Multi-view implicit scene reconstruction methods have become increasingly popular due to their ability to represent complex scene details. Recent efforts have been devoted to improving the representation of input information and to reducing the number of views required to obtain high quality reconstructions. Yet, perhaps surprisingly, the study of which views to select to maximally improve scene understanding remains largely unexplored. We propose an uncertainty-driven active vision approach for implicit scene reconstruction, which leverages occupancy uncertainty accumulated across the scene using volume rendering to select the next view to acquire. To this end, we develop an occupancy-based reconstruction method which accurately represents scenes using either 2D or 3D supervision. We evaluate our proposed approach on the ABC dataset and the in the wild CO3D dataset, and show that: (1) we are able to obtain high quality state-of-the-art occupancy reconstructions; (2) our perspective conditioned uncertainty definition is effective to drive improvements in next best view selection and outperforms strong baseline approaches; and (3) we can further improve shape understanding by performing a gradient-based search on the view selection candidates. Overall, our results highlight the importance of view selection for implicit scene reconstruction, making it a promising avenue to explore further.
Modelling long-range dependencies is critical for scene understanding tasks in computer vision. Although convolution neural networks (CNNs) have excelled in many vision tasks, they are still limited in capturing long-range structured relationships as they typically consist of layers of local kernels. A fully-connected graph, such as the self-attention operation in Transformers, is beneficial for such modelling, however, its computational overhead is prohibitive. In this paper, we propose a dynamic graph message passing network, that significantly reduces the computational complexity compared to related works modelling a fully-connected graph. This is achieved by adaptively sampling nodes in the graph, conditioned on the input, for message passing. Based on the sampled nodes, we dynamically predict node-dependent filter weights and the affinity matrix for propagating information between them. This formulation allows us to design a self-attention module, and more importantly a new Transformer-based backbone network, that we use for both image classification pretraining, and for addressing various downstream tasks (object detection, instance and semantic segmentation). Using this model, we show significant improvements with respect to strong, state-of-the-art baselines on four different tasks. Our approach also outperforms fully-connected graphs while using substantially fewer floating-point operations and parameters. Code and models will be made publicly available at https://github.com/fudan-zvg/DGMN2
Abstract semantic 3D scene understanding is a problem of critical importance in robotics. As robots still lack the common-sense knowledge about household objects and locations of an average human, we investigate the use of pre-trained language models to impart common sense for scene understanding. We introduce and compare a wide range of scene classification paradigms that leverage language only (zero-shot, embedding-based, and structured-language) or vision and language (zero-shot and fine-tuned). We find that the best approaches in both categories yield $\sim 70\%$ room classification accuracy, exceeding the performance of pure-vision and graph classifiers. We also find such methods demonstrate notable generalization and transfer capabilities stemming from their use of language.
Recent advances in deep learning technology have triggered radical progress in the autonomy of ground vehicles. Marine coastal Autonomous Surface Vehicles (ASVs) that are regularly used for surveillance, monitoring and other routine tasks can benefit from this autonomy. Long haul deep sea transportation activities are additional opportunities. These two use cases present very different terrains -- the first being coastal waters -- with many obstacles, structures and human presence while the latter is mostly devoid of such obstacles. Variations in environmental conditions are common to both terrains. Robust labeled datasets mapping such terrains are crucial in improving the situational awareness that can drive autonomy. However, there are only limited such maritime datasets available and these primarily consist of optical images. Although, Long Wave Infrared (LWIR) is a strong complement to the optical spectrum that helps in extreme light conditions, a labeled public dataset with LWIR images does not currently exist. In this paper, we fill this gap by presenting a labeled dataset of over 2,900 LWIR segmented images captured in coastal maritime environment under diverse conditions. The images are labeled using instance segmentation and classified in seven categories -- sky, water, obstacle, living obstacle, bridge, self and background. We also evaluate this dataset across three deep learning architectures (UNet, PSPNet, DeepLabv3) and provide detailed analysis of its efficacy. While the dataset focuses on the coastal terrain it can equally help deep sea use cases. Such terrain would have less traffic, and the classifier trained on cluttered environment would be able to handle sparse scenes effectively. We share this dataset with the research community with the hope that it spurs new scene understanding capabilities in the maritime environment.
