The driving behavior at urban intersections is very complex. It is thus crucial for autonomous vehicles to comprehensively understand challenging urban traffic scenes in order to navigate intersections and prevent accidents. In this paper, we introduce a stereo vision and 3D digital map based approach to spatially and temporally analyze the traffic situation at urban intersections. Stereo vision is used to detect, classify and track obstacles, while a 3D digital map is used to improve ego-localization and provide context in terms of road-layout information. A probabilistic approach that temporally integrates these geometric, semantic, dynamic and contextual cues is presented. We qualitatively and quantitatively evaluate our proposed technique on real traffic data collected at an urban canyon in Tokyo to demonstrate the efficacy of the system in providing comprehensive awareness of the traffic surroundings.
Realistic 3D indoor scene datasets have enabled significant recent progress in computer vision, scene understanding, autonomous navigation, and 3D reconstruction. But the scale, diversity, and customizability of existing datasets is limited, and it is time-consuming and expensive to scan and annotate more. Fortunately, combinatorics is on our side: there are enough individual rooms in existing 3D scene datasets, if there was but a way to recombine them into new layouts. In this paper, we propose the task of generating novel 3D floor plans from existing 3D rooms. We identify three sub-tasks of this problem: generation of 2D layout, retrieval of compatible 3D rooms, and deformation of 3D rooms to fit the layout. We then discuss different strategies for solving the problem, and design two representative pipelines: one uses available 2D floor plans to guide selection and deformation of 3D rooms; the other learns to retrieve a set of compatible 3D rooms and combine them into novel layouts. We design a set of metrics that evaluate the generated results with respect to each of the three subtasks and show that different methods trade off performance on these subtasks. Finally, we survey downstream tasks that benefit from generated 3D scenes and discuss strategies in selecting the methods most appropriate for the demands of these tasks.
We present a new approach to instill 4D dynamic object priors into learned 3D representations by unsupervised pre-training. We observe that dynamic movement of an object through an environment provides important cues about its objectness, and thus propose to imbue learned 3D representations with such dynamic understanding, that can then be effectively transferred to improved performance in downstream 3D semantic scene understanding tasks. We propose a new data augmentation scheme leveraging synthetic 3D shapes moving in static 3D environments, and employ contrastive learning under 3D-4D constraints that encode 4D invariances into the learned 3D representations. Experiments demonstrate that our unsupervised representation learning results in improvement in downstream 3D semantic segmentation, object detection, and instance segmentation tasks, and moreover, notably improves performance in data-scarce scenarios.
The Depth-aware Video Panoptic Segmentation (DVPS) is a new challenging vision problem that aims to predict panoptic segmentation and depth in a video simultaneously. The previous work solves this task by extending the existing panoptic segmentation method with an extra dense depth prediction and instance tracking head. However, the relationship between the depth and panoptic segmentation is not well explored -- simply combining existing methods leads to competition and needs carefully weight balancing. In this paper, we present PolyphonicFormer, a vision transformer to unify these sub-tasks under the DVPS task and lead to more robust results. Our principal insight is that the depth can be harmonized with the panoptic segmentation with our proposed new paradigm of predicting instance level depth maps with object queries. Then the relationship between the two tasks via query-based learning is explored. From the experiments, we demonstrate the benefits of our design from both depth estimation and panoptic segmentation aspects. Since each thing query also encodes the instance-wise information, it is natural to perform tracking directly with appearance learning. Our method achieves state-of-the-art results on two DVPS datasets (Semantic KITTI, Cityscapes), and ranks 1st on the ICCV-2021 BMTT Challenge video + depth track. Code is available at https://github.com/HarborYuan/PolyphonicFormer .
