PyTorchKR Papers

최신 논문

총 208편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2104.08918공식 코드 · Papers with Code

Motion Vector Extrapolation for Video Object Detection

Despite the continued successes of computationally efficient deep neural network architectures for video object detection, performance continually arrives at the great trilemma of speed versus accuracy versus computational resources (pick two). Current attempts to exploit temporal information in video data to overcome this trilemma are bottlenecked by the state-of-the-art in object detection models. We present, a technique which performs video object detection through the use of off-the-shelf object detectors alongside existing optical flow based motion estimation techniques in parallel. Through a set of experiments on the benchmark MOT20 dataset, we demonstrate that our approach significantly reduces the baseline latency of any given object detector without sacrificing any accuracy. Further latency reduction, up to 25x lower than the original latency, can be achieved with minimal accuracy loss. MOVEX enables low latency video object detection on common CPU based systems, thus allowing for high performance video object detection beyond the domain of GPU computing. The code is available at https://github.com/juliantrue/movex.

arXiv:2104.08683공식 코드 · Papers with Code

Self-Supervised Pillar Motion Learning for Autonomous Driving

Autonomous driving can benefit from motion behavior comprehension when interacting with diverse traffic participants in highly dynamic environments. Recently, there has been a growing interest in estimating class-agnostic motion directly from point clouds. Current motion estimation methods usually require vast amount of annotated training data from self-driving scenes. However, manually labeling point clouds is notoriously difficult, error-prone and time-consuming. In this paper, we seek to answer the research question of whether the abundant unlabeled data collections can be utilized for accurate and efficient motion learning. To this end, we propose a learning framework that leverages free supervisory signals from point clouds and paired camera images to estimate motion purely via self-supervision. Our model involves a point cloud based structural consistency augmented with probabilistic motion masking as well as a cross-sensor motion regularization to realize the desired self-supervision. Experiments reveal that our approach performs competitively to supervised methods, and achieves the state-of-the-art result when combining our self-supervised model with supervised fine-tuning.

arXiv:2104.05017공식 코드 · Papers with Code

Estimating articulatory movements in speech production with transformer networks

We estimate articulatory movements in speech production from different modalities - acoustics and phonemes. Acoustic-to articulatory inversion (AAI) is a sequence-to-sequence task. On the other hand, phoneme to articulatory (PTA) motion estimation faces a key challenge in reliably aligning the text and the articulatory movements. To address this challenge, we explore the use of a transformer architecture - FastSpeech, with explicit duration modelling to learn hard alignments between the phonemes and articulatory movements. We also train a transformer model on AAI. We use correlation coefficient (CC) and root mean squared error (rMSE) to assess the estimation performance in comparison to existing methods on both tasks. We observe 154%, 11.8% & 4.8% relative improvement in CC with subject-dependent, pooled and fine-tuning strategies, respectively, for PTA estimation. Additionally, on the AAI task, we obtain 1.5%, 3% and 3.1% relative gain in CC on the same setups compared to the state-of-the-art baseline. We further present the computational benefits of having transformer architecture as representation blocks.

arXiv:2104.00431공식 코드 · Papers with Code

Unsupervised Learning of Monocular Depth and Ego-Motion Using Multiple Masks

A new unsupervised learning method of depth and ego-motion using multiple masks from monocular video is proposed in this paper. The depth estimation network and the ego-motion estimation network are trained according to the constraints of depth and ego-motion without truth values. The main contribution of our method is to carefully consider the occlusion of the pixels generated when the adjacent frames are projected to each other, and the blank problem generated in the projection target imaging plane. Two fine masks are designed to solve most of the image pixel mismatch caused by the movement of the camera. In addition, some relatively rare circumstances are considered, and repeated masking is proposed. To some extent, the method is to use a geometric relationship to filter the mismatched pixels for training, making unsupervised learning more efficient and accurate. The experiments on KITTI dataset show our method achieves good performance in terms of depth and ego-motion. The generalization capability of our method is demonstrated by training on the low-quality uncalibrated bike video dataset and evaluating on KITTI dataset, and the results are still good.