In multi-task learning (MTL) for visual scene understanding, it is crucial to transfer useful information between multiple tasks with minimal interferences. In this paper, we propose a novel architecture that effectively transfers informative features by applying the attention mechanism to the multi-scale features of the tasks. Since applying the attention module directly to all possible features in terms of scale and task requires a high complexity, we propose to apply the attention module sequentially for the task and scale. The cross-task attention module (CTAM) is first applied to facilitate the exchange of relevant information between the multiple task features of the same scale. The cross-scale attention module (CSAM) then aggregates useful information from feature maps at different resolutions in the same task. Also, we attempt to capture long range dependencies through the self-attention module in the feature extraction network. Extensive experiments demonstrate that our method achieves state-of-the-art performance on the NYUD-v2 and PASCAL-Context dataset.
Holistic scene understanding is pivotal for the performance of autonomous machines. In this paper we propose a new end-to-end model for performing semantic segmentation and depth completion jointly. The vast majority of recent approaches have developed semantic segmentation and depth completion as independent tasks. Our approach relies on RGB and sparse depth as inputs to our model and produces a dense depth map and the corresponding semantic segmentation image. It consists of a feature extractor, a depth completion branch, a semantic segmentation branch and a joint branch which further processes semantic and depth information altogether. The experiments done on Virtual KITTI 2 dataset, demonstrate and provide further evidence, that combining both tasks, semantic segmentation and depth completion, in a multi-task network can effectively improve the performance of each task. Code is available at https://github.com/juanb09111/semantic depth.
Recognizing 3D part instances from a 3D point cloud is crucial for 3D structure and scene understanding. Several learning-based approaches use semantic segmentation and instance center prediction as training tasks and fail to further exploit the inherent relationship between shape semantics and part instances. In this paper, we present a new method for 3D part instance segmentation. Our method exploits semantic segmentation to fuse nonlocal instance features, such as center prediction, and further enhances the fusion scheme in a multi- and cross-level way. We also propose a semantic region center prediction task to train and leverage the prediction results to improve the clustering of instance points. Our method outperforms existing methods with a large-margin improvement in the PartNet benchmark. We also demonstrate that our feature fusion scheme can be applied to other existing methods to improve their performance in indoor scene instance segmentation tasks.
Text-VQA aims at answering questions that require understanding the textual cues in an image. Despite the great progress of existing Text-VQA methods, their performance suffers from insufficient human-labeled question-answer (QA) pairs. However, we observe that, in general, the scene text is not fully exploited in the existing datasets -- only a small portion of the text in each image participates in the annotated QA activities. This results in a huge waste of useful information. To address this deficiency, we develop a new method to generate high-quality and diverse QA pairs by explicitly utilizing the existing rich text available in the scene context of each image. Specifically, we propose, TAG, a text-aware visual question-answer generation architecture that learns to produce meaningful, and accurate QA samples using a multimodal transformer. The architecture exploits underexplored scene text information and enhances scene understanding of Text-VQA models by combining the generated QA pairs with the initial training data. Extensive experimental results on two well-known Text-VQA benchmarks (TextVQA and ST-VQA) demonstrate that our proposed TAG effectively enlarges the training data that helps improve the Text-VQA performance without extra labeling effort. Moreover, our model outperforms state-of-the-art approaches that are pre-trained with extra large-scale data. Code is available at https://github.com/HenryJunW/TAG.