Advances in LiDAR sensors provide rich 3D data that supports 3D scene understanding. However, due to occlusion and signal miss, LiDAR point clouds are in practice 2.5D as they cover only partial underlying shapes, which poses a fundamental challenge to 3D perception. To tackle the challenge, we present a novel LiDAR-based 3D object detection model, dubbed Behind the Curtain Detector (BtcDet), which learns the object shape priors and estimates the complete object shapes that are partially occluded (curtained) in point clouds. BtcDet first identifies the regions that are affected by occlusion and signal miss. In these regions, our model predicts the probability of occupancy that indicates if a region contains object shapes. Integrated with this probability map, BtcDet can generate high-quality 3D proposals. Finally, the probability of occupancy is also integrated into a proposal refinement module to generate the final bounding boxes. Extensive experiments on the KITTI Dataset and the Waymo Open Dataset demonstrate the effectiveness of BtcDet. Particularly, for the 3D detection of both cars and cyclists on the KITTI benchmark, BtcDet surpasses all of the published state-of-the-art methods by remarkable margins. Code is released (https://github.com/Xharlie/BtcDet}{https://github.com/Xharlie/BtcDet).
Although considerable progress has been made in semantic scene understanding under clear weather, it is still a tough problem under adverse weather conditions, such as dense fog, due to the uncertainty caused by imperfect observations. Besides, difficulties in collecting and labeling foggy images hinder the progress of this field. Considering the success in semantic scene understanding under clear weather, we think it is reasonable to transfer knowledge learned from clear images to the foggy domain. As such, the problem becomes to bridge the domain gap between clear images and foggy images. Unlike previous methods that mainly focus on closing the domain gap caused by fog -- defogging the foggy images or fogging the clear images, we propose to alleviate the domain gap by considering fog influence and style variation simultaneously. The motivation is based on our finding that the style-related gap and the fog-related gap can be divided and closed respectively, by adding an intermediate domain. Thus, we propose a new pipeline to cumulatively adapt style, fog and the dual-factor (style and fog). Specifically, we devise a unified framework to disentangle the style factor and the fog factor separately, and then the dual-factor from images in different domains. Furthermore, we collaborate the disentanglement of three factors with a novel cumulative loss to thoroughly disentangle these three factors. Our method achieves the state-of-the-art performance on three benchmarks and shows generalization ability in rainy and snowy scenes.
Differentiable physics is a powerful tool in computer vision and robotics for scene understanding and reasoning about interactions. Existing approaches have frequently been limited to objects with simple shape or shapes that are known in advance. In this paper, we propose a novel approach to differentiable physics with frictional contacts which represents object shapes implicitly using signed distance fields (SDFs). Our simulation supports contact point calculation even when the involved shapes are nonconvex. Moreover, we propose ways for differentiating the dynamics for the object shape to facilitate shape optimization using gradient-based methods. In our experiments, we demonstrate that our approach allows for model-based inference of physical parameters such as friction coefficients, mass, forces or shape parameters from trajectory and depth image observations in several challenging synthetic scenarios and a real image sequence.
Fully supervised semantic segmentation technologies bring a paradigm shift in scene understanding. However, the burden of expensive labeling cost remains as a challenge. To solve the cost problem, recent studies proposed language model based zero-shot semantic segmentation (L-ZSSS) approaches. In this paper, we address L-ZSSS has a limitation in generalization which is a virtue of zero-shot learning. Tackling the limitation, we propose a language-model-free zero-shot semantic segmentation framework, Spatial and Multi-scale aware Visual Class Embedding Network (SM-VCENet). Furthermore, leveraging vision-oriented class embedding SM-VCENet enriches visual information of the class embedding by multi-scale attention and spatial attention. We also propose a novel benchmark (PASCAL2COCO) for zero-shot semantic segmentation, which provides generalization evaluation by domain adaptation and contains visually challenging samples. In experiments, our SM-VCENet outperforms zero-shot semantic segmentation state-of-the-art by a relative margin in PASCAL-5i benchmark and shows generalization-robustness in PASCAL2COCO benchmark.
