Chen Wang

Yiqing Wang, Zihan Li, Jieru Mei et al. · uw

Recent advancements in large-scale Vision Transformers have made significant strides in improving pre-trained models for medical image segmentation. However, these methods face a notable challenge in acquiring a substantial amount of pre-training data, particularly within the medical field. To address this limitation, we present Masked Multi-view with Swin Transformers (SwinMM), a novel multi-view pipeline for enabling accurate and data-efficient self-supervised medical image analysis. Our strategy harnesses the potential of multi-view information by incorporating two principal components. In the pre-training phase, we deploy a masked multi-view encoder devised to concurrently train masked multi-view observations through a range of diverse proxy tasks. These tasks span image reconstruction, rotation, contrastive learning, and a novel task that employs a mutual learning paradigm. This new task capitalizes on the consistency between predictions from various perspectives, enabling the extraction of hidden multi-view information from 3D medical data. In the fine-tuning stage, a cross-view decoder is developed to aggregate the multi-view information through a cross-attention block. Compared with the previous state-of-the-art self-supervised learning method Swin UNETR, SwinMM demonstrates a notable advantage on several medical image segmentation tasks. It allows for a smooth integration of multi-view information, significantly boosting both the accuracy and data-efficiency of the model. Code and models are available at https://github.com/UCSC-VLAA/SwinMM/.

Yafei Hu, Junyi Geng, Chen Wang et al. · cmu

Autonomous exploration has many important applications. However, classic information gain-based or frontier-based exploration only relies on the robot current state to determine the immediate exploration goal, which lacks the capability of predicting the value of future states and thus leads to inefficient exploration decisions. This paper presents a method to learn how "good" states are, measured by the state value function, to provide a guidance for robot exploration in real-world challenging environments. We formulate our work as an off-policy evaluation (OPE) problem for robot exploration (OPERE). It consists of offline Monte-Carlo training on real-world data and performs Temporal Difference (TD) online adaptation to optimize the trained value estimator. We also design an intrinsic reward function based on sensor information coverage to enable the robot to gain more information with sparse extrinsic rewards. Results show that our method enables the robot to predict the value of future states so as to better guide robot exploration. The proposed algorithm achieves better prediction and exploration performance compared with the state-of-the-arts. To the best of our knowledge, this work for the first time demonstrates value function prediction on real-world dataset for robot exploration in challenging subterranean and urban environments. More details and demo videos can be found at https://jeffreyyh.github.io/opere/.

Shishira R Maiya, Sharath Girish, Max Ehrlich et al. · nvidia

Implicit Neural Representations (INR) have recently shown to be powerful tool for high-quality video compression. However, existing works are limiting as they do not explicitly exploit the temporal redundancy in videos, leading to a long encoding time. Additionally, these methods have fixed architectures which do not scale to longer videos or higher resolutions. To address these issues, we propose NIRVANA, which treats videos as groups of frames and fits separate networks to each group performing patch-wise prediction. This design shares computation within each group, in the spatial and temporal dimensions, resulting in reduced encoding time of the video. The video representation is modeled autoregressively, with networks fit on a current group initialized using weights from the previous group's model. To further enhance efficiency, we perform quantization of the network parameters during training, requiring no post-hoc pruning or quantization. When compared with previous works on the benchmark UVG dataset, NIRVANA improves encoding quality from 37.36 to 37.70 (in terms of PSNR) and the encoding speed by 12X, while maintaining the same compression rate. In contrast to prior video INR works which struggle with larger resolution and longer videos, we show that our algorithm is highly flexible and scales naturally due to its patch-wise and autoregressive designs. Moreover, our method achieves variable bitrate compression by adapting to videos with varying inter-frame motion. NIRVANA achieves 6X decoding speed and scales well with more GPUs, making it practical for various deployment scenarios.

Aryan, Bowen Li, Sebastian Scherer et al. · cmu

Indoor relocalization is vital for both robotic tasks like autonomous exploration and civil applications such as navigation with a cell phone in a shopping mall. Some previous approaches adopt geometrical information such as key-point features or local textures to carry out indoor relocalization, but they either easily fail in an environment with visually similar scenes or require many database images. Inspired by the fact that humans often remember places by recognizing unique landmarks, we resort to objects, which are more informative than geometry elements. In this work, we propose a simple yet effective object-based indoor relocalization approach, dubbed AirLoc. To overcome the critical challenges of object reidentification and remembering object relationships, we extract object-wise appearance embedding and inter-object geometric relationships. The geometry and appearance features are integrated to generate cumulative scene features. This results in a robust, accurate, and portable indoor relocalization system, which outperforms the state-of-the-art methods in room-level relocalization by 9.5% of PR-AUC and 7% of accuracy. In addition to exhaustive evaluation, we also carry out real-world tests, where AirLoc shows robustness in challenges like severe occlusion, perceptual aliasing, viewpoint shift, and deformation.

