PyTorchKR Papers

최신 논문

총 140편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1904.12599

Self-Supervised Flow Estimation using Geometric Regularization with Applications to Camera Image and Grid Map Sequences

We present a self-supervised approach to estimate flow in camera image and top-view grid map sequences using fully convolutional neural networks in the domain of automated driving. We extend existing approaches for self-supervised optical flow estimation by adding a regularizer expressing motion consistency assuming a static environment. However, as this assumption is violated for other moving traffic participants we also estimate a mask to scale this regularization. Adding a regularization towards motion consistency improves convergence and flow estimation accuracy. Furthermore, we scale the errors due to spatial flow inconsistency by a mask that we derive from the motion mask. This improves accuracy in regions where the flow drastically changes due to a better separation between static and dynamic environment. We apply our approach to optical flow estimation from camera image sequences, validate on odometry estimation and suggest a method to iteratively increase optical flow estimation accuracy using the generated motion masks. Finally, we provide quantitative and qualitative results based on the KITTI odometry and tracking benchmark for scene flow estimation based on grid map sequences. We show that we can improve accuracy and convergence when applying motion and spatial consistency regularization.

arXiv:1904.11163

A Conditional Adversarial Network for Scene Flow Estimation

The problem of Scene flow estimation in depth videos has been attracting attention of researchers of robot vision, due to its potential application in various areas of robotics. The conventional scene flow methods are difficult to use in reallife applications due to their long computational overhead. We propose a conditional adversarial network SceneFlowGAN for scene flow estimation. The proposed SceneFlowGAN uses loss function at two ends: both generator and descriptor ends. The proposed network is the first attempt to estimate scene flow using generative adversarial networks, and is able to estimate both the optical flow and disparity from the input stereo images simultaneously. The proposed method is experimented on a large RGB-D benchmark sceneflow dataset.

arXiv:1904.08913

Deep Rigid Instance Scene Flow

In this paper we tackle the problem of scene flow estimation in the context of self-driving. We leverage deep learning techniques as well as strong priors as in our application domain the motion of the scene can be composed by the motion of the robot and the 3D motion of the actors in the scene. We formulate the problem as energy minimization in a deep structured model, which can be solved efficiently in the GPU by unrolling a Gaussian-Newton solver. Our experiments in the challenging KITTI scene flow dataset show that we outperform the state-of-the-art by a very large margin, while being 800 times faster.

arXiv:1904.06116공식 코드 · Papers with Code

PWOC-3D: Deep Occlusion-Aware End-to-End Scene Flow Estimation

In the last few years, convolutional neural networks (CNNs) have demonstrated increasing success at learning many computer vision tasks including dense estimation problems such as optical flow and stereo matching. However, the joint prediction of these tasks, called scene flow, has traditionally been tackled using slow classical methods based on primitive assumptions which fail to generalize. The work presented in this paper overcomes these drawbacks efficiently (in terms of speed and accuracy) by proposing PWOC-3D, a compact CNN architecture to predict scene flow from stereo image sequences in an end-to-end supervised setting. Further, large motion and occlusions are well-known problems in scene flow estimation. PWOC-3D employs specialized design decisions to explicitly model these challenges. In this regard, we propose a novel self-supervised strategy to predict occlusions from images (learned without any labeled occlusion data). Leveraging several such constructs, our network achieves competitive results on the KITTI benchmark and the challenging FlyingThings3D dataset. Especially on KITTI, PWOC-3D achieves the second place among end-to-end deep learning methods with 48 times fewer parameters than the top-performing method.

arXiv:1902.10099

SceneFlowFields++: Multi-frame Matching, Visibility Prediction, and Robust Interpolation for Scene Flow Estimation

State-of-the-art scene flow algorithms pursue the conflicting targets of accuracy, run time, and robustness. With the successful concept of pixel-wise matching and sparse-to-dense interpolation, we push the limits of scene flow estimation. Avoiding strong assumptions on the domain or the problem yields a more robust algorithm. This algorithm is fast because we avoid explicit regularization during matching, which allows an efficient computation. Using image information from multiple time steps and explicit visibility prediction based on previous results, we achieve competitive performances on different data sets. Our contributions and results are evaluated in comparative experiments. Overall, we present an accurate scene flow algorithm that is faster and more generic than any individual benchmark leader.