arXiv:2103.13875공식 코드 · Papers with Code

Finding Geometric Models by Clustering in the Consensus Space

We propose a new algorithm for finding an unknown number of geometric models, e.g., homographies. The problem is formalized as finding dominant model instances progressively without forming crisp point-to-model assignments. Dominant instances are found via a RANSAC-like sampling and a consolidation process driven by a model quality function considering previously proposed instances. New ones are found by clustering in the consensus space. This new formulation leads to a simple iterative algorithm with state-of-the-art accuracy while running in real-time on a number of vision problems - at least two orders of magnitude faster than the competitors on two-view motion estimation. Also, we propose a deterministic sampler reflecting the fact that real-world data tend to form spatially coherent structures. The sampler returns connected components in a progressively densified neighborhood-graph. We present a number of applications where the use of multiple geometric models improves accuracy. These include pose estimation from multiple generalized homographies; trajectory estimation of fast-moving objects; and we also propose a way of using multiple homographies in global SfM algorithms. Source code: https://github.com/danini/clustering-in-consensus-space.

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:2103.05955공식 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:2103.00760공식 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:2102.09656공식 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: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:2101.02874공식 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:1804.04813공식 코드 · Papers with Code

SpatioTemporal Feature Integration and Model Fusion for Full Reference Video Quality Assessment

Perceptual video quality assessment models are either frame-based or video-based, i.e., they apply spatiotemporal filtering or motion estimation to capture temporal video distortions. Despite their good performance on video quality databases, video-based approaches are time-consuming and harder to efficiently deploy. To balance between high performance and computational efficiency, Netflix developed the Video Multi-method Assessment Fusion (VMAF) framework, which integrates multiple quality-aware features to predict video quality. Nevertheless, this fusion framework does not fully exploit temporal video quality measurements which are relevant to temporal video distortions. To this end, we propose two improvements to the VMAF framework: SpatioTemporal VMAF and Ensemble VMAF. Both algorithms exploit efficient temporal video features which are fed into a single or multiple regression models. To train our models, we designed a large subjective database and evaluated the proposed models against state-of-the-art approaches. The compared algorithms will be made available as part of the open source package in https://github.com/Netflix/vmaf.

arXiv:2011.09697공식 코드 · Papers with Code

Deep Motion Blind Video Stabilization

Despite the advances in the field of generative models in computer vision, video stabilization still lacks a pure regressive deep-learning-based formulation. Deep video stabilization is generally formulated with the help of explicit motion estimation modules due to the lack of a dataset containing pairs of videos with similar perspective but different motion. Therefore, the deep learning approaches for this task have difficulties in the pixel-level synthesis of latent stabilized frames, and resort to motion estimation modules for indirect transformations of the unstable frames to stabilized frames, leading to the loss of visual content near the frame boundaries. In this work, we aim to declutter this over-complicated formulation of video stabilization with the help of a novel dataset that contains pairs of training videos with similar perspective but different motion, and verify its effectiveness by successfully learning motion blind full-frame video stabilization through employing strictly conventional generative techniques and further improve the stability through a curriculum-learning inspired adversarial training strategy. Through extensive experimentation, we show the quantitative and qualitative advantages of the proposed approach to the state-of-the-art video stabilization approaches. Moreover, our method achieves $\sim3\times$ speed-up over the currently available fastest video stabilization methods.

arXiv:2011.08518공식 코드 · Papers with Code

DeepSeqSLAM: A Trainable CNN+RNN for Joint Global Description and Sequence-based Place Recognition