Jiacong Xu, Yi Zhang, Jiawei Peng et al.

Accurately estimating the 3D pose and shape is an essential step towards understanding animal behavior, and can potentially benefit many downstream applications, such as wildlife conservation. However, research in this area is held back by the lack of a comprehensive and diverse dataset with high-quality 3D pose and shape annotations. In this paper, we propose Animal3D, the first comprehensive dataset for mammal animal 3D pose and shape estimation. Animal3D consists of 3379 images collected from 40 mammal species, high-quality annotations of 26 keypoints, and importantly the pose and shape parameters of the SMAL model. All annotations were labeled and checked manually in a multi-stage process to ensure highest quality results. Based on the Animal3D dataset, we benchmark representative shape and pose estimation models at: (1) supervised learning from only the Animal3D data, (2) synthetic to real transfer from synthetically generated images, and (3) fine-tuning human pose and shape estimation models. Our experimental results demonstrate that predicting the 3D shape and pose of animals across species remains a very challenging task, despite significant advances in human pose estimation. Our results further demonstrate that synthetic pre-training is a viable strategy to boost the model performance. Overall, Animal3D opens new directions for facilitating future research in animal 3D pose and shape estimation, and is publicly available.

Linfang Zheng, Chen Wang, Yinghan Sun et al.

In this paper, we focus on the problem of category-level object pose estimation, which is challenging due to the large intra-category shape variation. 3D graph convolution (3D-GC) based methods have been widely used to extract local geometric features, but they have limitations for complex shaped objects and are sensitive to noise. Moreover, the scale and translation invariant properties of 3D-GC restrict the perception of an object's size and translation information. In this paper, we propose a simple network structure, the HS-layer, which extends 3D-GC to extract hybrid scope latent features from point cloud data for category-level object pose estimation tasks. The proposed HS-layer: 1) is able to perceive local-global geometric structure and global information, 2) is robust to noise, and 3) can encode size and translation information. Our experiments show that the simple replacement of the 3D-GC layer with the proposed HS-layer on the baseline method (GPV-Pose) achieves a significant improvement, with the performance increased by 14.5% on 5d2cm metric and 10.3% on IoU75. Our method outperforms the state-of-the-art methods by a large margin (8.3% on 5d2cm, 6.9% on IoU75) on the REAL275 dataset and runs in real-time (50 FPS).

Huseyin Coskun, Alireza Zareian, Joshua L. Moore et al.

Clustering is a ubiquitous tool in unsupervised learning. Most of the existing self-supervised representation learning methods typically cluster samples based on visually dominant features. While this works well for image-based self-supervision, it often fails for videos, which require understanding motion rather than focusing on background. Using optical flow as complementary information to RGB can alleviate this problem. However, we observe that a naive combination of the two views does not provide meaningful gains. In this paper, we propose a principled way to combine two views. Specifically, we propose a novel clustering strategy where we use the initial cluster assignment of each view as prior to guide the final cluster assignment of the other view. This idea will enforce similar cluster structures for both views, and the formed clusters will be semantically abstract and robust to noisy inputs coming from each individual view. Additionally, we propose a novel regularization strategy to address the feature collapse problem, which is common in cluster-based self-supervised learning methods. Our extensive evaluation shows the effectiveness of our learned representations on downstream tasks, e.g., video retrieval and action recognition. Specifically, we outperform the state of the art by 7% on UCF and 4% on HMDB for video retrieval, and 5% on UCF and 6% on HMDB for video classification

Yuheng Qiu, Chen Wang, Can Xu et al.

Inertial odometry (IO) using strap-down inertial measurement units (IMUs) is critical in many robotic applications where precise orientation and position tracking are essential. Prior kinematic motion model-based IO methods often use a simplified linearized IMU noise model and thus usually encounter difficulties in modeling non-deterministic errors arising from environmental disturbances and mechanical defects. In contrast, data-driven IO methods struggle to accurately model the sensor motions, often leading to generalizability and interoperability issues. To address these challenges, we present AirIMU, a hybrid approach to estimate the uncertainty, especially the non-deterministic errors, by data-driven methods and increase the generalization abilities using model-based methods. We demonstrate the adaptability of AirIMU using a full spectrum of IMUs, from low-cost automotive grades to high-end navigation grades. We also validate its effectiveness on various platforms, including hand-held devices, vehicles, and a helicopter that covers a trajectory of 262 kilometers. In the ablation study, we validate the effectiveness of our learned uncertainty in an IMU-GPS pose graph optimization experiment, achieving a 31.6\% improvement in accuracy. Experiments demonstrate that jointly training the IMU noise correction and uncertainty estimation synergistically benefits both tasks.

