PyTorchKR Papers

최신 논문

총 2,148편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2103.06422공식 코드 · Papers with Code

Holistic 3D Scene Understanding from a Single Image with Implicit Representation

We present a new pipeline for holistic 3D scene understanding from a single image, which could predict object shapes, object poses, and scene layout. As it is a highly ill-posed problem, existing methods usually suffer from inaccurate estimation of both shapes and layout especially for the cluttered scene due to the heavy occlusion between objects. We propose to utilize the latest deep implicit representation to solve this challenge. We not only propose an image-based local structured implicit network to improve the object shape estimation, but also refine the 3D object pose and scene layout via a novel implicit scene graph neural network that exploits the implicit local object features. A novel physical violation loss is also proposed to avoid incorrect context between objects. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods in terms of object shape, scene layout estimation, and 3D object detection.

arXiv:2103.05558

Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph Analysis

Scene understanding is a critical problem in computer vision. In this paper, we propose a 3D point-based scene graph generation ($\mathbf{SGG_{point}}$) framework to effectively bridge perception and reasoning to achieve scene understanding via three sequential stages, namely scene graph construction, reasoning, and inference. Within the reasoning stage, an EDGE-oriented Graph Convolutional Network ($\texttt{EdgeGCN}$) is created to exploit multi-dimensional edge features for explicit relationship modeling, together with the exploration of two associated twinning interaction mechanisms between nodes and edges for the independent evolution of scene graph representations. Overall, our integrated $\mathbf{SGG_{point}}$ framework is established to seek and infer scene structures of interest from both real-world and synthetic 3D point-based scenes. Our experimental results show promising edge-oriented reasoning effects on scene graph generation studies. We also demonstrate our method advantage on several traditional graph representation learning benchmark datasets, including the node-wise classification on citation networks and whole-graph recognition problems for molecular analysis.

arXiv:2103.03651

Fine-Grained Off-Road Semantic Segmentation and Mapping via Contrastive Learning

Road detection or traversability analysis has been a key technique for a mobile robot to traverse complex off-road scenes. The problem has been mainly formulated in early works as a binary classification one, e.g. associating pixels with road or non-road labels. Whereas understanding scenes with fine-grained labels are needed for off-road robots, as scenes are very diverse, and the various mechanical performance of off-road robots may lead to different definitions of safe regions to traverse. How to define and annotate fine-grained labels to achieve meaningful scene understanding for a robot to traverse off-road is still an open question. This research proposes a contrastive learning based method. With a set of human-annotated anchor patches, a feature representation is learned to discriminate regions with different traversability, a method of fine-grained semantic segmentation and mapping is subsequently developed for off-road scene understanding. Experiments are conducted on a dataset of three driving segments that represent very diverse off-road scenes. An anchor accuracy of 89.8% is achieved by evaluating the matching with human-annotated image patches in cross-scene validation. Examined by associated 3D LiDAR data, the fine-grained segments of visual images are demonstrated to have different levels of toughness and terrain elevation, which represents their semantical meaningfulness. The resultant maps contain both fine-grained labels and confidence values, providing rich information to support a robot traversing complex off-road scenes.

arXiv:2103.02451공식 코드 · Papers with Code

Multimodal Scale Consistency and Awareness for Monocular Self-Supervised Depth Estimation

Dense depth estimation is essential to scene-understanding for autonomous driving. However, recent self-supervised approaches on monocular videos suffer from scale-inconsistency across long sequences. Utilizing data from the ubiquitously copresent global positioning systems (GPS), we tackle this challenge by proposing a dynamically-weighted GPS-to-Scale (g2s) loss to complement the appearance-based losses. We emphasize that the GPS is needed only during the multimodal training, and not at inference. The relative distance between frames captured through the GPS provides a scale signal that is independent of the camera setup and scene distribution, resulting in richer learned feature representations. Through extensive evaluation on multiple datasets, we demonstrate scale-consistent and -aware depth estimation during inference, improving the performance even when training with low-frequency GPS data.

arXiv:2103.01593

Simulation-to-Real domain adaptation with teacher-student learning for endoscopic instrument segmentation

