Given a single scene image, this paper proposes a method of Category-level 6D Object Pose and Size Estimation (COPSE) from the point cloud of the target object, without external real pose-annotated training data. Specifically, beyond the visual cues in RGB images, we rely on the shape information predominately from the depth (D) channel. The key idea is to explore the shape alignment of each instance against its corresponding category-level template shape, and the symmetric correspondence of each object category for estimating a coarse 3D object shape. Our framework deforms the point cloud of the category-level template shape to align the observed instance point cloud for implicitly representing its 3D rotation. Then we model the symmetric correspondence by predicting symmetric point cloud from the partially observed point cloud. The concatenation of the observed point cloud and symmetric one reconstructs a coarse object shape, thus facilitating object center (3D translation) and 3D size estimation. Extensive experiments on the category-level NOCS benchmark demonstrate that our lightweight model still competes with state-of-the-art approaches that require labeled real-world images. We also deploy our approach to a physical Baxter robot to perform grasping tasks on unseen but category-known instances, and the results further validate the efficacy of our proposed model. Code and pre-trained models are available on the project webpage.
Automotive traffic scenes are complex due to the variety of possible scenarios, objects, and weather conditions that need to be handled. In contrast to more constrained environments, such as automated underground trains, automotive perception systems cannot be tailored to a narrow field of specific tasks but must handle an ever-changing environment with unforeseen events. As currently no single sensor is able to reliably perceive all relevant activity in the surroundings, sensor data fusion is applied to perceive as much information as possible. Data fusion of different sensors and sensor modalities on a low abstraction level enables the compensation of sensor weaknesses and misdetections among the sensors before the information-rich sensor data are compressed and thereby information is lost after a sensor-individual object detection. This paper develops a low-level sensor fusion network for 3D object detection, which fuses lidar, camera, and radar data. The fusion network is trained and evaluated on the nuScenes data set. On the test set, fusion of radar data increases the resulting AP (Average Precision) detection score by about 5.1% in comparison to the baseline lidar network. The radar sensor fusion proves especially beneficial in inclement conditions such as rain and night scenes. Fusing additional camera data contributes positively only in conjunction with the radar fusion, which shows that interdependencies of the sensors are important for the detection result. Additionally, the paper proposes a novel loss to handle the discontinuity of a simple yaw representation for object detection. Our updated loss increases the detection and orientation estimation performance for all sensor input configurations. The code for this research has been made available on GitHub.
As a core problem in computer vision, the performance of object detection has improved drastically in the past few years. Despite their impressive performance, object detectors suffer from a lack of interpretability. Visualization techniques have been developed and widely applied to introspect the decisions made by other kinds of deep learning models; however, visualizing object detectors has been underexplored. In this paper, we propose using inversion as a primary tool to understand modern object detectors and develop an optimization-based approach to layout inversion, allowing us to generate synthetic images recognized by trained detectors as containing a desired configuration of objects. We reveal intriguing properties of detectors by applying our layout inversion technique to a variety of modern object detectors, and further investigate them via validation experiments: they rely on qualitatively different features for classification and regression; they learn canonical motifs of commonly co-occurring objects; they use diff erent visual cues to recognize objects of varying sizes. We hope our insights can help practitioners improve object detectors.
We ask the question: to what extent can recent large-scale language and image generation models blend visual concepts? Given an arbitrary object, we identify a relevant object and generate a single-sentence description of the blend of the two using a language model. We then generate a visual depiction of the blend using a text-based image generation model. Quantitative and qualitative evaluations demonstrate the superiority of language models over classical methods for conceptual blending, and of recent large-scale image generation models over prior models for the visual depiction.
Highly constrained manipulation tasks continue to be challenging for autonomous robots as they require high levels of precision, typically less than 1mm, which is often incompatible with what can be achieved by traditional perception systems. This paper demonstrates that the combination of state-of-the-art object tracking with passively adaptive mechanical hardware can be leveraged to complete precision manipulation tasks with tight, industrially-relevant tolerances (0.25mm). The proposed control method closes the loop through vision by tracking the relative 6D pose of objects in the relevant workspace. It adjusts the control reference of both the compliant manipulator and the hand to complete object insertion tasks via within-hand manipulation. Contrary to previous efforts for insertion, our method does not require expensive force sensors, precision manipulators, or time-consuming, online learning, which is data hungry. Instead, this effort leverages mechanical compliance and utilizes an object agnostic manipulation model of the hand learned offline, off-the-shelf motion planning, and an RGBD-based object tracker trained solely with synthetic data. These features allow the proposed system to easily generalize and transfer to new tasks and environments. This paper describes in detail the system components and showcases its efficacy with extensive experiments involving tight tolerance peg-in-hole insertion tasks of various geometries as well as open-world constrained placement tasks.
