and their positions. But multi object scenes are difficult to create because of the dataset being multimodal in nature. The conventional 3D generative adversarial models are not efficient in generating multi object scenes, they usually tend to generate either one object or generate fuzzy results of multiple objects. Auto-encoder models have much scope in feature extraction and representation learning using the unsupervised paradigm in probabilistic s…
The Ohio State University（俄亥俄州立大学）；Chongqing Changan Automobile Co Ltd（重庆长安汽车股份有限公司）
Driving simulators play a large role in developing and testing new intelligent vehicle systems. The visual fidelity of the simulation is critical for building vision-based algorithms and conducting human driver experiments. Low visual fidelity breaks immersion for human-in-the-loop driving experiments. Conventional computer graphics pipelines use detailed 3D models, meshes, textures, and rendering engines to generate 2D images from 3D scenes. These processes are labor-intensive, and they do not generate photorealistic imagery. Here we introduce a hybrid generative neural graphics pipeline for …
Generating photorealistic images with controllable camera pose and scene contents is essential for many applications including AR/VR and simulation. Despite the fact that rapid progress has been made in 3D-aware generative models, most existing methods focus on object-centric images and are not applicable to generating urban scenes for free camera viewpoint control and scene editing. To address this challenging task, we propose UrbanGIRAFFE, which uses a coarse 3D panoptic prior, including the layout distribution of uncountable stuff and countable objects, to guide a 3D-aware generative model.…
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；University of Tübingen（蒂宾根大学）
Deep generative models allow for photorealistic image synthesis at high resolutions. But for many applications, this is not enough: content creation also needs to be controllable. While several recent works investigate how to disentangle underlying factors of variation in the data, most of them operate in 2D and hence ignore that our world is three-dimensional. Further, only few works consider the compositional nature of scenes. Our key hypothesis is that incorporating a compositional 3D scene representation into the generative model leads to more controllable image synthesis. Representing sce…
The Chinese University of Hong Kong（香港中文大学）；Nanyang Technological University（南洋理工大学）；Centre of Perceptual and Interactive Intelligence（感知与交互智能研究中心）
We revisit human motion synthesis, a task useful in various real world applications, in this paper. Whereas a number of methods have been developed previously for this task, they are often limited in two aspects: focusing on the poses while leaving the location movement behind, and ignoring the impact of the environment on the human motion. In this paper, we propose a new framework, with the interaction between the scene and the human motion taken into account. Considering the uncertainty of human motion, we formulate this task as a generative task, whose objective is to generate plausible hum…
South China University of Technology（华南理工大学）；Technical University of Munich（慕尼黑工业大学）；Peng Cheng Laboratory（鹏城实验室）
We address the challenge of recovering an underlying scene geometry and colors from a sparse set of RGBD view observations. In this work, we present a new solution termed RGBD$^2$ that sequentially generates novel RGBD views along a camera trajectory, and the scene geometry is simply the fusion result of these views. More specifically, we maintain an intermediate surface mesh used for rendering new RGBD views, which subsequently becomes complete by an inpainting network; each rendered RGBD view is later back-projected as a partial surface and is supplemented into the intermediate mesh. The use…
3D-aware image synthesis has attracted increasing interest as it models the 3D nature of our real world. However, performing realistic object-level editing of the generated images in the multi-object scenario still remains a challenge. Recently, a 2D GAN termed BlobGAN has demonstrated great multi-object editing capabilities on real-world indoor scene datasets. In this work, we propose BlobGAN-3D, which is a 3D-aware improvement of the original 2D BlobGAN. We enable explicit camera pose control while maintaining the disentanglement for individual objects in the scene by extending the 2D blobs …
Despite increasingly realistic image quality, recent 3D image generative models often operate on 3D volumes of fixed extent with limited camera motions. We investigate the task of unconditionally synthesizing unbounded nature scenes, enabling arbitrarily large camera motion while maintaining a persistent 3D world model. Our scene representation consists of an extendable, planar scene layout grid, which can be rendered from arbitrary camera poses via a 3D decoder and volume rendering, and a panoramic skydome. Based on this representation, we learn a generative world model solely from single-vie…