We present MonteBoxFinder, a method that, given a noisy input point cloud, fits cuboids to the input scene. Our primary contribution is a discrete optimization algorithm that, from a dense set of initially detected cuboids, is able to efficiently filter good boxes from the noisy ones. Inspired by recent applications of MCTS to scene understanding problems, we develop a stochastic algorithm that is, by design, more efficient for our task. Indeed, the quality of a fit for a cuboid arrangement is invariant to the order in which the cuboids are added into the scene. We develop several search baselines for our problem and demonstrate, on the ScanNet dataset, that our approach is more efficient and precise. Finally, we strongly believe that our core algorithm is very general and that it could be extended to many other problems in 3D scene understanding.
Large-scale deployment of autonomous vehicles has been continually delayed due to safety concerns. On the one hand, comprehensive scene understanding is indispensable, a lack of which would result in vulnerability to rare but complex traffic situations, such as the sudden emergence of unknown objects. However, reasoning from a global context requires access to sensors of multiple types and adequate fusion of multi-modal sensor signals, which is difficult to achieve. On the other hand, the lack of interpretability in learning models also hampers the safety with unverifiable failure causes. In this paper, we propose a safety-enhanced autonomous driving framework, named Interpretable Sensor Fusion Transformer(InterFuser), to fully process and fuse information from multi-modal multi-view sensors for achieving comprehensive scene understanding and adversarial event detection. Besides, intermediate interpretable features are generated from our framework, which provide more semantics and are exploited to better constrain actions to be within the safe sets. We conducted extensive experiments on CARLA benchmarks, where our model outperforms prior methods, ranking the first on the public CARLA Leaderboard. Our code will be made available at https://github.com/opendilab/InterFuser
Accurate and fast scene understanding is one of the challenging task for autonomous driving, which requires to take full advantage of LiDAR point clouds for semantic segmentation. In this paper, we present a \textbf{concise} and \textbf{efficient} image-based semantic segmentation network, named \textbf{CENet}. In order to improve the descriptive power of learned features and reduce the computational as well as time complexity, our CENet integrates the convolution with larger kernel size instead of MLP, carefully-selected activation functions, and multiple auxiliary segmentation heads with corresponding loss functions into architecture. Quantitative and qualitative experiments conducted on publicly available benchmarks, SemanticKITTI and SemanticPOSS, demonstrate that our pipeline achieves much better mIoU and inference performance compared with state-of-the-art models. The code will be available at https://github.com/huixiancheng/CENet.
We study open-world 3D scene understanding, a family of tasks that require agents to reason about their 3D environment with an open-set vocabulary and out-of-domain visual inputs - a critical skill for robots to operate in the unstructured 3D world. Towards this end, we propose Semantic Abstraction (SemAbs), a framework that equips 2D Vision-Language Models (VLMs) with new 3D spatial capabilities, while maintaining their zero-shot robustness. We achieve this abstraction using relevancy maps extracted from CLIP, and learn 3D spatial and geometric reasoning skills on top of those abstractions in a semantic-agnostic manner. We demonstrate the usefulness of SemAbs on two open-world 3D scene understanding tasks: 1) completing partially observed objects and 2) localizing hidden objects from language descriptions. Experiments show that SemAbs can generalize to novel vocabulary, materials/lighting, classes, and domains (i.e., real-world scans) from training on limited 3D synthetic data. Code and data is available at https://semantic-abstraction.cs.columbia.edu/
Instance segmentation on point clouds is crucially important for 3D scene understanding. Most SOTAs adopt distance clustering, which is typically effective but does not perform well in segmenting adjacent objects with the same semantic label (especially when they share neighboring points). Due to the uneven distribution of offset points, these existing methods can hardly cluster all instance points. To this end, we design a novel divide-and-conquer strategy named PBNet that binarizes each point and clusters them separately to segment instances. Our binary clustering divides offset instance points into two categories: high and low density points (HPs vs. LPs). Adjacent objects can be clearly separated by removing LPs, and then be completed and refined by assigning LPs via a neighbor voting method. To suppress potential over-segmentation, we propose to construct local scenes with the weight mask for each instance. As a plug-in, the proposed binary clustering can replace traditional distance clustering and lead to consistent performance gains on many mainstream baselines. A series of experiments on ScanNetV2 and S3DIS datasets indicate the superiority of our model. In particular, PBNet ranks first on the ScanNetV2 official benchmark challenge, achieving the highest mAP. Code will be available publicly at https://github.com/weiguangzhao/PBNet.