Bowen Li, Zhaoyu Li, Qiwei Du et al.

Recent years have witnessed the rapid development of Neuro-Symbolic (NeSy) AI systems, which integrate symbolic reasoning into deep neural networks. However, most of the existing benchmarks for NeSy AI fail to provide long-horizon reasoning tasks with complex multi-agent interactions. Furthermore, they are usually constrained by fixed and simplistic logical rules over limited entities, making them far from real-world complexities. To address these crucial gaps, we introduce LogiCity, the first simulator based on customizable first-order logic (FOL) for an urban-like environment with multiple dynamic agents. LogiCity models diverse urban elements using semantic and spatial concepts, such as IsAmbulance(X) and IsClose(X, Y). These concepts are used to define FOL rules that govern the behavior of various agents. Since the concepts and rules are abstractions, they can be universally applied to cities with any agent compositions, facilitating the instantiation of diverse scenarios. Besides, a key feature of LogiCity is its support for user-configurable abstractions, enabling customizable simulation complexities for logical reasoning. To explore various aspects of NeSy AI, LogiCity introduces two tasks, one features long-horizon sequential decision-making, and the other focuses on one-step visual reasoning, varying in difficulty and agent behaviors. Our extensive evaluation reveals the advantage of NeSy frameworks in abstract reasoning. Moreover, we highlight the significant challenges of handling more complex abstractions in long-horizon multi-agent scenarios or under high-dimensional, imbalanced data. With its flexible design, various features, and newly raised challenges, we believe LogiCity represents a pivotal step forward in advancing the next generation of NeSy AI. All the code and data are open-sourced at our website: https://jaraxxus-me.github.io/LogiCity/

Bowen Li, Chen Wang, Pranay Reddy et al.

Few-shot object detection has attracted increasing attention and rapidly progressed in recent years. However, the requirement of an exhaustive offline fine-tuning stage in existing methods is time-consuming and significantly hinders their usage in online applications such as autonomous exploration of low-power robots. We find that their major limitation is that the little but valuable information from a few support images is not fully exploited. To solve this problem, we propose a brand new architecture, AirDet, and surprisingly find that, by learning class-agnostic relation with the support images in all modules, including cross-scale object proposal network, shots aggregation module, and localization network, AirDet without fine-tuning achieves comparable or even better results than many fine-tuned methods, reaching up to 30-40% improvements. We also present solid results of onboard tests on real-world exploration data from the DARPA Subterranean Challenge, which strongly validate the feasibility of AirDet in robotics. To the best of our knowledge, AirDet is the first feasible few-shot detection method for autonomous exploration of low-power robots. The code and pre-trained models are released at https://github.com/Jaraxxus-Me/AirDet.

Nikhil Varma Keetha, Chen Wang, Yuheng Qiu et al.

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.

Ajay Mandlekar, Danfei Xu, Josiah Wong et al.

Imitating human demonstrations is a promising approach to endow robots with various manipulation capabilities. While recent advances have been made in imitation learning and batch (offline) reinforcement learning, a lack of open-source human datasets and reproducible learning methods make assessing the state of the field difficult. In this paper, we conduct an extensive study of six offline learning algorithms for robot manipulation on five simulated and three real-world multi-stage manipulation tasks of varying complexity, and with datasets of varying quality. Our study analyzes the most critical challenges when learning from offline human data for manipulation. Based on the study, we derive a series of lessons including the sensitivity to different algorithmic design choices, the dependence on the quality of the demonstrations, and the variability based on the stopping criteria due to the different objectives in training and evaluation. We also highlight opportunities for learning from human datasets, such as the ability to learn proficient policies on challenging, multi-stage tasks beyond the scope of current reinforcement learning methods, and the ability to easily scale to natural, real-world manipulation scenarios where only raw sensory signals are available. We have open-sourced our datasets and all algorithm implementations to facilitate future research and fair comparisons in learning from human demonstration data. Codebase, datasets, trained models, and more available at https://arise-initiative.github.io/robomimic-web/

Han Wang, Chen Wang, Lihua Xie

The LIght Detection And Ranging (LiDAR) sensor has become one of the most important perceptual devices due to its important role in simultaneous localization and mapping (SLAM). Existing SLAM methods are mainly developed for mechanical LiDAR sensors, which are often adopted by large scale robots. Recently, the solid-state LiDAR is introduced and becomes popular since it provides a cost-effective and lightweight solution for small scale robots. Compared to mechanical LiDAR, solid-state LiDAR sensors have higher update frequency and angular resolution, but also have smaller field of view (FoV), which is very challenging for existing LiDAR SLAM algorithms. Therefore, it is necessary to have a more robust and computationally efficient SLAM method for this new sensing device. To this end, we propose a new SLAM framework for solid-state LiDAR sensors, which involves feature extraction, odometry estimation, and probability map building. The proposed method is evaluated on a warehouse robot and a hand-held device. In the experiments, we demonstrate both the accuracy and efficiency of our method using an Intel L515 solid-state LiDAR. The results show that our method is able to provide precise localization and high quality mapping. We made the source codes public at \url{https://github.com/wh200720041/SSL_SLAM}.