arXiv:1810.11205

Deep learning based 2.5D flow field estimation for maximum intensity projections of 4D optical coherence tomography

In microsurgery, lasers have emerged as precise tools for bone ablation. A challenge is automatic control of laser bone ablation with 4D optical coherence tomography (OCT). OCT as high resolution imaging modality provides volumetric images of tissue and foresees information of bone position and orientation (pose) as well as thickness. However, existing approaches for OCT based laser ablation control rely on external tracking systems or invasively ablated artificial landmarks for tracking the pose of the OCT probe relative to the tissue. This can be superseded by estimating the scene flow caused by relative movement between OCT-based laser ablation system and patient. Therefore, this paper deals with 2.5D scene flow estimation of volumetric OCT images for application in laser ablation. We present a semi-supervised convolutional neural network based tracking scheme for subsequent 3D OCT volumes and apply it to a realistic semi-synthetic data set of ex vivo human temporal bone specimen. The scene flow is estimated in a two-stage approach. In the first stage, 2D lateral scene flow is computed on census-transformed en-face arguments-of-maximum intensity projections. Subsequent to this, the projections are warped by predicted lateral flow and 1D depth flow is estimated. The neural network is trained semi-supervised by combining error to ground truth and the reconstruction error of warped images with assumptions of spatial flow smoothness. Quantitative evaluation reveals a mean endpoint error of $ (4.7\pm{}3.5) $ voxel or $ 27.5 \pm 20.5 \mu\mathrm{m} $ for scene flow estimation caused by simulated relative movement between the OCT probe and bone. The scene flow estimation for 4D OCT enables its use for markerless tracking of mastoid bone structures for image guidance in general, and automated laser ablation control.

arXiv:1810.06125공식 코드 · Papers with Code

Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understanding

Learning to estimate 3D geometry in a single frame and optical flow from consecutive frames by watching unlabeled videos via deep convolutional network has made significant progress recently. Current state-of-the-art (SoTA) methods treat the two tasks independently. One typical assumption of the existing depth estimation methods is that the scenes contain no independent moving objects. while object moving could be easily modeled using optical flow. In this paper, we propose to address the two tasks as a whole, i.e. to jointly understand per-pixel 3D geometry and motion. This eliminates the need of static scene assumption and enforces the inherent geometrical consistency during the learning process, yielding significantly improved results for both tasks. We call our method as "Every Pixel Counts++" or "EPC++". Specifically, during training, given two consecutive frames from a video, we adopt three parallel networks to predict the camera motion (MotionNet), dense depth map (DepthNet), and per-pixel optical flow between two frames (OptFlowNet) respectively. The three types of information are fed into a holistic 3D motion parser (HMP), and per-pixel 3D motion of both rigid background and moving objects are disentangled and recovered. Comprehensive experiments were conducted on datasets with different scenes, including driving scenario (KITTI 2012 and KITTI 2015 datasets), mixed outdoor/indoor scenes (Make3D) and synthetic animation (MPI Sintel dataset). Performance on the five tasks of depth estimation, optical flow estimation, odometry, moving object segmentation and scene flow estimation shows that our approach outperforms other SoTA methods. Code will be available at: https://github.com/chenxuluo/EPC.

arXiv:1808.10146

Dense Scene Flow from Stereo Disparity and Optical Flow

Scene flow describes 3D motion in a 3D scene. It can either be modeled as a single task, or it can be reconstructed from the auxiliary tasks of stereo depth and optical flow estimation. While the second method can achieve real-time performance by using real-time auxiliary methods, it will typically produce non-dense results. In this representation of a basic combination approach for scene flow estimation, we will tackle the problem of non-density by interpolation.

