Although recent complex scene conditional generation models generate increasingly appealing scenes, it is very hard to assess which models perform better and why. This is often due to models being trained to fit different data splits, and defining their own experimental setups. In this paper, we propose a methodology to compare complex scene conditional generation models, and provide an in-depth analysis that assesses the ability of each model to (1) fit the training distribution and hence perform well on seen conditionings, (2) to generalize to unseen conditionings composed of seen object combinations, and (3) generalize to unseen conditionings composed of unseen object combinations. As a result, we observe that recent methods are able to generate recognizable scenes given seen conditionings, and exploit compositionality to generalize to unseen conditionings with seen object combinations. However, all methods suffer from noticeable image quality degradation when asked to generate images from conditionings composed of unseen object combinations. Moreover, through our analysis, we identify the advantages of different pipeline components, and find that (1) encouraging compositionality through instance-wise spatial conditioning normalizations increases robustness to both types of unseen conditionings, (2) using semantically aware losses such as the scene-graph perceptual similarity helps improve some dimensions of the generation process, and (3) enhancing the quality of generated masks and the quality of the individual objects are crucial steps to improve robustness to both types of unseen conditionings.
Relative pose regressors (RPRs) localize a camera by estimating its relative translation and rotation to a pose-labelled reference. Unlike scene coordinate regression and absolute pose regression methods, which learn absolute scene parameters, RPRs can (theoretically) localize in unseen environments, since they only learn the residual pose between camera pairs. In practice, however, the performance of RPRs is significantly degraded in unseen scenes. In this work, we propose to aggregate paired feature maps into latent codes, instead of operating on global image descriptors, in order to improve…
Contextual Robotics Institute（情境机器人研究所）；University of California, San Diego（加州大学圣地亚哥分校）
In recent years, there has been a rapid increase in the number of service robots deployed for aiding people in their daily activities. Unfortunately, most of these robots require human input for training in order to do tasks in indoor environments. Successful domestic navigation often requires access to semantic information about the environment, which can be learned without human guidance. In this paper, we propose a set of DEDUCE - Diverse scEne Detection methods in Unseen Challenging Environments algorithms which incorporate deep fusion models derived from scene recognition systems and obje…
Middle East Technical University（中东技术大学）；HAVELSAN Inc.（哈维尔桑公司）
Image caption generation is one of the most challenging problems at the intersection of vision and language domains. In this work, we propose a realistic captioning task where the input scenes may incorporate visual objects with no corresponding visual or textual training examples. For this problem, we propose a detection-driven approach that consists of a single-stage generalized zero-shot detection model to recognize and localize instances of both seen and unseen classes, and a template-based captioning model that transforms detections into sentences. To improve the generalized zero-shot det…
GEN3D: Generating Domain-Free 3D Scenes from a Single Image
Shenzhen International Graduate School, Tsinghua University, Shenzhen, China（清华大学深圳国际研究生院）；Central Media Technology Institute, Huawei, Shenzhen, China（华为中央媒体技术研究所）
One-Shot Crowd Counting With Density Guidance For Scene Adaptation
Jiangsu Key Laboratory of Intelligent Weather Forecasting and Applications Based on Big Data（江苏大数据智能天气预报与应用重点实验室）；State Key Laboratory of Climate System Prediction and Risk Management (CPRM)（气候变化预测与风险管理国家重点实验室）；ICAR/CIC-FEMD/KLME/ILCEC；Nanjing University of Information Science and Technology（南京信息工程大学）；School of Artificial Intelligence, OPtics and ElectroNics, Northwestern Polytechnical University（人工智能、光学与电子学学院，西北工业大学）；School of Computer Science, Wuhan University（武汉大学计算机学院）；School of Computer Science and Engineering, Nanjing University of Science and Technology（南京理工大学计算机科学与工程学院）