Chen Wang, Yuheng Qiu, Dasong Gao et al.

Graph neural networks (GNN) are powerful models for many graph-structured tasks. Existing models often assume that the complete structure of the graph is available during training. In practice, however, graph-structured data is usually formed in a streaming fashion so that learning a graph continuously is often necessary. In this paper, we bridge GNN and lifelong learning by converting a continual graph learning problem to a regular graph learning problem so GNN can inherit the lifelong learning techniques developed for convolutional neural networks (CNN). We propose a new topology, the feature graph, which takes features as new nodes and turns nodes into independent graphs. This successfully converts the original problem of node classification to graph classification. In the experiments, we demonstrate the efficiency and effectiveness of feature graph networks (FGN) by continuously learning a sequence of classical graph datasets. We also show that FGN achieves superior performance in two applications, i.e., lifelong human action recognition with wearable devices and feature matching. To the best of our knowledge, FGN is the first method to bridge graph learning and lifelong learning via a novel graph topology. Source code is available at https://github.com/wang-chen/LGL

Han Wang, Chen Wang, Lihua Xie

As an essential component of visual simultaneous localization and mapping (SLAM), place recognition is crucial for robot navigation and autonomous driving. Existing methods often formulate visual place recognition as feature matching, which is computationally expensive for many robotic applications with limited computing power, e.g., autonomous driving and cleaning robot. Inspired by the fact that human beings always recognize a place by remembering salient regions or landmarks that are more attractive or interesting than others, we formulate visual place recognition as saliency re-identification. In the meanwhile, we propose to perform both saliency detection and re-identification in frequency domain, in which all operations become element-wise. The experiments show that our proposed method achieves competitive accuracy and much higher speed than the state-of-the-art feature-based methods. The proposed method is open-sourced and available at https://github.com/wh200720041/SRLCD.git.

Siyu Chen, Kangcheng Liu, Chen Wang et al.

Visual Odometry (VO) is vital for the navigation of autonomous systems, providing accurate position and orientation estimates at reasonable costs. While traditional VO methods excel in some conditions, they struggle with challenges like variable lighting and motion blur. Deep learning-based VO, though more adaptable, can face generalization problems in new environments. Addressing these drawbacks, this paper presents a novel hybrid visual odometry (VO) framework that leverages pose-only supervision, offering a balanced solution between robustness and the need for extensive labeling. We propose two cost-effective and innovative designs: a self-supervised homographic pre-training for enhancing optical flow learning from pose-only labels and a random patch-based salient point detection strategy for more accurate optical flow patch extraction. These designs eliminate the need for dense optical flow labels for training and significantly improve the generalization capability of the system in diverse and challenging environments. Our pose-only supervised method achieves competitive performance on standard datasets and greater robustness and generalization ability in extreme and unseen scenarios, even compared to dense optical flow-supervised state-of-the-art methods.

Yi Du, Zhipeng Zhao, Shaoshu Su et al.

Point cloud (PC) processing tasks-such as completion, upsampling, denoising, and colorization-are crucial in applications like autonomous driving and 3D reconstruction. Despite substantial advancements, prior approaches often address each of these tasks independently, with separate models focused on individual issues. However, this isolated approach fails to account for the fact that defects like incompleteness, low resolution, noise, and lack of color frequently coexist, with each defect influencing and correlating with the others. Simply applying these models sequentially can lead to error accumulation from each model, along with increased computational costs. To address these challenges, we introduce SuperPC, the first unified diffusion model capable of concurrently handling all four tasks. Our approach employs a three-level-conditioned diffusion framework, enhanced by a novel spatial-mix-fusion strategy, to leverage the correlations among these four defects for simultaneous, efficient processing. We show that SuperPC outperforms the state-of-the-art specialized models as well as their combination on all four individual tasks.

Yi Du, Taimeng Fu, Zhuoqun Chen et al.