We capitalize on large amounts of unlabeled video in order to learn a model of scene dynamics for both video recognition tasks (e.g. action classification) and video generation tasks (e.g. future prediction). We propose a generative adversarial network for video with a spatio-temporal convolutional architecture that untangles the scene's foreground from the background. Experiments suggest this model can generate tiny videos up to a second at full frame rate better than simple baselines, and we show its utility at predicting plausible futures of static images. Moreover, experiments and visualiz…
Humans can imagine a scene from a sound. We want machines to do so by using conditional generative adversarial networks (GANs). By applying the techniques including spectral norm, projection discriminator and auxiliary classifier, compared with naive conditional GAN, the model can generate images with better quality in terms of both subjective and objective evaluations. Almost three-fourth of people agree that our model have the ability to generate images related to sounds. By inputting different volumes of the same sound, our model output different scales of changes based on the volumes, show…
National Key Laboratory of General Artificial Intelligence, BIGAI（北京通用人工智能研究院通用人工智能国家重点实验室）；Tsinghua University（清华大学）；Peking University（北京大学）；Beijing Institute of Technology（北京理工大学）
We introduce SceneDiffuser, a conditional generative model for 3D scene understanding. SceneDiffuser provides a unified model for solving scene-conditioned generation, optimization, and planning. In contrast to prior works, SceneDiffuser is intrinsically scene-aware, physics-based, and goal-oriented. With an iterative sampling strategy, SceneDiffuser jointly formulates the scene-aware generation, physics-based optimization, and goal-oriented planning via a diffusion-based denoising process in a fully differentiable fashion. Such a design alleviates the discrepancies among different modules and…
Scene Graph-Guided Generative AI Framework for Synthesizing and Evaluating Industrial Hazard Scenarios
Ph.D. Student, Dept. of Civil Eng., University of Texas at Arlington. E-mail；Assistant Professor, Dept. of Computer Sci. \& Eng., University of Texas at Arlington. E-mail；Assistant Professor, Dept. of Civil Eng., University of Texas at Arlington. E-mail
Technical University of Munich（慕尼黑工业大学）；TUM Department of Civil, Geo and Environmental Engineering（慕尼黑工业大学土木工程、地质与环境工程系）
We present a new two-stage pipeline for predicting frames of traffic scenes where relevant objects can still reliably be detected. Using a recent video prediction network, we first generate a sequence of future frames based on past frames. A second network then enhances these frames in order to make them appear more realistic. This ensures the quality of the predicted frames to be sufficient to enable accurate detection of objects, which is especially important for autonomously driving cars. To verify this two-stage approach, we conducted experiments on the Cityscapes dataset. For enhancing, w…
University of Trento（特伦托大学）；University of Oxford（牛津大学）；Texas State University（德克萨斯州立大学）；Huawei Research Ireland（华为爱尔兰研究院）
In this paper, we address the task of semantic-guided scene generation. One open challenge in scene generation is the difficulty of the generation of small objects and detailed local texture, which has been widely observed in global image-level generation methods. To tackle this issue, in this work we consider learning the scene generation in a local context, and correspondingly design a local class-specific generative network with semantic maps as a guidance, which separately constructs and learns sub-generators concentrating on the generation of different classes, and is able to provide more…
Beihang University（北京航空航天大学）；Microsoft Research Asia（微软亚洲研究院）
We present a method for creating 3D indoor scenes with a generative model learned from a collection of semantic-segmented depth images captured from different unknown scenes. Given a room with a specified size, our method automatically generates 3D objects in a room from a randomly sampled latent code. Different from existing methods that represent an indoor scene with the type, location, and other properties of objects in the room and learn the scene layout from a collection of complete 3D indoor scenes, our method models each indoor scene as a 3D semantic scene volume and learns a volumetric…
Kyushu University（九州大学）；Jet Propulsion Laboratory, California Institute of Technology（加州理工学院喷气推进实验室）
3D LiDAR sensors are indispensable for the robust vision of autonomous mobile robots. However, deploying LiDAR-based perception algorithms often fails due to a domain gap from the training environment, such as inconsistent angular resolution and missing properties. Existing studies have tackled the issue by learning inter-domain mapping, while the transferability is constrained by the training configuration and the training is susceptible to peculiar lossy noises called ray-drop. To address the issue, this paper proposes a generative model of LiDAR range images applicable to the data-level dom…