Object encoding and identification are vital for robotic tasks such as autonomous exploration, semantic scene understanding, and re-localization. Previous approaches have attempted to either track objects or generate descriptors for object identification. However, such systems are limited to a "fixed" partial object representation from a single viewpoint. In a robot exploration setup, there is a requirement for a temporally "evolving" global object representation built as the robot observes the object from multiple viewpoints. Furthermore, given the vast distribution of unknown novel objects in the real world, the object identification process must be class-agnostic. In this context, we propose a novel temporal 3D object encoding approach, dubbed AirObject, to obtain global keypoint graph-based embeddings of objects. Specifically, the global 3D object embeddings are generated using a temporal convolutional network across structural information of multiple frames obtained from a graph attention-based encoding method. We demonstrate that AirObject achieves the state-of-the-art performance for video object identification and is robust to severe occlusion, perceptual aliasing, viewpoint shift, deformation, and scale transform, outperforming the state-of-the-art single-frame and sequential descriptors. To the best of our knowledge, AirObject is one of the first temporal object encoding methods. Source code is available at https://github.com/Nik-V9/AirObject.
Fine-grained geometry, captured by aggregation of point features in local regions, is crucial for object recognition and scene understanding in point clouds. Nevertheless, existing preeminent point cloud backbones usually incorporate max/average pooling for local feature aggregation, which largely ignores points' positional distribution, leading to inadequate assembling of fine-grained structures. To mitigate this bottleneck, we present an efficient alternative to max pooling, Position Adaptive Pooling (PAPooling), that explicitly models spatial relations among local points using a novel graph representation, and aggregates features in a position adaptive manner, enabling position-sensitive representation of aggregated features. Specifically, PAPooling consists of two key steps, Graph Construction and Feature Aggregation, respectively in charge of constructing a graph with edges linking the center point with every neighboring point in a local region to map their relative positional information to channel-wise attentive weights, and adaptively aggregating local point features based on the generated weights through Graph Convolution Network (GCN). PAPooling is simple yet effective, and flexible enough to be ready to use for different popular backbones like PointNet++ and DGCNN, as a plug-andplay operator. Extensive experiments on various tasks ranging from 3D shape classification, part segmentation to scene segmentation well demonstrate that PAPooling can significantly improve predictive accuracy, while with minimal extra computational overhead. Code will be released.
In this paper, we introduce a new dataset, named InstaOrder, that can be used to understand the geometrical relationships of instances in an image. The dataset consists of 2.9M annotations of geometric orderings for class-labeled instances in 101K natural scenes. The scenes were annotated by 3,659 crowd-workers regarding (1) occlusion order that identifies occluder/occludee and (2) depth order that describes ordinal relations that consider relative distance from the camera. The dataset provides joint annotation of two kinds of orderings for the same instances, and we discover that the occlusion order and depth order are complementary. We also introduce a geometric order prediction network called InstaOrderNet, which is superior to state-of-the-art approaches. Moreover, we propose a dense depth prediction network called InstaDepthNet that uses auxiliary geometric order loss to boost the accuracy of the state-of-the-art depth prediction approach, MiDaS [56].
We present a new learning-based framework S-3D-RCNN that can recover accurate object orientation in SO(3) and simultaneously predict implicit rigid shapes from stereo RGB images. For orientation estimation, in contrast to previous studies that map local appearance to observation angles, we propose a progressive approach by extracting meaningful Intermediate Geometrical Representations (IGRs). This approach features a deep model that transforms perceived intensities from one or two views to object part coordinates to achieve direct egocentric object orientation estimation in the camera coordinate system. To further achieve finer description inside 3D bounding boxes, we investigate the implicit shape estimation problem from stereo images. We model visible object surfaces by designing a point-based representation, augmenting IGRs to explicitly address the unseen surface hallucination problem. Extensive experiments validate the effectiveness of the proposed IGRs, and S-3D-RCNN achieves superior 3D scene understanding performance. We also designed new metrics on the KITTI benchmark for our evaluation of implicit shape estimation.