Vision-language navigation in unknown environments is crucial for mobile robots. In scenarios such as household assistance and rescue, mobile robots need to understand a human command, such as "find a person wearing black". We present a novel vision-language navigation (VL-Nav) system that integrates efficient spatial reasoning on low-power robots. Unlike prior methods that rely on a single image-level feature similarity to guide a robot, our method integrates pixel-wise vision-language features with curiosity-driven exploration. This approach enables robust navigation to human-instructed instances across diverse environments. We deploy VL-Nav on a four-wheel mobile robot and evaluate its performance through comprehensive navigation tasks in both indoor and outdoor environments, spanning different scales and semantic complexities. Remarkably, VL-Nav operates at a real-time frequency of 30 Hz with a Jetson Orin NX, highlighting its ability to conduct efficient vision-language navigation. Results show that VL-Nav achieves an overall success rate of 86.3%, outperforming previous methods by 44.15%.

Chengshu Li, Ruohan Zhang, Josiah Wong et al.

We present BEHAVIOR-1K, a comprehensive simulation benchmark for human-centered robotics. BEHAVIOR-1K includes two components, guided and motivated by the results of an extensive survey on "what do you want robots to do for you?". The first is the definition of 1,000 everyday activities, grounded in 50 scenes (houses, gardens, restaurants, offices, etc.) with more than 9,000 objects annotated with rich physical and semantic properties. The second is OMNIGIBSON, a novel simulation environment that supports these activities via realistic physics simulation and rendering of rigid bodies, deformable bodies, and liquids. Our experiments indicate that the activities in BEHAVIOR-1K are long-horizon and dependent on complex manipulation skills, both of which remain a challenge for even state-of-the-art robot learning solutions. To calibrate the simulation-to-reality gap of BEHAVIOR-1K, we provide an initial study on transferring solutions learned with a mobile manipulator in a simulated apartment to its real-world counterpart. We hope that BEHAVIOR-1K's human-grounded nature, diversity, and realism make it valuable for embodied AI and robot learning research. Project website: https://behavior.stanford.edu.

Chen Wang, Yuheng Qiu, Wenshan Wang et al.

Autonomous robots frequently need to detect "interesting" scenes to decide on further exploration, or to decide which data to share for cooperation. These scenarios often require fast deployment with little or no training data. Prior work considers "interestingness" based on data from the same distribution. Instead, we propose to develop a method that automatically adapts online to the environment to report interesting scenes quickly. To address this problem, we develop a novel translation-invariant visual memory and design a three-stage architecture for long-term, short-term, and online learning, which enables the system to learn human-like experience, environmental knowledge, and online adaption, respectively. With this system, we achieve an average of 20% higher accuracy than the state-of-the-art unsupervised methods in a subterranean tunnel environment. We show comparable performance to supervised methods for robot exploration scenarios showing the efficacy of our approach. We expect that the presented method will play an important role in the robotic interestingness recognition exploration tasks.

Yuheng Qiu, Chen Wang, Wenshan Wang et al.

Dynamic Object-aware SLAM (DOS) exploits object-level information to enable robust motion estimation in dynamic environments. Existing methods mainly focus on identifying and excluding dynamic objects from the optimization. In this paper, we show that feature-based visual SLAM systems can also benefit from the presence of dynamic articulated objects by taking advantage of two observations: (1) The 3D structure of each rigid part of articulated object remains consistent over time; (2) The points on the same rigid part follow the same motion. In particular, we present AirDOS, a dynamic object-aware system that introduces rigidity and motion constraints to model articulated objects. By jointly optimizing the camera pose, object motion, and the object 3D structure, we can rectify the camera pose estimation, preventing tracking loss, and generate 4D spatio-temporal maps for both dynamic objects and static scenes. Experiments show that our algorithm improves the robustness of visual SLAM algorithms in challenging crowded urban environments. To the best of our knowledge, AirDOS is the first dynamic object-aware SLAM system demonstrating that camera pose estimation can be improved by incorporating dynamic articulated objects.

Dasong Gao, Chen Wang, Sebastian Scherer

Loop closure detection is an important building block that ensures the accuracy and robustness of simultaneous localization and mapping (SLAM) systems. Due to their generalization ability, CNN-based approaches have received increasing attention. Although they normally benefit from training on datasets that are diverse and reflective of the environments, new environments often emerge after the model is deployed. It is therefore desirable to incorporate the data newly collected during operation for incremental learning. Nevertheless, simply finetuning the model on new data is infeasible since it may cause the model's performance on previously learned data to degrade over time, which is also known as the problem of catastrophic forgetting. In this paper, we present AirLoop, a method that leverages techniques from lifelong learning to minimize forgetting when training loop closure detection models incrementally. We experimentally demonstrate the effectiveness of AirLoop on TartanAir, Nordland, and RobotCar datasets. To the best of our knowledge, AirLoop is one of the first works to achieve lifelong learning of deep loop closure detectors.