arXiv:1808.01838

Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimation

Occlusions play an important role in disparity and optical flow estimation, since matching costs are not available in occluded areas and occlusions indicate depth or motion boundaries. Moreover, occlusions are relevant for motion segmentation and scene flow estimation. In this paper, we present an efficient learning-based approach to estimate occlusion areas jointly with disparities or optical flow. The estimated occlusions and motion boundaries clearly improve over the state-of-the-art. Moreover, we present networks with state-of-the-art performance on the popular KITTI benchmark and good generic performance. Making use of the estimated occlusions, we also show improved results on motion segmentation and scene flow estimation.

arXiv:1807.03464

SceneEDNet: A Deep Learning Approach for Scene Flow Estimation

Estimating scene flow in RGB-D videos is attracting much interest of the computer vision researchers, due to its potential applications in robotics. The state-of-the-art techniques for scene flow estimation, typically rely on the knowledge of scene structure of the frame and the correspondence between frames. However, with the increasing amount of RGB-D data captured from sophisticated sensors like Microsoft Kinect, and the recent advances in the area of sophisticated deep learning techniques, introduction of an efficient deep learning technique for scene flow estimation, is becoming important. This paper introduces a first effort to apply a deep learning method for direct estimation of scene flow by presenting a fully convolutional neural network with an encoder-decoder (ED) architecture. The proposed network SceneEDNet involves estimation of three dimensional motion vectors of all the scene points from sequence of stereo images. The training for direct estimation of scene flow is done using consecutive pairs of stereo images and corresponding scene flow ground truth. The proposed architecture is applied on a huge dataset and provides meaningful results.

arXiv:1806.10556

Every Pixel Counts: Unsupervised Geometry Learning with Holistic 3D Motion Understanding

Learning to estimate 3D geometry in a single image by watching unlabeled videos via deep convolutional network has made significant process recently. Current state-of-the-art (SOTA) methods, are based on the learning framework of rigid structure-from-motion, where only 3D camera ego motion is modeled for geometry estimation.However, moving objects also exist in many videos, e.g. moving cars in a street scene. In this paper, we tackle such motion by additionally incorporating per-pixel 3D object motion into the learning framework, which provides holistic 3D scene flow understanding and helps single image geometry estimation. Specifically, given two consecutive frames from a video, we adopt a motion network to predict their relative 3D camera pose and a segmentation mask distinguishing moving objects and rigid background. An optical flow network is used to estimate dense 2D per-pixel correspondence. A single image depth network predicts depth maps for both images. The four types of information, i.e. 2D flow, camera pose, segment mask and depth maps, are integrated into a differentiable holistic 3D motion parser (HMP), where per-pixel 3D motion for rigid background and moving objects are recovered. We design various losses w.r.t. the two types of 3D motions for training the depth and motion networks, yielding further error reduction for estimated geometry. Finally, in order to solve the 3D motion confusion from monocular videos, we combine stereo images into joint training. Experiments on KITTI 2015 dataset show that our estimated geometry, 3D motion and moving object masks, not only are constrained to be consistent, but also significantly outperforms other SOTA algorithms, demonstrating the benefits of our approach.

arXiv:1512.02134

A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation

Recent work has shown that optical flow estimation can be formulated as a supervised learning task and can be successfully solved with convolutional networks. Training of the so-called FlowNet was enabled by a large synthetically generated dataset. The present paper extends the concept of optical flow estimation via convolutional networks to disparity and scene flow estimation. To this end, we propose three synthetic stereo video datasets with sufficient realism, variation, and size to successfully train large networks. Our datasets are the first large-scale datasets to enable training and evaluating scene flow methods. Besides the datasets, we present a convolutional network for real-time disparity estimation that provides state-of-the-art results. By combining a flow and disparity estimation network and training it jointly, we demonstrate the first scene flow estimation with a convolutional network.