Tufts University（塔夫茨大学）；Bosch Center for Artificial Intelligence（博世人工智能中心）；Carnegie Mellon University（卡内基梅隆大学）
Generalisation to unseen contexts remains a challenge for embodied navigation agents. In the context of semantic audio-visual navigation (SAVi) tasks, the notion of generalisation should include both generalising to unseen indoor visual scenes as well as generalising to unheard sounding objects. However, previous SAVi task definitions do not include evaluation conditions on truly novel sounding objects, resorting instead to evaluating agents on unheard sound clips of known objects; meanwhile, previous SAVi methods do not include explicit mechanisms for incorporating domain knowledge about obje…
LG AI Research（LG AI研究院）；KAIST（韩国科学技术院）；Korea University（高丽大学）；Sogang University（西江大学）
Enhancing the generalization capability of deep neural networks to unseen domains is crucial for safety-critical applications in the real world such as autonomous driving. To address this issue, this paper proposes a novel instance selective whitening loss to improve the robustness of the segmentation networks for unseen domains. Our approach disentangles the domain-specific style and domain-invariant content encoded in higher-order statistics (i.e., feature covariance) of the feature representations and selectively removes only the style information causing domain shift. As shown in Fig. 1, o…
Algolux（Algolux公司）；Technical University of Munich（慕尼黑工业大学）；Princeton University（普林斯顿大学）
Recent implicit neural rendering methods have demonstrated that it is possible to learn accurate view synthesis for complex scenes by predicting their volumetric density and color supervised solely by a set of RGB images. However, existing methods are restricted to learning efficient representations of static scenes that encode all scene objects into a single neural network, and lack the ability to represent dynamic scenes and decompositions into individual scene objects. In this work, we present the first neural rendering method that decomposes dynamic scenes into scene graphs. We propose a l…
Recent years have witnessed some exciting developments in the domain of generating images from scene-based text descriptions. These approaches have primarily focused on generating images from a static text description and are limited to generating images in a single pass. They are unable to generate an image interactively based on an incrementally additive text description (something that is more intuitive and similar to the way we describe an image). We propose a method to generate an image incrementally based on a sequence of graphs of scene descriptions (scene-graphs). We propose a recurren…
Dynamic scene graph generation from a video is challenging due to the temporal dynamics of the scene and the inherent temporal fluctuations of predictions. We hypothesize that capturing long-term temporal dependencies is the key to effective generation of dynamic scene graphs. We propose to learn the long-term dependencies in a video by capturing the object-level consistency and inter-object relationship dynamics over object-level long-term tracklets using transformers. Experimental results demonstrate that our Dynamic Scene Graph Detection Transformer (DSG-DETR) outperforms state-of-the-art m…
Generating Multimodal Driving Scenes via Next-Scene Prediction
School of Software Engineering, XJTU（西安交通大学软件学院）；Horizon Robotics（地平线机器人）；School of Computer and Communication Sciences, EPFL（洛桑联邦理工学院计算机与通信科学学院）；University of Chinese Academy of Sciences（中国科学院大学）
Chinese Univ. of Hong Kong（香港中文大学）；Carnegie Mellon Univ.（卡内基梅隆大学）；University of Toronto（多伦多大学）
This paper proposes a novel framework for generating lingual descriptions of indoor scenes. Whereas substantial efforts have been made to tackle this problem, previous approaches focusing primarily on generating a single sentence for each image, which is not sufficient for describing complex scenes. We attempt to go beyond this, by generating coherent descriptions with multiple sentences. Our approach is distinguished from conventional ones in several aspects: (1) a 3D visual parsing system that jointly infers objects, attributes, and relations; (2) a generative grammar learned automatically f…
Advancing Complex Wide-Area Scene Understanding with Hierarchical Coresets Selection
Institute of Software Chinese Academy of Sciences（中国科学院软件研究所）；University of the Chinese Academy of Sciences（中国科学院大学）；Beijing University of Technology（北京理工大学）
