PyTorchKR Papers

최신 논문

총 670편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2103.12496공식 코드 · Papers with Code

Revisiting Self-Supervised Monocular Depth Estimation

Self-supervised learning of depth map prediction and motion estimation from monocular video sequences is of vital importance -- since it realizes a broad range of tasks in robotics and autonomous vehicles. A large number of research efforts have enhanced the performance by tackling illumination variation, occlusions, and dynamic objects, to name a few. However, each of those efforts targets individual goals and endures as separate works. Moreover, most of previous works have adopted the same CNN architecture, not reaping architectural benefits. Therefore, the need to investigate the inter-dependency of the previous methods and the effect of architectural factors remains. To achieve these objectives, we revisit numerous previously proposed self-supervised methods for joint learning of depth and motion, perform a comprehensive empirical study, and unveil multiple crucial insights. Furthermore, we remarkably enhance the performance as a result of our study -- outperforming previous state-of-the-art performance.

arXiv:2103.11744

Large Motion Video Super-Resolution with Dual Subnet and Multi-Stage Communicated Upsampling

Video super-resolution (VSR) aims at restoring a video in low-resolution (LR) and improving it to higher-resolution (HR). Due to the characteristics of video tasks, it is very important that motion information among frames should be well concerned, summarized and utilized for guidance in a VSR algorithm. Especially, when a video contains large motion, conventional methods easily bring incoherent results or artifacts. In this paper, we propose a novel deep neural network with Dual Subnet and Multi-stage Communicated Upsampling (DSMC) for super-resolution of videos with large motion. We design a new module named U-shaped residual dense network with 3D convolution (U3D-RDN) for fine implicit motion estimation and motion compensation (MEMC) as well as coarse spatial feature extraction. And we present a new Multi-Stage Communicated Upsampling (MSCU) module to make full use of the intermediate results of upsampling for guiding the VSR. Moreover, a novel dual subnet is devised to aid the training of our DSMC, whose dual loss helps to reduce the solution space as well as enhance the generalization ability. Our experimental results confirm that our method achieves superior performance on videos with large motion compared to state-of-the-art methods.

arXiv:2103.08764

Fast and Accurate: Video Enhancement using Sparse Depth

This paper presents a general framework to build fast and accurate algorithms for video enhancement tasks such as super-resolution, deblurring, and denoising. Essential to our framework is the realization that the accuracy, rather than the density, of pixel flows is what is required for high-quality video enhancement. Most of prior works take the opposite approach: they estimate dense (per-pixel)-but generally less robust-flows, mostly using computationally costly algorithms. Instead, we propose a lightweight flow estimation algorithm; it fuses the sparse point cloud data and (even sparser and less reliable) IMU data available in modern autonomous agents to estimate the flow information. Building on top of the flow estimation, we demonstrate a general framework that integrates the flows in a plug-and-play fashion with different task-specific layers. Algorithms built in our framework achieve 1.78x - 187.41x speedup while providing a 0.42 dB - 6.70 dB quality improvement over competing methods.

arXiv:2103.05955공식 코드 · Papers with Code

Spatiotemporal Registration for Event-based Visual Odometry

A useful application of event sensing is visual odometry, especially in settings that require high-temporal resolution. The state-of-the-art method of contrast maximisation recovers the motion from a batch of events by maximising the contrast of the image of warped events. However, the cost scales with image resolution and the temporal resolution can be limited by the need for large batch sizes to yield sufficient structure in the contrast image. In this work, we propose spatiotemporal registration as a compelling technique for event-based rotational motion estimation. We theoretcally justify the approach and establish its fundamental and practical advantages over contrast maximisation. In particular, spatiotemporal registration also produces feature tracks as a by-product, which directly supports an efficient visual odometry pipeline with graph-based optimisation for motion averaging. The simplicity of our visual odometry pipeline allows it to process more than 1 M events/second. We also contribute a new event dataset for visual odometry, where motion sequences with large velocity variations were acquired using a high-precision robot arm.

arXiv:2103.02074공식 코드 · Papers with Code

Sequential Place Learning: Heuristic-Free High-Performance Long-Term Place Recognition