Scene graph generation (SGG) aims to capture a wide variety of interactions between pairs of objects, which is essential for full scene understanding. Existing SGG methods trained on the entire set of relations fail to acquire complex reasoning about visual and textual correlations due to various biases in training data. Learning on trivial relations that indicate generic spatial configuration like 'on' instead of informative relations such as 'parked on' does not enforce this complex reasoning, harming generalization. To address this problem, we propose a novel framework for SGG training that exploits relation labels based on their informativeness. Our model-agnostic training procedure imputes missing informative relations for less informative samples in the training data and trains a SGG model on the imputed labels along with existing annotations. We show that this approach can successfully be used in conjunction with state-of-the-art SGG methods and improves their performance significantly in multiple metrics on the standard Visual Genome benchmark. Furthermore, we obtain considerable improvements for unseen triplets in a more challenging zero-shot setting.
Multi-task indoor scene understanding is widely considered as an intriguing formulation, as the affinity of different tasks may lead to improved performance. In this paper, we tackle the new problem of joint semantic, affordance and attribute parsing. However, successfully resolving it requires a model to capture long-range dependency, learn from weakly aligned data and properly balance sub-tasks during training. To this end, we propose an attention-based architecture named Cerberus and a tailored training framework. Our method effectively addresses the aforementioned challenges and achieves state-of-the-art performance on all three tasks. Moreover, an in-depth analysis shows concept affinity consistent with human cognition, which inspires us to explore the possibility of weakly supervised learning. Surprisingly, Cerberus achieves strong results using only 0.1%-1% annotation. Visualizations further confirm that this success is credited to common attention maps across tasks. Code and models can be accessed at https://github.com/OPEN-AIR-SUN/Cerberus.
Panoptic segmentation combines instance and semantic predictions, allowing the detection of "things" and "stuff" simultaneously. Effectively approaching panoptic segmentation in remotely sensed data can be auspicious in many challenging problems since it allows continuous mapping and specific target counting. Several difficulties have prevented the growth of this task in remote sensing: (a) most algorithms are designed for traditional images, (b) image labelling must encompass "things" and "stuff" classes, and (c) the annotation format is complex. Thus, aiming to solve and increase the operability of panoptic segmentation in remote sensing, this study has five objectives: (1) create a novel data preparation pipeline for panoptic segmentation, (2) propose an annotation conversion software to generate panoptic annotations; (3) propose a novel dataset on urban areas, (4) modify the Detectron2 for the task, and (5) evaluate difficulties of this task in the urban setting. We used an aerial image with a 0,24-meter spatial resolution considering 14 classes. Our pipeline considers three image inputs, and the proposed software uses point shapefiles for creating samples in the COCO format. Our study generated 3,400 samples with 512x512 pixel dimensions. We used the Panoptic-FPN with two backbones (ResNet-50 and ResNet-101), and the model evaluation considered semantic instance and panoptic metrics. We obtained 93.9, 47.7, and 64.9 for the mean IoU, box AP, and PQ. Our study presents the first effective pipeline for panoptic segmentation and an extensive database for other researchers to use and deal with other data or related problems requiring a thorough scene understanding.
The utility of collocating robots largely depends on the easy and intuitive interaction mechanism with the human. If a robot accepts task instruction in natural language, first, it has to understand the user's intention by decoding the instruction. However, while executing the task, the robot may face unforeseeable circumstances due to the variations in the observed scene and therefore requires further user intervention. In this article, we present a system called Talk-to-Resolve (TTR) that enables a robot to initiate a coherent dialogue exchange with the instructor by observing the scene visually to resolve the impasse. Through dialogue, it either finds a cue to move forward in the original plan, an acceptable alternative to the original plan, or affirmation to abort the task altogether. To realize the possible stalemate, we utilize the dense captions of the observed scene and the given instruction jointly to compute the robot's next action. We evaluate our system based on a data set of initial instruction and situational scene pairs. Our system can identify the stalemate and resolve them with appropriate dialogue exchange with 82% accuracy. Additionally, a user study reveals that the questions from our systems are more natural (4.02 on average on a scale of 1 to 5) as compared to a state-of-the-art (3.08 on average).