Fondazione Bruno Kessler (FBK)（布鲁诺·凯斯勒基金会）；University of Trento（特伦托大学）；Queen Mary University of London（伦敦大学玛丽女王学院）；Idiap Research Institute（伊迪亚普研究所）；École polytechnique fédérale de Lausanne (EPFL)（洛桑联邦理工学院）
Open-Vocabulary Domain Generalization in Urban-Scene Segmentation
Department of Information Engineering and Computer Science, University of Trento（信息工程与计算机科学系，特伦托大学）；School of Computer Science and Information Engineering, Hefei University of Technology（计算机科学与信息工程学院，合肥工业大学）
Rensselaer Polytechnic Institute（伦斯勒理工学院）；Air Force Research Laboratory（美国空军研究实验室）
Driven by successes in deep learning, computer vision research has begun to move beyond object detection and image classification to more sophisticated tasks like image captioning or visual question answering. Motivating such endeavors is the desire for models to capture not only objects present in an image, but more fine-grained aspects of a scene such as relationships between objects and their attributes. Scene graphs provide a formal construct for capturing these aspects of an image. Despite this, there have been only a few recent efforts to generate scene graphs from imagery. Previous work…
Feature generating networks face to the most important question, which is the fitting difference (inconsistence) of the distribution between the generated feature and the real data. This inconsistence further influence the performance of the networks model, because training samples from seen classes is disjointed with testing samples from unseen classes in zero-shot learning (ZSL). In generalization zero-shot learning (GZSL), testing samples come from not only seen classes but also unseen classes for closer to the practical situation. Therefore, most of feature generating networks difficultly …
From Semantics, Scene to Instance-awareness: Distilling Foundation Model for Grounded Open-vocabulary Situation Recognition
National University of Singapore（新加坡国立大学）；Nanyang Technological University（南洋理工大学）；Huazhong University of Science and Technology（华中科技大学）；The Hong Kong Polytechnic University（香港理工大学）
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…
University of Virginia（弗吉尼亚大学）；IBM Thomas J. Watson Research Center（IBM托马斯·J·沃森研究中心）
In this paper, we propose Text2Scene, a model that generates various forms of compositional scene representations from natural language descriptions. Unlike recent works, our method does NOT use Generative Adversarial Networks (GANs). Text2Scene instead learns to sequentially generate objects and their attributes (location, size, appearance, etc) at every time step by attending to different parts of the input text and the current status of the generated scene. We show that under minor modifications, the proposed framework can handle the generation of different forms of scene representations, i…
Monash University（莫纳什大学）；University of Electronic Science and Technology of China（电子科技大学）
Scene graph generation (SGG) is a fundamental task aimed at detecting visual relations between objects in an image. The prevailing SGG methods require all object classes to be given in the training set. Such a closed setting limits the practical application of SGG. In this paper, we introduce open-vocabulary scene graph generation, a novel, realistic and challenging setting in which a model is trained on a set of base object classes but is required to infer relations for unseen target object classes. To this end, we propose a two-step method that firstly pre-trains on large amounts of coarse-g…
Beihang University（北航大学）；University of Durham（达勒姆大学）；State Key Laboratory of Virtual Reality Technology and Systems（虚拟现实技术与系统国家重点实验室）；Zhongguancun Laboratory（中关村实验室）
Simon Fraser University（西蒙弗雷泽大学）；Borealis AI（北极光人工智能）；University of British Columbia（不列颠哥伦比亚大学）
Recently there is an increasing interest in scene generation within the research community. However, models used for generating scene layouts from textual description largely ignore plausible visual variations within the structure dictated by the text. We propose LayoutVAE, a variational autoencoder based framework for generating stochastic scene layouts. LayoutVAE is a versatile modeling framework that allows for generating full image layouts given a label set, or per label layouts for an existing image given a new label. In addition, it is also capable of detecting unusual layouts, potential…