Purpose: Segmentation of surgical instruments in endoscopic videos is essential for automated surgical scene understanding and process modeling. However, relying on fully supervised deep learning for this task is challenging because manual annotation occupies valuable time of the clinical experts. Methods: We introduce a teacher-student learning approach that learns jointly from annotated simulation data and unlabeled real data to tackle the erroneous learning problem of the current consistency-based unsupervised domain adaptation framework. Results: Empirical results on three datasets highlight the effectiveness of the proposed framework over current approaches for the endoscopic instrument segmentation task. Additionally, we provide analysis of major factors affecting the performance on all datasets to highlight the strengths and failure modes of our approach. Conclusion: We show that our proposed approach can successfully exploit the unlabeled real endoscopic video frames and improve generalization performance over pure simulation-based training and the previous state-of-the-art. This takes us one step closer to effective segmentation of surgical tools in the annotation scarce setting.

arXiv:2103.00868공식 코드 · Papers with Code

Panoramic Panoptic Segmentation: Towards Complete Surrounding Understanding via Unsupervised Contrastive Learning

In this work, we introduce panoramic panoptic segmentation as the most holistic scene understanding both in terms of field of view and image level understanding for standard camera based input. A complete surrounding understanding provides a maximum of information to the agent, which is essential for any intelligent vehicle in order to make informed decisions in a safety-critical dynamic environment such as real-world traffic. In order to overcome the lack of annotated panoramic images, we propose a framework which allows model training on standard pinhole images and transfers the learned features to a different domain. Using our proposed method, we manage to achieve significant improvements of over 5% measured in PQ over non-adapted models on our Wild Panoramic Panoptic Segmentation (WildPPS) dataset. We show that our proposed Panoramic Robust Feature (PRF) framework is not only suitable to improve performance on panoramic images but can be beneficial whenever model training and deployment are executed on data taken from different distributions. As an additional contribution, we publish WildPPS: The first panoramic panoptic image dataset to foster progress in surrounding perception.

arXiv:2103.00738공식 코드 · Papers with Code

FPS-Net: A Convolutional Fusion Network for Large-Scale LiDAR Point Cloud Segmentation

Scene understanding based on LiDAR point cloud is an essential task for autonomous cars to drive safely, which often employs spherical projection to map 3D point cloud into multi-channel 2D images for semantic segmentation. Most existing methods simply stack different point attributes/modalities (e.g. coordinates, intensity, depth, etc.) as image channels to increase information capacity, but ignore distinct characteristics of point attributes in different image channels. We design FPS-Net, a convolutional fusion network that exploits the uniqueness and discrepancy among the projected image channels for optimal point cloud segmentation. FPS-Net adopts an encoder-decoder structure. Instead of simply stacking multiple channel images as a single input, we group them into different modalities to first learn modality-specific features separately and then map the learned features into a common high-dimensional feature space for pixel-level fusion and learning. Specifically, we design a residual dense block with multiple receptive fields as a building block in the encoder which preserves detailed information in each modality and learns hierarchical modality-specific and fused features effectively. In the FPS-Net decoder, we use a recurrent convolution block likewise to hierarchically decode fused features into output space for pixel-level classification. Extensive experiments conducted on two widely adopted point cloud datasets show that FPS-Net achieves superior semantic segmentation as compared with state-of-the-art projection-based methods. In addition, the proposed modality fusion idea is compatible with typical projection-based methods and can be incorporated into them with consistent performance improvements.

arXiv:2103.00586

A Kinematic Bottleneck Approach For Pose Regression of Flexible Surgical Instruments directly from Images

3-D pose estimation of instruments is a crucial step towards automatic scene understanding in robotic minimally invasive surgery. Although robotic systems can potentially directly provide joint values, this information is not commonly exploited inside the operating room, due to its possible unreliability, limited access and the time-consuming calibration required, especially for continuum robots. For this reason, standard approaches for 3-D pose estimation involve the use of external tracking systems. Recently, image-based methods have emerged as promising, non-invasive alternatives. While many image-based approaches in the literature have shown accurate results, they generally require either a complex iterative optimization for each processed image, making them unsuitable for real-time applications, or a large number of manually-annotated images for efficient learning. In this paper we propose a self-supervised image-based method, exploiting, at training time only, the imprecise kinematic information provided by the robot. In order to avoid introducing time-consuming manual annotations, the problem is formulated as an auto-encoder, smartly bottlenecked by the presence of a physical model of the robotic instruments and surgical camera, forcing a separation between image background and kinematic content. Validation of the method was performed on semi-synthetic, phantom and in-vivo datasets, obtained using a flexible robotized endoscope, showing promising results for real-time image-based 3-D pose estimation of surgical instruments.