Sequential matching using hand-crafted heuristics has been standard practice in route-based place recognition for enhancing pairwise similarity results for nearly a decade. However, precision-recall performance of these algorithms dramatically degrades when searching on short temporal window (TW) lengths, while demanding high compute and storage costs on large robotic datasets for autonomous navigation research. Here, influenced by biological systems that robustly navigate spacetime scales even without vision, we develop a joint visual and positional representation learning technique, via a sequential process, and design a learning-based CNN+LSTM architecture, trainable via backpropagation through time, for viewpoint- and appearance-invariant place recognition. Our approach, Sequential Place Learning (SPL), is based on a CNN function that visually encodes an environment from a single traversal, thus reducing storage capacity, while an LSTM temporally fuses each visual embedding with corresponding positional data -- obtained from any source of motion estimation -- for direct sequential inference. Contrary to classical two-stage pipelines, e.g., match-then-temporally-filter, our network directly eliminates false-positive rates while jointly learning sequence matching from a single monocular image sequence, even using short TWs. Hence, we demonstrate that our model outperforms 15 classical methods while setting new state-of-the-art performance standards on 4 challenging benchmark datasets, where one of them can be considered solved with recall rates of 100% at 100% precision, correctly matching all places under extreme sunlight-darkness changes. In addition, we show that SPL can be up to 70x faster to deploy than classical methods on a 729 km route comprising 35,768 consecutive frames. Extensive experiments demonstrate the... Baseline code available at https://github.com/mchancan/deepseqslam

arXiv:2103.01306

Scalable Scene Flow from Point Clouds in the Real World

Autonomous vehicles operate in highly dynamic environments necessitating an accurate assessment of which aspects of a scene are moving and where they are moving to. A popular approach to 3D motion estimation, termed scene flow, is to employ 3D point cloud data from consecutive LiDAR scans, although such approaches have been limited by the small size of real-world, annotated LiDAR data. In this work, we introduce a new large-scale dataset for scene flow estimation derived from corresponding tracked 3D objects, which is $\sim$1,000$\times$ larger than previous real-world datasets in terms of the number of annotated frames. We demonstrate how previous works were bounded based on the amount of real LiDAR data available, suggesting that larger datasets are required to achieve state-of-the-art predictive performance. Furthermore, we show how previous heuristics for operating on point clouds such as down-sampling heavily degrade performance, motivating a new class of models that are tractable on the full point cloud. To address this issue, we introduce the FastFlow3D architecture which provides real time inference on the full point cloud. Additionally, we design human-interpretable metrics that better capture real world aspects by accounting for ego-motion and providing breakdowns per object type. We hope that this dataset may provide new opportunities for developing real world scene flow systems.

arXiv:2103.01530

A Pose-only Solution to Visual Reconstruction and Navigation

Visual navigation and three-dimensional (3D) scene reconstruction are essential for robotics to interact with the surrounding environment. Large-scale scenes and critical camera motions are great challenges facing the research community to achieve this goal. We raised a pose-only imaging geometry framework and algorithms that can help solve these challenges. The representation is a linear function of camera global translations, which allows for efficient and robust camera motion estimation. As a result, the spatial feature coordinates can be analytically reconstructed and do not require nonlinear optimization. Experiments demonstrate that the computational efficiency of recovering the scene and associated camera poses is significantly improved by 2-4 orders of magnitude. This solution might be promising to unlock real-time 3D visual computing in many forefront applications.

arXiv:2103.00760공식 코드 · Papers with Code

Self-Supervised Depth and Ego-Motion Estimation for Monocular Thermal Video Using Multi-Spectral Consistency Loss

A thermal camera can robustly capture thermal radiation images under harsh light conditions such as night scenes, tunnels, and disaster scenarios. However, despite this advantage, neither depth nor ego-motion estimation research for the thermal camera have not been actively explored so far. In this paper, we propose a self-supervised learning method for depth and ego-motion estimation from thermal images. The proposed method exploits multi-spectral consistency that consists of temperature and photometric consistency loss. The temperature consistency loss provides a fundamental self-supervisory signal by reconstructing clipped and colorized thermal images. Additionally, we design a differentiable forward warping module that can transform the coordinate system of the estimated depth map and relative pose from thermal camera to visible camera. Based on the proposed module, the photometric consistency loss can provide complementary self-supervision to networks. Networks trained with the proposed method robustly estimate the depth and pose from monocular thermal video under low-light and even zero-light conditions. To the best of our knowledge, this is the first work to simultaneously estimate both depth and ego-motion from monocular thermal video in a self-supervised manner.