Han Wang, Chen Wang, Chun-Lin Chen et al.

Simultaneous Localization and Mapping (SLAM) has wide robotic applications such as autonomous driving and unmanned aerial vehicles. Both computational efficiency and localization accuracy are of great importance towards a good SLAM system. Existing works on LiDAR based SLAM often formulate the problem as two modules: scan-to-scan match and scan-to-map refinement. Both modules are solved by iterative calculation which are computationally expensive. In this paper, we propose a general solution that aims to provide a computationally efficient and accurate framework for LiDAR based SLAM. Specifically, we adopt a non-iterative two-stage distortion compensation method to reduce the computational cost. For each scan input, the edge and planar features are extracted and matched to a local edge map and a local plane map separately, where the local smoothness is also considered for iterative pose optimization. Thorough experiments are performed to evaluate its performance in challenging scenarios, including localization for a warehouse Automated Guided Vehicle (AGV) and a public dataset on autonomous driving. The proposed method achieves a competitive localization accuracy with a processing rate of more than 10 Hz in the public dataset evaluation, which provides a good trade-off between performance and computational cost for practical applications.

Kuan Xu, Chen Wang, Chao Chen et al.

Object encoding and identification are crucial for many robotic tasks such as autonomous exploration and semantic relocalization. Existing works heavily rely on the tracking of detected objects but have difficulty recalling revisited objects precisely. In this paper, we propose a novel object encoding method, which is named as AirCode, based on a graph of key-points. To be robust to the number of key-points detected, we propose a feature sparse encoding and object dense encoding method to ensure that each key-point can only affect a small part of the object descriptors, leading it to be robust to viewpoint changes, scaling, occlusion, and even object deformation. In the experiments, we show that it achieves superior performance for object identification than the state-of-the-art algorithms and is able to provide reliable semantic relocalization. It is a plug-and-play module and we expect that it will play an important role in various applications.

Tete Ji, Chen Wang, Lihua Xie

Most of the existing visual SLAM methods heavily rely on a static world assumption and easily fail in dynamic environments. Some recent works eliminate the influence of dynamic objects by introducing deep learning-based semantic information to SLAM systems. However such methods suffer from high computational cost and cannot handle unknown objects. In this paper, we propose a real-time semantic RGB-D SLAM system for dynamic environments that is capable of detecting both known and unknown moving objects. To reduce the computational cost, we only perform semantic segmentation on keyframes to remove known dynamic objects, and maintain a static map for robust camera tracking. Furthermore, we propose an efficient geometry module to detect unknown moving objects by clustering the depth image into a few regions and identifying the dynamic regions via their reprojection errors. The proposed method is evaluated on public datasets and real-world conditions. To the best of our knowledge, it is one of the first semantic RGB-D SLAM systems that run in real-time on a low-power embedded platform and provide high localization accuracy in dynamic environments.

Han Wang, Chen Wang, Lihua Xie

Simultaneous Localization And Mapping (SLAM) is a task to estimate the robot location and to reconstruct the environment based on observation from sensors such as LIght Detection And Ranging (LiDAR) and camera. It is widely used in robotic applications such as autonomous driving and drone delivery. Traditional LiDAR-based SLAM algorithms mainly leverage the geometric features from the scene context, while the intensity information from LiDAR is ignored. Some recent deep-learning-based SLAM algorithms consider intensity features and train the pose estimation network in an end-to-end manner. However, they require significant data collection effort and their generalizability to environments other than the trained one remains unclear. In this paper we introduce intensity features to a SLAM system. And we propose a novel full SLAM framework that leverages both geometry and intensity features. The proposed SLAM involves both intensity-based front-end odometry estimation and intensity-based back-end optimization. Thorough experiments are performed including both outdoor autonomous driving and indoor warehouse robot manipulation. The results show that the proposed method outperforms existing geometric-only LiDAR SLAM methods.

Jingzhao Hu, Xiaoqi Zhang, Qiaomei Jia et al.

Convolutional Neural Networks(CNNs) has achieved remarkable performance breakthrough in Euclidean structure data. Recently, aggregation-transformation based Graph Neural networks(GNNs) gradually produce a powerful performance on non-Euclidean data. In this paper, we propose a cross-correlation based graph convolution method allowing to naturally generalize CNNs to non-Euclidean domains and inherit the excellent natures of CNNs, such as local filters, parameter sharing, flexible receptive field, etc. Meanwhile, it leverages dynamically generated convolution kernel and cross-correlation operators to address the shortcomings of prior methods based on aggregation-transformation or their approximations. Our method has achieved or matched popular state-of-the-art results across three established graph benchmarks: the Cora, Citeseer, and Pubmed citation network datasets.

Charles Herrmann, Chen Wang, Richard Strong Bowen et al.