Video Question Answering (Video QA) is a powerful testbed to develop new AI capabilities. This task necessitates learning to reason about objects, relations, and events across visual and linguistic domains in space-time. High-level reasoning demands lifting from associative visual pattern recognition to symbol-like manipulation over objects, their behavior and interactions. Toward reaching this goal we propose an object-oriented reasoning approach in that video is abstracted as a dynamic stream of interacting objects. At each stage of the video event flow, these objects interact with each other, and their interactions are reasoned about with respect to the query and under the overall context of a video. This mechanism is materialized into a family of general-purpose neural units and their multi-level architecture called Hierarchical Object-oriented Spatio-Temporal Reasoning (HOSTR) networks. This neural model maintains the objects' consistent lifelines in the form of a hierarchically nested spatio-temporal graph. Within this graph, the dynamic interactive object-oriented representations are built up along the video sequence, hierarchically abstracted in a bottom-up manner, and converge toward the key information for the correct answer. The method is evaluated on multiple major Video QA datasets and establishes new state-of-the-arts in these tasks. Analysis into the model's behavior indicates that object-oriented reasoning is a reliable, interpretable and efficient approach to Video QA.
Semantic image synthesis is a process for generating photorealistic images from a single semantic mask. To enrich the diversity of multimodal image synthesis, previous methods have controlled the global appearance of an output image by learning a single latent space. However, a single latent code is often insufficient for capturing various object styles because object appearance depends on multiple factors. To handle individual factors that determine object styles, we propose a class- and layer-wise extension to the variational autoencoder (VAE) framework that allows flexible control over each object class at the local to global levels by learning multiple latent spaces. Furthermore, we demonstrate that our method generates images that are both plausible and more diverse compared to state-of-the-art methods via extensive experiments with real and synthetic datasets inthree different domains. We also show that our method enables a wide range of applications in image synthesis and editing tasks.
Camouflaged object detection (COD) aims to segment camouflaged objects hiding in the environment, which is challenging due to the similar appearance of camouflaged objects and their surroundings. Research in biology suggests depth can provide useful object localization cues for camouflaged object discovery. In this paper, we study the depth contribution for camouflaged object detection, where the depth maps are generated with existing monocular depth estimation (MDE) methods. Due to the domain gap between the MDE dataset and our COD dataset, the generated depth maps are not accurate enough to be directly used. We then introduce two solutions to avoid the noisy depth maps from dominating the training process. Firstly, we present an auxiliary depth estimation branch ("ADE"), aiming to regress the depth maps. We find that "ADE" is especially necessary for our "generated depth" scenario. Secondly, we introduce a multi-modal confidence-aware loss function via a generative adversarial network to weigh the contribution of depth for camouflaged object detection. Our extensive experiments on various camouflaged object detection datasets explain that the existing "sensor depth" based RGB-D segmentation techniques work poorly with "generated depth", and our proposed two solutions work cooperatively, achieving effective depth contribution exploration for camouflaged object detection.
We present an algorithm that learns a coarse 3D representation of objects from unposed multi-view 2D mask supervision, then uses it to generate detailed mask and image texture. In contrast to existing voxel-based methods for unposed object reconstruction, our approach learns to represent the generated shape and pose with a set of self-supervised canonical 3D anisotropic Gaussians via a perspective camera, and a set of per-image transforms. We show that this approach can robustly estimate a 3D space for the camera and object, while recent baselines sometimes struggle to reconstruct coherent 3D spaces in this setting. We show results on synthetic datasets with realistic lighting, and demonstrate object insertion with interactive posing. With our work, we help move towards structured representations that handle more real-world variation in learning-based object reconstruction.
Identification of high-risk driving situations is generally approached through collision risk estimation or accident pattern recognition. In this work, we approach the problem from the perspective of subjective risk. We operationalize subjective risk assessment by predicting driver behavior changes and identifying the cause of changes. To this end, we introduce a new task called driver-centric risk object identification (DROID), which uses egocentric video to identify object(s) influencing a driver's behavior, given only the driver's response as the supervision signal. We formulate the task as a cause-effect problem and present a novel two-stage DROID framework, taking inspiration from models of situation awareness and causal inference. A subset of data constructed from the Honda Research Institute Driving Dataset (HDD) is used to evaluate DROID. We demonstrate state-of-the-art DROID performance, even compared with strong baseline models using this dataset. Additionally, we conduct extensive ablative studies to justify our design choices. Moreover, we demonstrate the applicability of DROID for risk assessment.