arXiv:2102.12418

Rigid and non-rigid motion compensation in weight-bearing cone-beam CT of the knee using (noisy) inertial measurements

Involuntary subject motion is the main source of artifacts in weight-bearing cone-beam CT of the knee. To achieve image quality for clinical diagnosis, the motion needs to be compensated. We propose to use inertial measurement units (IMUs) attached to the leg for motion estimation. We perform a simulation study using real motion recorded with an optical tracking system. Three IMU-based correction approaches are evaluated, namely rigid motion correction, non-rigid 2D projection deformation and non-rigid 3D dynamic reconstruction. We present an initialization process based on the system geometry. With an IMU noise simulation, we investigate the applicability of the proposed methods in real applications. All proposed IMU-based approaches correct motion at least as good as a state-of-the-art marker-based approach. The structural similarity index and the root mean squared error between motion-free and motion corrected volumes are improved by 24-35% and 78-85%, respectively, compared with the uncorrected case. The noise analysis shows that the noise levels of commercially available IMUs need to be improved by a factor of $10^5$ which is currently only achieved by specialized hardware not robust enough for the application. The presented study confirms the feasibility of this novel approach and defines improvements necessary for a real application.

arXiv:2102.09656공식 코드 · Papers with Code

Relying on a rate constraint to reduce Motion Estimation complexity

This paper proposes a rate-based candidate elimination strategy for Motion Estimation, which is considered one of the main sources of encoder complexity. We build from findings of previous works that show that selected motion vectors are generally near the predictor to propose a solution that uses the motion vector bitrate to constrain the candidate search to a subset of the original search window, resulting in less distortion computations. The proposed method is not tied to a particular search pattern, which makes it applicable to several ME strategies. The technique was tested in the VVC reference software implementation and showed complexity reductions of over 80% at the cost of an average 0.74% increase in BD-Rate with respect to the original TZ Search algorithm in the LDP configuration.

arXiv:2102.02629공식 코드 · Papers with Code

Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency

We present an end-to-end joint training framework that explicitly models 6-DoF motion of multiple dynamic objects, ego-motion and depth in a monocular camera setup without supervision. Our technical contributions are three-fold. First, we highlight the fundamental difference between inverse and forward projection while modeling the individual motion of each rigid object, and propose a geometrically correct projection pipeline using a neural forward projection module. Second, we design a unified instance-aware photometric and geometric consistency loss that holistically imposes self-supervisory signals for every background and object region. Lastly, we introduce a general-purpose auto-annotation scheme using any off-the-shelf instance segmentation and optical flow models to produce video instance segmentation maps that will be utilized as input to our training pipeline. These proposed elements are validated in a detailed ablation study. Through extensive experiments conducted on the KITTI and Cityscapes dataset, our framework is shown to outperform the state-of-the-art depth and motion estimation methods. Our code, dataset, and models are available at https://github.com/SeokjuLee/Insta-DM .

arXiv:2102.00487

Nonlinear Evolutionary PDE-Based Refinement of Optical Flow

The goal of this paper is to propose two nonlinear variational models for obtaining a refined motion estimation from an image sequence. Both the proposed models can be considered as a part of a generalized framework for an accurate estimation of physics-based flow fields such as rotational and fluid flow. The first model is novel in the sense that it is divided into two phases: the first phase obtains a crude estimate of the optical flow and then the second phase refines this estimate using additional constraints. The correctness of this model is proved using an evolutionary PDE approach. The second model achieves the same refinement as the first model, but in a standard manner, using a single functional. A special feature of our models is that they permit us to provide efficient numerical implementations through the first-order primal-dual Chambolle-Pock scheme. Both the models are compared in the context of accurate estimation of angle by performing an anisotropic regularization of the divergence and curl of the flow respectively. We observe that, although both the models obtain the same level of accuracy, the two-phase model is more efficient. In fact, we empirically demonstrate that the single-phase and the two-phase models have convergence rates of order $O(1/N^2)$ and $O(1/N)$ respectively.