Existing research addresses scene graph generation (SGG) -- a critical technology for scene understanding in images -- from a detection perspective, i.e., objects are detected using bounding boxes followed by prediction of their pairwise relationships. We argue that such a paradigm causes several problems that impede the progress of the field. For instance, bounding box-based labels in current datasets usually contain redundant classes like hairs, and leave out background information that is crucial to the understanding of context. In this work, we introduce panoptic scene graph generation (PSG), a new problem task that requires the model to generate a more comprehensive scene graph representation based on panoptic segmentations rather than rigid bounding boxes. A high-quality PSG dataset, which contains 49k well-annotated overlapping images from COCO and Visual Genome, is created for the community to keep track of its progress. For benchmarking, we build four two-stage baselines, which are modified from classic methods in SGG, and two one-stage baselines called PSGTR and PSGFormer, which are based on the efficient Transformer-based detector, i.e., DETR. While PSGTR uses a set of queries to directly learn triplets, PSGFormer separately models the objects and relations in the form of queries from two Transformer decoders, followed by a prompting-like relation-object matching mechanism. In the end, we share insights on open challenges and future directions.
In this paper, we study a problem of egocentric scene understanding, i.e., predicting depths and surface normals from an egocentric image. Egocentric scene understanding poses unprecedented challenges: (1) due to large head movements, the images are taken from non-canonical viewpoints (i.e., tilted images) where existing models of geometry prediction do not apply; (2) dynamic foreground objects including hands constitute a large proportion of visual scenes. These challenges limit the performance of the existing models learned from large indoor datasets, such as ScanNet and NYUv2, which comprise predominantly upright images of static scenes. We present a multimodal spatial rectifier that stabilizes the egocentric images to a set of reference directions, which allows learning a coherent visual representation. Unlike unimodal spatial rectifier that often produces excessive perspective warp for egocentric images, the multimodal spatial rectifier learns from multiple directions that can minimize the impact of the perspective warp. To learn visual representations of the dynamic foreground objects, we present a new dataset called EDINA (Egocentric Depth on everyday INdoor Activities) that comprises more than 500K synchronized RGBD frames and gravity directions. Equipped with the multimodal spatial rectifier and the EDINA dataset, our proposed method on single-view depth and surface normal estimation significantly outperforms the baselines not only on our EDINA dataset, but also on other popular egocentric datasets, such as First Person Hand Action (FPHA) and EPIC-KITCHENS.
Advances in deep learning have resulted in steady progress in computer vision with improved accuracy on tasks such as object detection and semantic segmentation. Nevertheless, deep neural networks are vulnerable to adversarial attacks, thus presenting a challenge in reliable deployment. Two of the prominent tasks in 3D scene-understanding for robotics and advanced drive assistance systems are monocular depth and pose estimation, often learned together in an unsupervised manner. While studies evaluating the impact of adversarial attacks on monocular depth estimation exist, a systematic demonstration and analysis of adversarial perturbations against pose estimation are lacking. We show how additive imperceptible perturbations can not only change predictions to increase the trajectory drift but also catastrophically alter its geometry. We also study the relation between adversarial perturbations targeting monocular depth and pose estimation networks, as well as the transferability of perturbations to other networks with different architectures and losses. Our experiments show how the generated perturbations lead to notable errors in relative rotation and translation predictions and elucidate vulnerabilities of the networks.