arXiv:1704.03273

Simultaneous Stereo Video Deblurring and Scene Flow Estimation

Videos for outdoor scene often show unpleasant blur effects due to the large relative motion between the camera and the dynamic objects and large depth variations. Existing works typically focus monocular video deblurring. In this paper, we propose a novel approach to deblurring from stereo videos. In particular, we exploit the piece-wise planar assumption about the scene and leverage the scene flow information to deblur the image. Unlike the existing approach [31] which used a pre-computed scene flow, we propose a single framework to jointly estimate the scene flow and deblur the image, where the motion cues from scene flow estimation and blur information could reinforce each other, and produce superior results than the conventional scene flow estimation or stereo deblurring methods. We evaluate our method extensively on two available datasets and achieve significant improvement in flow estimation and removing the blur effect over the state-of-the-art methods.

arXiv:1612.02590

Scene Flow Estimation: A Survey

This paper is the first to review the scene flow estimation field, which analyzes and compares methods, technical challenges, evaluation methodologies and performance of scene flow estimation. Existing algorithms are categorized in terms of scene representation, data source, and calculation scheme, and the pros and cons in each category are compared briefly. The datasets and evaluation protocols are enumerated, and the performance of the most representative methods is presented. A future vision is illustrated with few questions arisen for discussion. This survey presents a general introduction and analysis of scene flow estimation.

arXiv:1710.02124

Multiframe Scene Flow with Piecewise Rigid Motion

We introduce a novel multiframe scene flow approach that jointly optimizes the consistency of the patch appearances and their local rigid motions from RGB-D image sequences. In contrast to the competing methods, we take advantage of an oversegmentation of the reference frame and robust optimization techniques. We formulate scene flow recovery as a global non-linear least squares problem which is iteratively solved by a damped Gauss-Newton approach. As a result, we obtain a qualitatively new level of accuracy in RGB-D based scene flow estimation which can potentially run in real-time. Our method can handle challenging cases with rigid, piecewise rigid, articulated and moderate non-rigid motion, and does not rely on prior knowledge about the types of motions and deformations. Extensive experiments on synthetic and real data show that our method outperforms state-of-the-art.

arXiv:1801.04720

Combining Stereo Disparity and Optical Flow for Basic Scene Flow

Scene flow is a description of real world motion in 3D that contains more information than optical flow. Because of its complexity there exists no applicable variant for real-time scene flow estimation in an automotive or commercial vehicle context that is sufficiently robust and accurate. Therefore, many applications estimate the 2D optical flow instead. In this paper, we examine the combination of top-performing state-of-the-art optical flow and stereo disparity algorithms in order to achieve a basic scene flow. On the public KITTI Scene Flow Benchmark we demonstrate the reasonable accuracy of the combination approach and show its speed in computation.

arXiv:1804.04259공식 코드 · Papers with Code

Learning Rigidity in Dynamic Scenes with a Moving Camera for 3D Motion Field Estimation

Estimation of 3D motion in a dynamic scene from a temporal pair of images is a core task in many scene understanding problems. In real world applications, a dynamic scene is commonly captured by a moving camera (i.e., panning, tilting or hand-held), increasing the task complexity because the scene is observed from different view points. The main challenge is the disambiguation of the camera motion from scene motion, which becomes more difficult as the amount of rigidity observed decreases, even with successful estimation of 2D image correspondences. Compared to other state-of-the-art 3D scene flow estimation methods, in this paper we propose to \emph{learn} the rigidity of a scene in a supervised manner from a large collection of dynamic scene data, and directly infer a rigidity mask from two sequential images with depths. With the learned network, we show how we can effectively estimate camera motion and projected scene flow using computed 2D optical flow and the inferred rigidity mask. For training and testing the rigidity network, we also provide a new semi-synthetic dynamic scene dataset (synthetic foreground objects with a real background) and an evaluation split that accounts for the percentage of observed non-rigid pixels. Through our evaluation we show the proposed framework outperforms current state-of-the-art scene flow estimation methods in challenging dynamic scenes.