Image stitching is typically decomposed into three phases: registration, which aligns the source images with a common target image; seam finding, which determines for each target pixel the source image it should come from; and blending, which smooths transitions over the seams. As described in [1], the seam finding phase attempts to place seams between pixels where the transition between source images is not noticeable. Here, we observe that the most problematic failures of this approach occur when objects are cropped, omitted, or duplicated. We therefore take an object-centered approach to the problem, leveraging recent advances in object detection [2,3,4]. We penalize candidate solutions with this class of error by modifying the energy function used in the seam finding stage. This produces substantially more realistic stitching results on challenging imagery. In addition, these methods can be used to determine when there is non-recoverable occlusion in the input data, and also suggest a simple evaluation metric that can be used to evaluate the output of stitching algorithms.

Chen Wang, Chengyuan Deng

Applying Global Self-attention (GSA) mechanism over features has achieved remarkable success on Convolutional Neural Networks (CNNs). However, it is not clear if Graph Convolutional Networks (GCNs) can similarly benefit from such a technique. In this paper, inspired by the similarity between CNNs and GCNs, we study the impact of the Global Self-attention mechanism on GCNs. We find that consistent with the intuition, the GSA mechanism allows GCNs to capture feature-based vertex relations regardless of edge connections; As a result, the GSA mechanism can introduce extra expressive power to the GCNs. Furthermore, we analyze the impacts of the GSA mechanism on the issues of overfitting and over-smoothing. We prove that the GSA mechanism can alleviate both the overfitting and the over-smoothing issues based on some recent technical developments. Experiments on multiple benchmark datasets illustrate both superior expressive power and less significant overfitting and over-smoothing problems for the GSA-augmented GCNs, which corroborate the intuitions and the theoretical results.

Yilin Chen, Ming Li, Yongfei Wu et al.

Membranous nephropathy (MN) is a frequent type of adult nephrotic syndrome, which has a high clinical incidence and can cause various complications. In the biopsy microscope slide of membranous nephropathy, spikelike projections on the glomerular basement membrane is a prominent feature of the MN. However, due to the whole biopsy slide contains large number of glomeruli, and each glomerulus includes many spike lesions, the pathological feature of the spikes is not obvious. It thus is time-consuming for doctors to diagnose glomerulus one by one and is difficult for pathologists with less experience to diagnose. In this paper, we establish a visualized classification model based on the multi-scale annotation multi-instance learning (MSA-MIL) to achieve glomerular classification and spikes visualization. The MSA-MIL model mainly involves three parts. Firstly, U-Net is used to extract the region of the glomeruli to ensure that the features learned by the succeeding algorithm are focused inside the glomeruli itself. Secondly, we use MIL to train an instance-level classifier combined with MSA method to enhance the learning ability of the network by adding a location-level labeled reinforced dataset, thereby obtaining an example-level feature representation with rich semantics. Lastly, the predicted scores of each tile in the image are summarized to obtain glomerular classification and visualization of the classification results of the spikes via the usage of sliding window method. The experimental results confirm that the proposed MSA-MIL model can effectively and accurately classify normal glomeruli and spiked glomerulus and visualize the position of spikes in the glomerulus. Therefore, the proposed model can provide a good foundation for assisting the clinical doctors to diagnose the glomerular membranous nephropathy.

Wenshan Wang, Delong Zhu, Xiangwei Wang et al.

We present a challenging dataset, the TartanAir, for robot navigation tasks and more. The data is collected in photo-realistic simulation environments with the presence of moving objects, changing light and various weather conditions. By collecting data in simulations, we are able to obtain multi-modal sensor data and precise ground truth labels such as the stereo RGB image, depth image, segmentation, optical flow, camera poses, and LiDAR point cloud. We set up large numbers of environments with various styles and scenes, covering challenging viewpoints and diverse motion patterns that are difficult to achieve by using physical data collection platforms. In order to enable data collection at such a large scale, we develop an automatic pipeline, including mapping, trajectory sampling, data processing, and data verification. We evaluate the impact of various factors on visual SLAM algorithms using our data. The results of state-of-the-art algorithms reveal that the visual SLAM problem is far from solved. Methods that show good performance on established datasets such as KITTI do not perform well in more difficult scenarios. Although we use the simulation, our goal is to push the limits of Visual SLAM algorithms in the real world by providing a challenging benchmark for testing new methods, while also using a large diverse training data for learning-based methods. Our dataset is available at \url{http://theairlab.org/tartanair-dataset}.