Semantic scene understanding is essential for mobile agents acting in various environments. Although semantic segmentation already provides a lot of information, details about individual objects as well as the general scene are missing but required for many real-world applications. However, solving multiple tasks separately is expensive and cannot be accomplished in real time given limited computing and battery capabilities on a mobile platform. In this paper, we propose an efficient multi-task approach for RGB-D scene analysis~(EMSANet) that simultaneously performs semantic and instance segmentation~(panoptic segmentation), instance orientation estimation, and scene classification. We show that all tasks can be accomplished using a single neural network in real time on a mobile platform without diminishing performance - by contrast, the individual tasks are able to benefit from each other. In order to evaluate our multi-task approach, we extend the annotations of the common RGB-D indoor datasets NYUv2 and SUNRGB-D for instance segmentation and orientation estimation. To the best of our knowledge, we are the first to provide results in such a comprehensive multi-task setting for indoor scene analysis on NYUv2 and SUNRGB-D.
We propose a novel method applicable in many scene understanding problems that adapts the Monte Carlo Tree Search (MCTS) algorithm, originally designed to learn to play games of high-state complexity. From a generated pool of proposals, our method jointly selects and optimizes proposals that minimize the objective term. In our first application for floor plan reconstruction from point clouds, our method selects and refines the room proposals, modelled as 2D polygons, by optimizing on an objective function combining the fitness as predicted by a deep network and regularizing terms on the room shapes. We also introduce a novel differentiable method for rendering the polygonal shapes of these proposals. Our evaluations on the recent and challenging Structured3D and Floor-SP datasets show significant improvements over the state-of-the-art, without imposing hard constraints nor assumptions on the floor plan configurations. In our second application, we extend our approach to reconstruct general 3D room layouts from a color image and obtain accurate room layouts. We also show that our differentiable renderer can easily be extended for rendering 3D planar polygons and polygon embeddings. Our method shows high performance on the Matterport3D-Layout dataset, without introducing hard constraints on room layout configurations.
Human-Object Interaction (HOI) detection has received considerable attention in the context of scene understanding. Despite the growing progress on benchmarks, we realize that existing methods often perform unsatisfactorily on distant interactions, where the leading causes are two-fold: 1) Distant interactions are by nature more difficult to recognize than close ones. A natural scene often involves multiple humans and objects with intricate spatial relations, making the interaction recognition for distant human-object largely affected by complex visual context. 2) Insufficient number of distant interactions in benchmark datasets results in under-fitting on these instances. To address these problems, in this paper, we propose a novel two-stage method for better handling distant interactions in HOI detection. One essential component in our method is a novel Far Near Distance Attention module. It enables information propagation between humans and objects, whereby the spatial distance is skillfully taken into consideration. Besides, we devise a novel Distance-Aware loss function which leads the model to focus more on distant yet rare interactions. We conduct extensive experiments on two challenging datasets - HICO-DET and V-COCO. The results demonstrate that the proposed method can surpass existing approaches by a large margin, resulting in new state-of-the-art performance.
Reliable scene understanding is indispensable for modern autonomous systems. Current learning-based methods typically try to maximize their performance based on segmentation metrics that only consider the quality of the segmentation. However, for the safe operation of a system in the real world it is crucial to consider the uncertainty in the prediction as well. In this work, we introduce the novel task of uncertainty-aware panoptic segmentation, which aims to predict per-pixel semantic and instance segmentations, together with per-pixel uncertainty estimates. We define two novel metrics to facilitate its quantitative analysis, the uncertainty-aware Panoptic Quality (uPQ) and the panoptic Expected Calibration Error (pECE). We further propose the novel top-down Evidential Panoptic Segmentation Network (EvPSNet) to solve this task. Our architecture employs a simple yet effective panoptic fusion module that leverages the predicted uncertainties. Furthermore, we provide several strong baselines combining state-of-the-art panoptic segmentation networks with sampling-free uncertainty estimation techniques. Extensive evaluations show that our EvPSNet achieves the new state-of-the-art for the standard Panoptic Quality (PQ), as well as for our uncertainty-aware panoptic metrics. We make the code available at: \url{https://github.com/kshitij3112/EvPSNet}