In this survey, we first introduce the background of popular sensors used for self-driving, their data properties, and the corresponding object detection algorithms. Next, we discuss existing datasets that can be used for evaluating multi-modal 3D object detection algorithms. Then we present a review of multi-modal fusion based 3D detection networks, taking a close look at their fusion stage, fusion input and fusion granularity, and how these design choices evolve with time and technology. After the review, we discuss open challenges as well as possible solutions. We hope that this survey can help researchers to get familiar with the field and embark on investigations in the area of multi-modal 3D object detection.
Multiple object tracking and segmentation requires detecting, tracking, and segmenting objects belonging to a set of given classes. Most approaches only exploit the temporal dimension to address the association problem, while relying on single frame predictions for the segmentation mask itself. We propose Prototypical Cross-Attention Network (PCAN), capable of leveraging rich spatio-temporal information for online multiple object tracking and segmentation. PCAN first distills a space-time memory into a set of prototypes and then employs cross-attention to retrieve rich information from the past frames. To segment each object, PCAN adopts a prototypical appearance module to learn a set of contrastive foreground and background prototypes, which are then propagated over time. Extensive experiments demonstrate that PCAN outperforms current video instance tracking and segmentation competition winners on both Youtube-VIS and BDD100K datasets, and shows efficacy to both one-stage and two-stage segmentation frameworks. Code and video resources are available at http://vis.xyz/pub/pcan.
Contrastive self-supervised learning has largely narrowed the gap to supervised pre-training on ImageNet. However, its success highly relies on the object-centric priors of ImageNet, i.e., different augmented views of the same image correspond to the same object. Such a heavily curated constraint becomes immediately infeasible when pre-trained on more complex scene images with many objects. To overcome this limitation, we introduce Object-level Representation Learning (ORL), a new self-supervised learning framework towards scene images. Our key insight is to leverage image-level self-supervised pre-training as the prior to discover object-level semantic correspondence, thus realizing object-level representation learning from scene images. Extensive experiments on COCO show that ORL significantly improves the performance of self-supervised learning on scene images, even surpassing supervised ImageNet pre-training on several downstream tasks. Furthermore, ORL improves the downstream performance when more unlabeled scene images are available, demonstrating its great potential of harnessing unlabeled data in the wild. We hope our approach can motivate future research on more general-purpose unsupervised representation learning from scene data.
Confidence-aware learning is proven as an effective solution to prevent networks becoming overconfident. We present a confidence-aware camouflaged object detection framework using dynamic supervision to produce both accurate camouflage map and meaningful "confidence" representing model awareness about the current prediction. A camouflaged object detection network is designed to produce our camouflage prediction. Then, we concatenate it with the input image and feed it to the confidence estimation network to produce an one channel confidence map.We generate dynamic supervision for the confidence estimation network, representing the agreement of camouflage prediction with the ground truth camouflage map. With the produced confidence map, we introduce confidence-aware learning with the confidence map as guidance to pay more attention to the hard/low-confidence pixels in the loss function. We claim that, once trained, our confidence estimation network can evaluate pixel-wise accuracy of the prediction without relying on the ground truth camouflage map. Extensive results on four camouflaged object detection testing datasets illustrate the superior performance of the proposed model in explaining the camouflage prediction.
Moving Object Detection (MOD) is a crucial task for the Autonomous Driving pipeline. MOD is usually handled via 2-stream convolutional architectures that incorporates both appearance and motion cues, without considering the inter-relations between the spatial or motion features. In this paper, we tackle this problem through multi-head attention mechanisms, both across the spatial and motion streams. We propose MODETR; a Moving Object DEtection TRansformer network, comprised of multi-stream transformer encoders for both spatial and motion modalities, and an object transformer decoder that produces the moving objects bounding boxes using set predictions. The whole architecture is trained end-to-end using bi-partite loss. Several methods of incorporating motion cues with the Transformer model are explored, including two-stream RGB and Optical Flow (OF) methods, and multi-stream architectures that take advantage of sequence information. To incorporate the temporal information, we propose a new Temporal Positional Encoding (TPE) approach to extend the Spatial Positional Encoding(SPE) in DETR. We explore two architectural choices for that, balancing between speed and time. To evaluate the our network, we perform the MOD task on the KITTI MOD [6] data set. Results show significant 5% mAP of the Transformer network for MOD over the state-of-the art methods. Moreover, the proposed TPE encoding provides 10% mAP improvement over the SPE baseline.