Chen Wang, Chengyuan Deng, Vladimir Ivanov

Variational Autoencoders (VAEs) are powerful in data representation inference, but it cannot learn relations between features with its vanilla form and common variations. The ability to capture relations within data can provide the much needed inductive bias necessary for building more robust Machine Learning algorithms with more interpretable results. In this paper, inspired by recent advances in relational learning using Graph Neural Networks, we propose the Self-Attention Graph Variational AutoEncoder (SAG-VAE) network which can simultaneously learn feature relations and data representations in an end-to-end manner. SAG-VAE is trained by jointly inferring the posterior distribution of two types of latent variables, which denote the data representation and a shared graph structure, respectively. Furthermore, we introduce a novel self-attention graph network that improves the generative capabilities of SAG-VAE by parameterizing the generative distribution allowing SAG-VAE to generate new data via graph convolution, while still trainable via backpropagation. A learnable relational graph representation enhances SAG-VAE's robustness to perturbation and noise, while also providing deeper intuition into model performance. Experiments based on graphs show that SAG-VAE is capable of approximately retrieving edges and links between nodes based entirely on feature observations. Finally, results on image data illustrate that SAG-VAE is fairly robust against perturbations in image reconstruction and sampling.

Chen Wang, Roberto Martín-Martín, Danfei Xu et al.

We present 6-PACK, a deep learning approach to category-level 6D object pose tracking on RGB-D data. Our method tracks in real-time novel object instances of known object categories such as bowls, laptops, and mugs. 6-PACK learns to compactly represent an object by a handful of 3D keypoints, based on which the interframe motion of an object instance can be estimated through keypoint matching. These keypoints are learned end-to-end without manual supervision in order to be most effective for tracking. Our experiments show that our method substantially outperforms existing methods on the NOCS category-level 6D pose estimation benchmark and supports a physical robot to perform simple vision-based closed-loop manipulation tasks. Our code and video are available at https://sites.google.com/view/6packtracking.

Binhang Yuan, Chen Wang, Chen Luo et al.

Wind power, as an alternative to burning fossil fuels, is abundant and inexhaustible. To fully utilize wind power, wind farms are usually located in areas of high altitude and facing serious ice conditions, which can lead to serious consequences. Quick detection of blade ice accretion is crucial for the maintenance of wind farms. Unlike traditional methods of installing expensive physical detectors on wind blades, data-driven approaches are increasingly popular for inspecting the wind turbine failures. In this work, we propose a wavelet enhanced autoencoder model (WaveletAE) to identify wind turbine dysfunction by analyzing the multivariate time series monitored by the SCADA system. WaveletAE is enhanced with wavelet detail coefficients to enforce the autoencoder to capture information from multiple scales, and the CNN-LSTM architecture is applied to learn channel-wise and temporal-wise relations. The empirical study shows that the proposed model outperforms other state-of-the-art time series anomaly detection methods for real-world blade icing detection.

Chen Wang, Charles Herrmann, Ramin Zabih

While Markov Random Fields (MRFs) are widely used in computer vision, they present a quite challenging inference problem. MRF inference can be accelerated by pre-processing techniques like Dead End Elimination (DEE) or QPBO-based approaches which compute the optimal labeling of a subset of variables. These techniques are guaranteed to never wrongly label a variable but they often leave a large number of variables unlabeled. We address this shortcoming by interpreting pre-processing as a classification problem, which allows us to trade off false positives (i.e., giving a variable an incorrect label) versus false negatives (i.e., failing to label a variable). We describe an efficient discriminative rule that finds optimal solutions for a subset of variables. Our technique provides both per-instance and worst-case guarantees concerning the quality of the solution. Empirical studies were conducted over several benchmark datasets. We obtain a speedup factor of 2 to 12 over expansion moves without preprocessing, and on difficult non-submodular energy functions produce slightly lower energy.

Chen Wang, Junsong Yuan, Lihua Xie

The goal of this paper is to create a new framework for dense SLAM that is light enough for micro-robot systems based on depth camera and inertial sensor. Feature-based and direct methods are two mainstreams in visual SLAM. Both methods minimize photometric or reprojection error by iterative solutions, which are computationally expensive. To overcome this problem, we propose a non-iterative framework to reduce computational requirement. First, the attitude and heading reference system (AHRS) and axonometric projection are utilized to decouple the 6 Degree-of-Freedom (DoF) data, so that point clouds can be matched in independent spaces respectively. Second, based on single key-frame training, the matching process is carried out in frequency domain by Fourier transformation, which provides a closed-form non-iterative solution. In this manner, the time complexity is reduced to $\mathcal{O}(n \log{n})$, where $n$ is the number of matched points in each frame. To the best of our knowledge, this method is the first non-iterative and online trainable approach for data association in visual SLAM. Compared with the state-of-the-arts, it runs at a faster speed and obtains 3-D maps with higher resolution yet still with comparable accuracy.