Sequence-based place recognition methods for all-weather navigation are well-known for producing state-of-the-art results under challenging day-night or summer-winter transitions. These systems, however, rely on complex handcrafted heuristics for sequential matching - which are applied on top of a pre-computed pairwise similarity matrix between reference and query image sequences of a single route - to further reduce false-positive rates compared to single-frame retrieval methods. As a result, performing multi-frame place recognition can be extremely slow for deployment on autonomous vehicles or evaluation on large datasets, and fail when using relatively short parameter values such as a sequence length of 2 frames. In this paper, we propose DeepSeqSLAM: a trainable CNN+RNN architecture for jointly learning visual and positional representations from a single monocular image sequence of a route. We demonstrate our approach on two large benchmark datasets, Nordland and Oxford RobotCar - recorded over 728 km and 10 km routes, respectively, each during 1 year with multiple seasons, weather, and lighting conditions. On Nordland, we compare our method to two state-of-the-art sequence-based methods across the entire route under summer-winter changes using a sequence length of 2 and show that our approach can get over 72% AUC compared to 27% AUC for Delta Descriptors and 2% AUC for SeqSLAM; while drastically reducing the deployment time from around 1 hour to 1 minute against both. The framework code and video are available at https://mchancan.github.io/deepseqslam

arXiv:2010.11800공식 코드 · Papers with Code

Castle in the Sky: Dynamic Sky Replacement and Harmonization in Videos

This paper proposes a vision-based method for video sky replacement and harmonization, which can automatically generate realistic and dramatic sky backgrounds in videos with controllable styles. Different from previous sky editing methods that either focus on static photos or require inertial measurement units integrated in smartphones on shooting videos, our method is purely vision-based, without any requirements on the capturing devices, and can be well applied to either online or offline processing scenarios. Our method runs in real-time and is free of user interactions. We decompose this artistic creation process into a couple of proxy tasks including sky matting, motion estimation, and image blending. Experiments are conducted on videos diversely captured in the wild by handheld smartphones and dash cameras, and show high fidelity and good generalization of our method in both visual quality and lighting/motion dynamics. Our code and animated results are available at \url{https://jiupinjia.github.io/skyar/}.

arXiv:2010.07704공식 코드 · Papers with Code

Unsupervised Learning of Depth and Ego-Motion from Cylindrical Panoramic Video with Applications for Virtual Reality

We introduce a convolutional neural network model for unsupervised learning of depth and ego-motion from cylindrical panoramic video. Panoramic depth estimation is an important technology for applications such as virtual reality, 3D modeling, and autonomous robotic navigation. In contrast to previous approaches for applying convolutional neural networks to panoramic imagery, we use the cylindrical panoramic projection which allows for the use of the traditional CNN layers such as convolutional filters and max pooling without modification. Our evaluation of synthetic and real data shows that unsupervised learning of depth and ego-motion on cylindrical panoramic images can produce high-quality depth maps and that an increased field-of-view improves ego-motion estimation accuracy. We create two new datasets to evaluate our approach: a synthetic dataset created using the CARLA simulator, and Headcam, a novel dataset of panoramic video collected from a helmet-mounted camera while biking in an urban setting. We also apply our network to the problem of converting monocular panoramas to stereo panoramas.

arXiv:2010.02484공식 코드 · Papers with Code

Exposure Trajectory Recovery from Motion Blur

Motion blur in dynamic scenes is an important yet challenging research topic. Recently, deep learning methods have achieved impressive performance for dynamic scene deblurring. However, the motion information contained in a blurry image has yet to be fully explored and accurately formulated because: (i) the ground truth of dynamic motion is difficult to obtain; (ii) the temporal ordering is destroyed during the exposure; and (iii) the motion estimation from a blurry image is highly ill-posed. By revisiting the principle of camera exposure, motion blur can be described by the relative motions of sharp content with respect to each exposed position. In this paper, we define exposure trajectories, which represent the motion information contained in a blurry image and explain the causes of motion blur. A novel motion offset estimation framework is proposed to model pixel-wise displacements of the latent sharp image at multiple timepoints. Under mild constraints, our method can recover dense, (non-)linear exposure trajectories, which significantly reduce temporal disorder and ill-posed problems. Finally, experiments demonstrate that the recovered exposure trajectories not only capture accurate and interpretable motion information from a blurry image, but also benefit motion-aware image deblurring and warping-based video extraction tasks. Codes are available on https://github.com/yjzhang96/Motion-ETR.