Moving objects have special importance for Autonomous Driving tasks. Detecting moving objects can be posed as Moving Object Segmentation, by segmenting the object pixels, or Moving Object Detection, by generating a bounding box for the moving targets. In this paper, we present a Multi-Task Learning architecture, based on Transformers, to jointly perform both tasks through one network. Due to the importance of the motion features to the task, the whole setup is based on a Spatio-Temporal aggregation. We evaluate the performance of the individual tasks architecture versus the MTL setup, both with early shared encoders, and late shared encoder-decoder transformers. For the latter, we present a novel joint tasks query decoder transformer, that enables us to have tasks dedicated heads out of the shared model. To evaluate our approach, we use the KITTI MOD [29] data set. Results show1.5% mAP improvement for Moving Object Detection, and 2%IoU improvement for Moving Object Segmentation, over the individual tasks networks.
With the rise of automation, unmanned vehicles became a hot topic both as commercial products and as a scientific research topic. It composes a multi-disciplinary field of robotics that encompasses embedded systems, control theory, path planning, Simultaneous Localization and Mapping (SLAM), scene reconstruction, and pattern recognition. In this work, we present our exploratory research of how sensor data fusion and state-of-the-art machine learning algorithms can perform the Embodied Artificial Intelligence (E-AI) task called Visual Semantic Navigation. This task, a.k.a Object-Goal Navigation (ObjectNav) consists of autonomous navigation using egocentric visual observations to reach an object belonging to the target semantic class without prior knowledge of the environment. Our method reached fourth place on the Habitat Challenge 2021 ObjectNav on the Minival phase and the Test-Standard Phase.
Autonomous driving is regarded as one of the most promising remedies to shield human beings from severe crashes. To this end, 3D object detection serves as the core basis of perception stack especially for the sake of path planning, motion prediction, and collision avoidance etc. Taking a quick glance at the progress we have made, we attribute challenges to visual appearance recovery in the absence of depth information from images, representation learning from partially occluded unstructured point clouds, and semantic alignments over heterogeneous features from cross modalities. Despite existing efforts, 3D object detection for autonomous driving is still in its infancy. Recently, a large body of literature have been investigated to address this 3D vision task. Nevertheless, few investigations have looked into collecting and structuring this growing knowledge. We therefore aim to fill this gap in a comprehensive survey, encompassing all the main concerns including sensors, datasets, performance metrics and the recent state-of-the-art detection methods, together with their pros and cons. Furthermore, we provide quantitative comparisons with the state of the art. A case study on fifteen selected representative methods is presented, involved with runtime analysis, error analysis, and robustness analysis. Finally, we provide concluding remarks after an in-depth analysis of the surveyed works and identify promising directions for future work.
Low-power computer vision on embedded devices has many applications. This paper describes a low-power technique for the object re-identification (reID) problem: matching a query image against a gallery of previously seen images. State-of-the-art techniques rely on large, computationally-intensive Deep Neural Networks (DNNs). We propose a novel hierarchical DNN architecture that uses attribute labels in the training dataset to perform efficient object reID. At each node in the hierarchy, a small DNN identifies a different attribute of the query image. The small DNN at each leaf node is specialized to re-identify a subset of the gallery: only the images with the attributes identified along the path from the root to a leaf. Thus, a query image is re-identified accurately after processing with a few small DNNs. We compare our method with state-of-the-art object reID techniques. With a 4% loss in accuracy, our approach realizes significant resource savings: 74% less memory, 72% fewer operations, and 67% lower query latency, yielding 65% less energy consumption.
In the interactive segmentation, users initially click on the target object to segment the main body and then provide corrections on mislabeled regions to iteratively refine the segmentation masks. Most existing methods transform these user-provided clicks into interaction maps and concatenate them with image as the input tensor. Typically, the interaction maps are determined by measuring the distance of each pixel to the clicked points, ignoring the relation between clicks and mislabeled regions. We propose a Dynamic Click Transform Network~(DCT-Net), consisting of Spatial-DCT and Feature-DCT, to better represent user interactions. Spatial-DCT transforms each user-provided click with individual diffusion distance according to the target scale, and Feature-DCT normalizes the extracted feature map to a specific distribution predicted from the clicked points. We demonstrate the effectiveness of our proposed method and achieve favorable performance compared to the state-of-the-art on three standard benchmark datasets.