arXiv:2102.13258공식 코드 · Papers with Code

Boundary-induced and scene-aggregated network for monocular depth prediction

Monocular depth prediction is an important task in scene understanding. It aims to predict the dense depth of a single RGB image. With the development of deep learning, the performance of this task has made great improvements. However, two issues remain unresolved: (1) The deep feature encodes the wrong farthest region in a scene, which leads to a distorted 3D structure of the predicted depth; (2) The low-level features are insufficient utilized, which makes it even harder to estimate the depth near the edge with sudden depth change. To tackle these two issues, we propose the Boundary-induced and Scene-aggregated network (BS-Net). In this network, the Depth Correlation Encoder (DCE) is first designed to obtain the contextual correlations between the regions in an image, and perceive the farthest region by considering the correlations. Meanwhile, the Bottom-Up Boundary Fusion (BUBF) module is designed to extract accurate boundary that indicates depth change. Finally, the Stripe Refinement module (SRM) is designed to refine the dense depth induced by the boundary cue, which improves the boundary accuracy of the predicted depth. Several experimental results on the NYUD v2 dataset and \xff{the iBims-1 dataset} illustrate the state-of-the-art performance of the proposed approach. And the SUN-RGBD dataset is employed to evaluate the generalization of our method. Code is available at https://github.com/XuefengBUPT/BS-Net.

arXiv:2102.12472공식 코드 · Papers with Code

4D Panoptic LiDAR Segmentation

Temporal semantic scene understanding is critical for self-driving cars or robots operating in dynamic environments. In this paper, we propose 4D panoptic LiDAR segmentation to assign a semantic class and a temporally-consistent instance ID to a sequence of 3D points. To this end, we present an approach and a point-centric evaluation metric. Our approach determines a semantic class for every point while modeling object instances as probability distributions in the 4D spatio-temporal domain. We process multiple point clouds in parallel and resolve point-to-instance associations, effectively alleviating the need for explicit temporal data association. Inspired by recent advances in benchmarking of multi-object tracking, we propose to adopt a new evaluation metric that separates the semantic and point-to-instance association aspects of the task. With this work, we aim at paving the road for future developments of temporal LiDAR panoptic perception.

arXiv:2102.11730공식 코드 · Papers with Code

RGB-D Railway Platform Monitoring and Scene Understanding for Enhanced Passenger Safety

Automated monitoring and analysis of passenger movement in safety-critical parts of transport infrastructures represent a relevant visual surveillance task. Recent breakthroughs in visual representation learning and spatial sensing opened up new possibilities for detecting and tracking humans and objects within a 3D spatial context. This paper proposes a flexible analysis scheme and a thorough evaluation of various processing pipelines to detect and track humans on a ground plane, calibrated automatically via stereo depth and pedestrian detection. We consider multiple combinations within a set of RGB- and depth-based detection and tracking modalities. We exploit the modular concepts of Meshroom [2] and demonstrate its use as a generic vision processing pipeline and scalable evaluation framework. Furthermore, we introduce a novel open RGB-D railway platform dataset with annotations to support research activities in automated RGB-D surveillance. We present quantitative results for multiple object detection and tracking for various algorithmic combinations on our dataset. Results indicate that the combined use of depth-based spatial information and learned representations yields substantially enhanced detection and tracking accuracies. As demonstrated, these enhancements are especially pronounced in adverse situations when occlusions and objects not captured by learned representations are present.

arXiv:2102.08945공식 코드 · Papers with Code

Weakly Supervised Learning of Rigid 3D Scene Flow

We propose a data-driven scene flow estimation algorithm exploiting the observation that many 3D scenes can be explained by a collection of agents moving as rigid bodies. At the core of our method lies a deep architecture able to reason at the \textbf{object-level} by considering 3D scene flow in conjunction with other 3D tasks. This object level abstraction, enables us to relax the requirement for dense scene flow supervision with simpler binary background segmentation mask and ego-motion annotations. Our mild supervision requirements make our method well suited for recently released massive data collections for autonomous driving, which do not contain dense scene flow annotations. As output, our model provides low-level cues like pointwise flow and higher-level cues such as holistic scene understanding at the level of rigid objects. We further propose a test-time optimization refining the predicted rigid scene flow. We showcase the effectiveness and generalization capacity of our method on four different autonomous driving datasets. We release our source code and pre-trained models under \url{github.com/zgojcic/Rigid3DSceneFlow}.