arXiv:1804.11276

4D Temporally Coherent Light-field Video

Light-field video has recently been used in virtual and augmented reality applications to increase realism and immersion. However, existing light-field methods are generally limited to static scenes due to the requirement to acquire a dense scene representation. The large amount of data and the absence of methods to infer temporal coherence pose major challenges in storage, compression and editing compared to conventional video. In this paper, we propose the first method to extract a spatio-temporally coherent light-field video representation. A novel method to obtain Epipolar Plane Images (EPIs) from a spare light-field camera array is proposed. EPIs are used to constrain scene flow estimation to obtain 4D temporally coherent representations of dynamic light-fields. Temporal coherence is achieved on a variety of light-field datasets. Evaluation of the proposed light-field scene flow against existing multi-view dense correspondence approaches demonstrates a significant improvement in accuracy of temporal coherence.

arXiv:1806.02170

PointFlowNet: Learning Representations for Rigid Motion Estimation from Point Clouds

Despite significant progress in image-based 3D scene flow estimation, the performance of such approaches has not yet reached the fidelity required by many applications. Simultaneously, these applications are often not restricted to image-based estimation: laser scanners provide a popular alternative to traditional cameras, for example in the context of self-driving cars, as they directly yield a 3D point cloud. In this paper, we propose to estimate 3D motion from such unstructured point clouds using a deep neural network. In a single forward pass, our model jointly predicts 3D scene flow as well as the 3D bounding box and rigid body motion of objects in the scene. While the prospect of estimating 3D scene flow from unstructured point clouds is promising, it is also a challenging task. We show that the traditional global representation of rigid body motion prohibits inference by CNNs, and propose a translation equivariant representation to circumvent this problem. For training our deep network, a large dataset is required. Because of this, we augment real scans from KITTI with virtual objects, realistically modeling occlusions and simulating sensor noise. A thorough comparison with classic and learning-based techniques highlights the robustness of the proposed approach.

arXiv:2610.10759v1cs.CV

MESSENGER: 자기회귀적 다음 프레임 예측을 통한 메모리 강화 순차 씬 플로우 추정

MESSENGER: Memory-Enhanced Sequential Scene Flow Estimation via Autoregressive Next-Frame Forecasting

씬 플로우(Scene flow)는 동적 시나리오에서 저수준 3D 모션 변위를 포착할 수 있습니다. 순간적인 두 프레임 모션에 의존하는 초기 쌍별(pairwise) 추정기는 장기적인 시간적 상관관계가 결여되어 있으며 미래 예측 시 외삽(extrapolation) 능력이 떨어지는 문제도 겪습니다. 최근 일부 연구에서 시퀀스-투-시퀀스 방식으로 다중 프레임 씬 플로우 추정을 시도하고 있으나, 일반적으로 입력 프레임이 증가함에 따라 막대한 연산 오버헤드가 발생하며 비효과적인 모션 전파로 인해 장기 예측 성능이 저하되는 한계가 있습니다. 이러한 문제를 해결하기 위해, 본 논문에서는 MESSENGER라는 새로운 메모리 강화 순차 씬 플로우 파이프라인을 제안합니다. 연속적인 시퀀스 내에서 장기적인 시간적 의존성을 자연스럽게 충분히 발굴하기 위해, 과거의 플로우 추정치와 잠재 상태(latent states)를 명시적으로 저장하는 메모리 버퍼를 설계했습니다. 각 입력 프레임에 대해, 시간적으로 저장된 플로우와 상태는 다음 프레임 예측 방식으로 상관관계를 맺고 검색되어 현재의 초기화된 플로우를 예측합니다. 또한 신뢰할 수 없는 검색 결과를 필터링하고 누적 오차를 완화하기 위해 불확실성 인지 재가중치 모듈을 개발했습니다. nuScenes 및 Argoverse 2 데이터셋에 대한 광범위한 실험을 통해 MESSENGER의 SOTA(state-of-the-art) 성능을 입증하였으며, 장기 미래 외삽에서 EPE3D를 nuScenes에서 71.6%, Argoverse 2에서 67.7% 감소시켰습니다. 이러한 우수성은 네트워크가 과거 관측을 기반으로 다음 프레임 분포를 점진적으로 학습하도록 자연스럽게 유도하는 자기회귀적 예측 패러다임 설계 덕분입니다. 코드는 https://github.com/liujiuming123/Messenger 에서 공개될 예정입니다.