Iran Broadcasting University (IRIBU)（伊朗广播大学（IRIBU））；Alpha Reality
Indoor positioning aims at navigation inside areas with no GPS-data availability and could be employed in many applications such as augmented reality, autonomous driving specially inside closed areas and tunnels. In this paper, a deep neural network-based architecture has been proposed to address this problem. In this regard, a tandem set of convolutional neural networks, as well as a Pix2Pix GAN network have been leveraged to perform as the scene classifier, scene RGB image to point cloud converter, and position regressor, respectively. The proposed architecture outperforms the previous works…
University of Oxford（牛津大学）；University College London（伦敦大学学院）；Niantic；Adobe Research（Adobe研究院）
We present RELATE, a model that learns to generate physically plausible scenes and videos of multiple interacting objects. Similar to other generative approaches, RELATE is trained end-to-end on raw, unlabeled data. RELATE combines an object-centric GAN formulation with a model that explicitly accounts for correlations between individual objects. This allows the model to generate realistic scenes and videos from a physically-interpretable parameterization. Furthermore, we show that modeling the object correlation is necessary to learn to disentangle object positions and identity. We find that …
We propose an unsupervised, mid-level representation for a generative model of scenes. The representation is mid-level in that it is neither per-pixel nor per-image; rather, scenes are modeled as a collection of spatial, depth-ordered "blobs" of features. Blobs are differentiably placed onto a feature grid that is decoded into an image by a generative adversarial network. Due to the spatial uniformity of blobs and the locality inherent to convolution, our network learns to associate different blobs with different entities in a scene and to arrange these blobs to capture scene layout. We demons…
Autonomous Vision Group（自主视觉小组）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）；University of Tübingen（蒂宾根大学）
While 2D generative adversarial networks have enabled high-resolution image synthesis, they largely lack an understanding of the 3D world and the image formation process. Thus, they do not provide precise control over camera viewpoint or object pose. To address this problem, several recent approaches leverage intermediate voxel-based representations in combination with differentiable rendering. However, existing methods either produce low image resolution or fall short in disentangling camera and scene properties, e.g., the object identity may vary with the viewpoint. In this paper, we propose…
SceneCraft: Interactive System for Image Editing via Scene Graph
University of Science, Ho Chi Minh, Vietnam（胡志明市理科大学）；Vietnam National University, Ho Chi Minh, Vietnam（越南国家大学胡志明市）；University of Dayton, Dayton, Ohio, USA（代顿大学）
University of Guelph（圭尔夫大学）；Vector Institute for Artificial Intelligence（人工智能向量研究所）；Element AI（元素人工智能公司）；University of Cambridge（剑桥大学）；Mila（米拉人工智能研究所）；Université de Montréal（蒙特利尔大学）；Concordia University（康考迪亚大学）
Inferring objects and their relationships from an image in the form of a scene graph is useful in many applications at the intersection of vision and language. We consider a challenging problem of compositional generalization that emerges in this task due to a long tail data distribution. Current scene graph generation models are trained on a tiny fraction of the distribution corresponding to the most frequent compositions, e.g. <cup, on, table>. However, test images might contain zero- and few-shot compositions of objects and relationships, e.g. <cup, on, surfboard>. Despite each of the objec…
Institut national de la recherche scientifique (INRS-EMT)（国家科学研究院（INRS-EMT））
In this work, we introduce a two-step framework for generative modeling of temporal data. Specifically, the generative adversarial networks (GANs) setting is employed to generate synthetic scenes of moving objects. To do so, we propose a two-step training scheme within which: a generator of static frames is trained first. Afterwards, a recurrent model is trained with the goal of providing a sequence of inputs to the previously trained frames generator, thus yielding scenes which look natural. The adversarial setting is employed in both training steps. However, with the aim of avoiding known tr…
We propose a novel and unified Cycle in Cycle Generative Adversarial Network (C2GAN) for generating human faces, hands, bodies, and natural scenes. Our proposed C2GAN is a cross-modal model exploring the joint exploitation of the input image data and guidance data in an interactive manner. C2GAN contains two different generators, i.e., an image-generation generator and a guidance-generation generator. Both generators are mutually connected and trained in an end-to-end fashion and explicitly form three cycled subnets, i.e., one image generation cycle and two guidance generation cycles. Each cyc…