arXiv:2102.07997공식 코드 · Papers with Code

A2-FPN for Semantic Segmentation of Fine-Resolution Remotely Sensed Images

Semantic segmentation using fine-resolution remotely sensed images plays a critical role in many practical applications, such as urban planning, environmental protection, natural and anthropogenic landscape monitoring, etc. However, the automation of semantic segmentation, i.e., automatic categorization/labeling and segmentation is still a challenging task, particularly for fine-resolution images with huge spatial and spectral complexity. Addressing such a problem represents an exciting research field, which paves the way for scene-level landscape pattern analysis and decision making. In this paper, we propose an approach for automatic land segmentation based on the Feature Pyramid Network (FPN). As a classic architecture, FPN can build a feature pyramid with high-level semantics throughout. However, intrinsic defects in feature extraction and fusion hinder FPN from further aggregating more discriminative features. Hence, we propose an Attention Aggregation Module (AAM) to enhance multi-scale feature learning through attention-guided feature aggregation. Based on FPN and AAM, a novel framework named Attention Aggregation Feature Pyramid Network (A2-FPN) is developed for semantic segmentation of fine-resolution remotely sensed images. Extensive experiments conducted on three datasets demonstrate the effectiveness of our A2 -FPN in segmentation accuracy. Code is available at https://github.com/lironui/A2-FPN.

arXiv:2102.05811

Audiovisual Highlight Detection in Videos

In this paper, we test the hypothesis that interesting events in unstructured videos are inherently audiovisual. We combine deep image representations for object recognition and scene understanding with representations from an audiovisual affect recognition model. To this set, we include content agnostic audio-visual synchrony representations and mel-frequency cepstral coefficients to capture other intrinsic properties of audio. These features are used in a modular supervised model. We present results from two experiments: efficacy study of single features on the task, and an ablation study where we leave one feature out at a time. For the video summarization task, our results indicate that the visual features carry most information, and including audiovisual features improves over visual-only information. To better study the task of highlight detection, we run a pilot experiment with highlights annotations for a small subset of video clips and fine-tune our best model on it. Results indicate that we can transfer knowledge from the video summarization task to a model trained specifically for the task of highlight detection.

arXiv:2102.03939공식 코드 · Papers with Code

Single-Shot Cuboids: Geodesics-based End-to-end Manhattan Aligned Layout Estimation from Spherical Panoramas

It has been shown that global scene understanding tasks like layout estimation can benefit from wider field of views, and specifically spherical panoramas. While much progress has been made recently, all previous approaches rely on intermediate representations and postprocessing to produce Manhattan-aligned estimates. In this work we show how to estimate full room layouts in a single-shot, eliminating the need for postprocessing. Our work is the first to directly infer Manhattan-aligned outputs. To achieve this, our data-driven model exploits direct coordinate regression and is supervised end-to-end. As a result, we can explicitly add quasi-Manhattan constraints, which set the necessary conditions for a homography-based Manhattan alignment module. Finally, we introduce the geodesic heatmaps and loss and a boundary-aware center of mass calculation that facilitate higher quality keypoint estimation in the spherical domain. Our models and code are publicly available at https://vcl3d.github.io/SingleShotCuboids/.

arXiv:2102.03099

Bidirectional Multi-scale Attention Networks for Semantic Segmentation of Oblique UAV Imagery

Semantic segmentation for aerial platforms has been one of the fundamental scene understanding task for the earth observation. Most of the semantic segmentation research focused on scenes captured in nadir view, in which objects have relatively smaller scale variation compared with scenes captured in oblique view. The huge scale variation of objects in oblique images limits the performance of deep neural networks (DNN) that process images in a single scale fashion. In order to tackle the scale variation issue, in this paper, we propose the novel bidirectional multi-scale attention networks, which fuse features from multiple scales bidirectionally for more adaptive and effective feature extraction. The experiments are conducted on the UAVid2020 dataset and have shown the effectiveness of our method. Our model achieved the state-of-the-art (SOTA) result with a mean intersection over union (mIoU) score of 70.80%.