arXiv:2101.07756

Motion Estimation of Connected and Automated Vehicles under Communication Delay and Packet Loss of V2X Communications

The emergence of the connected and automated vehicle (CAV) technology enables numerous advanced applications in our transportation system, benefiting our daily travels in terms of safety, mobility, and sustainability. However, vehicular communication technologies such as Dedicated Short-Range Communications (DSRC) or Cellular-Based Vehicle-to-Everything (C-V2X) communications unavoidably introduce issues like communication delay and packet loss, which will downgrade the performances of any CAV applications. In this study, we propose a consensus-based motion estimation methodology to estimate the vehicle motion when the vehicular communication environment is not ideal. This methodology is developed based on the consensus-based feedforward/feedback motion control algorithm, estimating the position and speed of a CAV in the presence of communication delay and packet loss. The simulation study is conducted in a traffic scenario of unsignalized intersections, where CAVs coordinate with each other through V2X communications and cross intersections without any full stop. Game engine-based human-in-the-loop simulation results shows the proposed motion estimation methodology can cap the position estimation error to 0.5 m during periodic packet loss and time-variant communication delay.

arXiv:2101.06742

Deep Parametric Continuous Convolutional Neural Networks

Standard convolutional neural networks assume a grid structured input is available and exploit discrete convolutions as their fundamental building blocks. This limits their applicability to many real-world applications. In this paper we propose Parametric Continuous Convolution, a new learnable operator that operates over non-grid structured data. The key idea is to exploit parameterized kernel functions that span the full continuous vector space. This generalization allows us to learn over arbitrary data structures as long as their support relationship is computable. Our experiments show significant improvement over the state-of-the-art in point cloud segmentation of indoor and outdoor scenes, and lidar motion estimation of driving scenes.

arXiv:2101.06605공식 코드 · Papers with Code

MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization

We present MultiBodySync, a novel, end-to-end trainable multi-body motion segmentation and rigid registration framework for multiple input 3D point clouds. The two non-trivial challenges posed by this multi-scan multibody setting that we investigate are: (i) guaranteeing correspondence and segmentation consistency across multiple input point clouds capturing different spatial arrangements of bodies or body parts; and (ii) obtaining robust motion-based rigid body segmentation applicable to novel object categories. We propose an approach to address these issues that incorporates spectral synchronization into an iterative deep declarative network, so as to simultaneously recover consistent correspondences as well as motion segmentation. At the same time, by explicitly disentangling the correspondence and motion segmentation estimation modules, we achieve strong generalizability across different object categories. Our extensive evaluations demonstrate that our method is effective on various datasets ranging from rigid parts in articulated objects to individually moving objects in a 3D scene, be it single-view or full point clouds.

arXiv:2101.07005

Optical Flow Method for Measuring Deformation of Soil Specimen Subjected to Torsional Shearing

In this study optical flow method was used for soil small deformation measurement in laboratory tests. The main objective was to observe how the deformation distributes along the whole height of cylindrical soil specimen subjected to torsional shearing (TS test). The experiments were conducted on dry non-cohesive soil specimens under two values of isotropic pressure. Specimens were loaded with low-amplitude cyclic torque to analyze the deformation within the small strain range (0.001-0.01%). Optical flow method variant by Ce Liu (2009) was used for motion estimation from series of images. This algorithm uses scale-invariant feature transform (SIFT) for image feature extraction and coarse-to-fine matching scheme for faster calculations. The results were validated with the Particle Image Velocimetry (PIV). The results show that the displacement distribution deviates from commonly assumed linearity. Moreover, the observed deformation mechanisms analysis suggest that the shear modulus $G$ commonly determined through TS tests can be considerably overestimated.

arXiv:2101.02874공식 코드 · Papers with Code

A general framework for modeling and dynamic simulation of multibody systems using factor graphs