Grounded Situation Recognition (GSR) is the task that not only classifies a salient action (verb), but also predicts entities (nouns) associated with semantic roles and their locations in the given image. Inspired by the remarkable success of Transformers in vision tasks, we propose a GSR model based on a Transformer encoder-decoder architecture. The attention mechanism of our model enables accurate verb classification by capturing high-level semantic feature of an image effectively, and allows the model to flexibly deal with the complicated and image-dependent relations between entities for improved noun classification and localization. Our model is the first Transformer architecture for GSR, and achieves the state of the art in every evaluation metric on the SWiG benchmark. Our code is available at https://github.com/jhcho99/gsrtr .
Scene understanding is an active research area. Commercial depth sensors, such as Kinect, have enabled the release of several RGB-D datasets over the past few years which spawned novel methods in 3D scene understanding. More recently with the launch of the LiDAR sensor in Apple's iPads and iPhones, high quality RGB-D data is accessible to millions of people on a device they commonly use. This opens a whole new era in scene understanding for the Computer Vision community as well as app developers. The fundamental research in scene understanding together with the advances in machine learning can now impact people's everyday experiences. However, transforming these scene understanding methods to real-world experiences requires additional innovation and development. In this paper we introduce ARKitScenes. It is not only the first RGB-D dataset that is captured with a now widely available depth sensor, but to our best knowledge, it also is the largest indoor scene understanding data released. In addition to the raw and processed data from the mobile device, ARKitScenes includes high resolution depth maps captured using a stationary laser scanner, as well as manually labeled 3D oriented bounding boxes for a large taxonomy of furniture. We further analyze the usefulness of the data for two downstream tasks: 3D object detection and color-guided depth upsampling. We demonstrate that our dataset can help push the boundaries of existing state-of-the-art methods and it introduces new challenges that better represent real-world scenarios.
3D semantic segmentation is a fundamental building block for several scene understanding applications such as autonomous driving, robotics and AR/VR. Several state-of-the-art semantic segmentation models suffer from the part misclassification problem, wherein parts of the same object are labelled incorrectly. Previous methods have utilized hierarchical, iterative methods to fuse semantic and instance information, but they lack learnability in context fusion, and are computationally complex and heuristic driven. This paper presents Segment-Fusion, a novel attention-based method for hierarchical fusion of semantic and instance information to address the part misclassifications. The presented method includes a graph segmentation algorithm for grouping points into segments that pools point-wise features into segment-wise features, a learnable attention-based network to fuse these segments based on their semantic and instance features, and followed by a simple yet effective connected component labelling algorithm to convert segment features to instance labels. Segment-Fusion can be flexibly employed with any network architecture for semantic/instance segmentation. It improves the qualitative and quantitative performance of several semantic segmentation backbones by upto 5% when evaluated on the ScanNet and S3DIS datasets.
Learning object-centric representations of multi-object scenes is a promising approach towards machine intelligence, facilitating high-level reasoning and control from visual sensory data. However, current approaches for unsupervised object-centric scene representation are incapable of aggregating information from multiple observations of a scene. As a result, these "single-view" methods form their representations of a 3D scene based only on a single 2D observation (view). Naturally, this leads to several inaccuracies, with these methods falling victim to single-view spatial ambiguities. To address this, we propose The Multi-View and Multi-Object Network (MulMON) -- a method for learning accurate, object-centric representations of multi-object scenes by leveraging multiple views. In order to sidestep the main technical difficulty of the multi-object-multi-view scenario -- maintaining object correspondences across views -- MulMON iteratively updates the latent object representations for a scene over multiple views. To ensure that these iterative updates do indeed aggregate spatial information to form a complete 3D scene understanding, MulMON is asked to predict the appearance of the scene from novel viewpoints during training. Through experiments, we show that MulMON better-resolves spatial ambiguities than single-view methods -- learning more accurate and disentangled object representations -- and also achieves new functionality in predicting object segmentations for novel viewpoints.