arXiv:2102.00297공식 코드 · Papers with Code

Deep Learning--Based Scene Simplification for Bionic Vision

Retinal degenerative diseases cause profound visual impairment in more than 10 million people worldwide, and retinal prostheses are being developed to restore vision to these individuals. Analogous to cochlear implants, these devices electrically stimulate surviving retinal cells to evoke visual percepts (phosphenes). However, the quality of current prosthetic vision is still rudimentary. Rather than aiming to restore "natural" vision, there is potential merit in borrowing state-of-the-art computer vision algorithms as image processing techniques to maximize the usefulness of prosthetic vision. Here we combine deep learning--based scene simplification strategies with a psychophysically validated computational model of the retina to generate realistic predictions of simulated prosthetic vision, and measure their ability to support scene understanding of sighted subjects (virtual patients) in a variety of outdoor scenarios. We show that object segmentation may better support scene understanding than models based on visual saliency and monocular depth estimation. In addition, we highlight the importance of basing theoretical predictions on biologically realistic models of phosphene shape. Overall, this work has the potential to drastically improve the utility of prosthetic vision for people blinded from retinal degenerative diseases.

arXiv:2101.10837공식 코드 · Papers with Code

The Ikshana Hypothesis of Human Scene Understanding

In recent years, deep neural networks (DNNs) achieved state-of-the-art performance on several computer vision tasks. However, the one typical drawback of these DNNs is the requirement of massive labeled data. Even though few-shot learning methods address this problem, they often use techniques such as meta-learning and metric-learning on top of the existing methods. In this work, we address this problem from a neuroscience perspective by proposing a hypothesis named Ikshana, which is supported by several findings in neuroscience. Our hypothesis approximates the refining process of conceptual gist in the human brain while understanding a natural scene/image. While our hypothesis holds no particular novelty in neuroscience, it provides a novel perspective for designing DNNs for vision tasks. By following the Ikshana hypothesis, we design a novel neural-inspired CNN architecture named IkshanaNet. The empirical results demonstrate the effectiveness of our method by outperforming several baselines on the entire and subsets of the Cityscapes and the CamVid semantic segmentation benchmarks.

arXiv:2101.09641공식 코드 · Papers with Code

OpenGF: An Ultra-Large-Scale Ground Filtering Dataset Built Upon Open ALS Point Clouds Around the World

Ground filtering has remained a widely studied but incompletely resolved bottleneck for decades in the automatic generation of high-precision digital elevation model, due to the dramatic changes of topography and the complex structures of objects. The recent breakthrough of supervised deep learning algorithms in 3D scene understanding brings new solutions for better solving such problems. However, there are few large-scale and scene-rich public datasets dedicated to ground extraction, which considerably limits the development of effective deep-learning-based ground filtering methods. To this end, we present OpenGF, first Ultra-Large-Scale Ground Filtering dataset covering over 47 $km^2$ of 9 different typical terrain scenes built upon open ALS point clouds of 4 different countries around the world. OpenGF contains more than half a billion finely labeled ground and non-ground points, thousands of times the number of labeled points than the de facto standard ISPRS filtertest dataset. We extensively evaluate the performance of state-of-the-art rule-based algorithms and 3D semantic segmentation networks on our dataset and provide a comprehensive analysis. The results have confirmed the capability of OpenGF to train deep learning models effectively. This dataset is released at https://github.com/Nathan-UW/OpenGF to promote more advancing research for ground filtering and large-scale 3D geographic environment understanding.

arXiv:2101.08418

Rethinking Semantic Segmentation Evaluation for Explainability and Model Selection

Semantic segmentation aims to robustly predict coherent class labels for entire regions of an image. It is a scene understanding task that powers real-world applications (e.g., autonomous navigation). One important application, the use of imagery for automated semantic understanding of pedestrian environments, provides remote mapping of accessibility features in street environments. This application (and others like it) require detailed geometric information of geographical objects. Semantic segmentation is a prerequisite for this task since it maps contiguous regions of the same class as single entities. Importantly, semantic segmentation uses like ours are not pixel-wise outcomes; however, most of their quantitative evaluation metrics (e.g., mean Intersection Over Union) are based on pixel-wise similarities to a ground-truth, which fails to emphasize over- and under-segmentation properties of a segmentation model. Here, we introduce a new metric to assess region-based over- and under-segmentation. We analyze and compare it to other metrics, demonstrating that the use of our metric lends greater explainability to semantic segmentation model performance in real-world applications.