In this paper, we present a novel general framework grounded in the factor graph theory to solve kinematic and dynamic problems for multi-body systems. Although the motion of multi-body systems is considered to be a well-studied problem and various methods have been proposed for its solution, a unified approach providing an intuitive interpretation is still pursued. We describe how to build factor graphs to model and simulate multibody systems using both, independent and dependent coordinates. Then, batch optimization or a fixed-lag-smoother can be applied to solve the underlying optimization problem that results in a highly-sparse nonlinear minimization problem. The proposed framework has been tested in extensive simulations and validated against a commercial multibody software. We release a reference implementation as an open-source C++ library, based on the GTSAM framework, a well-known estimation library. Simulations of forward and inverse dynamics are presented, showing comparable accuracy with classical approaches. The proposed factor graph-based framework has the potential to be integrated into applications related with motion estimation and parameter identification of complex mechanical systems, ranging from mechanisms to vehicles, or robot manipulators.

arXiv:2101.01841공식 코드 · Papers with Code

CNN-based Ego-Motion Estimation for Fast MAV Maneuvers

In the field of visual ego-motion estimation for Micro Air Vehicles (MAVs), fast maneuvers stay challenging mainly because of the big visual disparity and motion blur. In the pursuit of higher robustness, we study convolutional neural networks (CNNs) that predict the relative pose between subsequent images from a fast-moving monocular camera facing a planar scene. Aided by the Inertial Measurement Unit (IMU), we mainly focus on translational motion. The networks we study have similar small model sizes (around 1.35MB) and high inference speeds (around 10 milliseconds on a mobile GPU). Images for training and testing have realistic motion blur. Departing from a network framework that iteratively warps the first image to match the second with cascaded network blocks, we study different network architectures and training strategies. Simulated datasets and a self-collected MAV flight dataset are used for evaluation. The proposed setup shows better accuracy over existing networks and traditional feature-point-based methods during fast maneuvers. Moreover, self-supervised learning outperforms supervised learning. Videos and open-sourced code are available at https://github.com/tudelft/PoseNet_Planar

arXiv:2012.15378

3D Human motion anticipation and classification

Human motion prediction and understanding is a challenging problem. Due to the complex dynamic of human motion and the non-deterministic aspect of future prediction. We propose a novel sequence-to-sequence model for human motion prediction and feature learning, trained with a modified version of generative adversarial network, with a custom loss function that takes inspiration from human motion animation and can control the variation between multiple predicted motion from the same input poses. Our model learns to predict multiple future sequences of human poses from the same input sequence. We show that the discriminator learns general presentation of human motion by using the learned feature in action recognition task. Furthermore, to quantify the quality of the non-deterministic predictions, we simultaneously train a motion-quality-assessment network that learns the probability that a given sequence of poses is a real human motion or not. We test our model on two of the largest human pose datasets: NTURGB-D and Human3.6M. We train on both single and multiple action types. Its predictive power for motion estimation is demonstrated by generating multiple plausible futures from the same input and show the effect of each of the loss functions. Furthermore, we show that it takes less than half the number of epochs to train an activity recognition network by using the feature learned from the discriminator.

arXiv:2012.08375

Practical Auto-Calibration for Spatial Scene-Understanding from Crowdsourced Dashcamera Videos

Spatial scene-understanding, including dense depth and ego-motion estimation, is an important problem in computer vision for autonomous vehicles and advanced driver assistance systems. Thus, it is beneficial to design perception modules that can utilize crowdsourced videos collected from arbitrary vehicular onboard or dashboard cameras. However, the intrinsic parameters corresponding to such cameras are often unknown or change over time. Typical manual calibration approaches require objects such as a chessboard or additional scene-specific information. On the other hand, automatic camera calibration does not have such requirements. Yet, the automatic calibration of dashboard cameras is challenging as forward and planar navigation results in critical motion sequences with reconstruction ambiguities. Structure reconstruction of complete visual-sequences that may contain tens of thousands of images is also computationally untenable. Here, we propose a system for practical monocular onboard camera auto-calibration from crowdsourced videos. We show the effectiveness of our proposed system on the KITTI raw, Oxford RobotCar, and the crowdsourced D$^2$-City datasets in varying conditions. Finally, we demonstrate its application for accurate monocular dense depth and ego-motion estimation on uncalibrated videos.