PyTorchKR Papers

최신 논문

총 9,712편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2210.12594

3D Reconstruction of unstained cells from a single defocused hologram

We investigate the problem of 3D complex field reconstruction corresponding to unstained red blood cells (RBCs) with a single defocused off-axis digital hologram. We employ recently introduced mean gradient descent (MGD) optimization framework, to solve the 3D recovery problem. While investigating volume recovery problem for a continuous phase object like RBC, we came across an interesting feature of the back-propagated field that it does not show clear focusing effect. Therefore the sparsity enforcement within the iterative optimization framework given the single hologram data cannot effectively restrict the true object volume. For phase objects, it is known that the amplitude contrast of the back-propagated object field at the focus plane is minimum and it increases at the defocus planes. We therefore use this information available in the detector field data to device weights as a function of inverse of amplitude contrast. This weight function is employed in the iterative steps of the optimization algorithm to assist the object volume localization. The experimental illustrations of 3D volume reconstruction of the healthy as well as the malaria infected RBCs are presented. The proposed methodology is simple to implement experimentally and provides an approximate tomographic solution which is axially restricted and is consistent with the object field data.

arXiv:2210.12347

Quantifying Complexity: An Object-Relations Approach to Complex Systems

The best way to model, understand, and quantify the information contained in complex systems is an open question in physics, mathematics, and computer science. The uncertain relationship between entropy and complexity further complicates this question. With ideas drawn from the object-relations theory of psychology, this paper develops an object-relations model of complex systems which generalizes to systems of all types, including mathematical operations, machines, biological organisms, and social structures. The resulting Complex Information Entropy (CIE) equation is a robust method to quantify complexity across various contexts. The paper also describes algorithms to iteratively update and improve approximate solutions to the CIE equation, to recursively infer the composition of complex systems, and to discover the connections among objects across different lengthscales and timescales. Applications are discussed in the fields of engineering design, atomic and molecular physics, chemistry, materials science, neuroscience, psychology, sociology, ecology, economics, and medicine.

arXiv:2210.12476

A Flexible-Frame-Rate Vision-Aided Inertial Object Tracking System for Mobile Devices

Real-time object pose estimation and tracking is challenging but essential for emerging augmented reality (AR) applications. In general, state-of-the-art methods address this problem using deep neural networks which indeed yield satisfactory results. Nevertheless, the high computational cost of these methods makes them unsuitable for mobile devices where real-world applications usually take place. In addition, head-mounted displays such as AR glasses require at least 90~FPS to avoid motion sickness, which further complicates the problem. We propose a flexible-frame-rate object pose estimation and tracking system for mobile devices. It is a monocular visual-inertial-based system with a client-server architecture. Inertial measurement unit (IMU) pose propagation is performed on the client side for high speed tracking, and RGB image-based 3D pose estimation is performed on the server side to obtain accurate poses, after which the pose is sent to the client side for visual-inertial fusion, where we propose a bias self-correction mechanism to reduce drift. We also propose a pose inspection algorithm to detect tracking failures and incorrect pose estimation. Connected by high-speed networking, our system supports flexible frame rates up to 120 FPS and guarantees high precision and real-time tracking on low-end devices. Both simulations and real world experiments show that our method achieves accurate and robust object tracking.

arXiv:2210.13053공식 코드 · Papers with Code

Foreground Guidance and Multi-Layer Feature Fusion for Unsupervised Object Discovery with Transformers

Unsupervised object discovery (UOD) has recently shown encouraging progress with the adoption of pre-trained Transformer features. However, current methods based on Transformers mainly focus on designing the localization head (e.g., seed selection-expansion and normalized cut) and overlook the importance of improving Transformer features. In this work, we handle UOD task from the perspective of feature enhancement and propose FOReground guidance and MUlti-LAyer feature fusion for unsupervised object discovery, dubbed FORMULA. Firstly, we present a foreground guidance strategy with an off-the-shelf UOD detector to highlight the foreground regions on the feature maps and then refine object locations in an iterative fashion. Moreover, to solve the scale variation issues in object detection, we design a multi-layer feature fusion module that aggregates features responding to objects at different scales. The experiments on VOC07, VOC12, and COCO 20k show that the proposed FORMULA achieves new state-of-the-art results on unsupervised object discovery. The code will be released at https://github.com/VDIGPKU/FORMULA.

arXiv:2210.12989공식 코드 · Papers with Code

Robust Object Detection in Remote Sensing Imagery with Noisy and Sparse Geo-Annotations (Full Version)

Recently, the availability of remote sensing imagery from aerial vehicles and satellites constantly improved. For an automated interpretation of such data, deep-learning-based object detectors achieve state-of-the-art performance. However, established object detectors require complete, precise, and correct bounding box annotations for training. In order to create the necessary training annotations for object detectors, imagery can be georeferenced and combined with data from other sources, such as points of interest localized by GPS sensors. Unfortunately, this combination often leads to poor object localization and missing annotations. Therefore, training object detectors with such data often results in insufficient detection performance. In this paper, we present a novel approach for training object detectors with extremely noisy and incomplete annotations. Our method is based on a teacher-student learning framework and a correction module accounting for imprecise and missing annotations. Thus, our method is easy to use and can be combined with arbitrary object detectors. We demonstrate that our approach improves standard detectors by 37.1\% $AP_{50}$ on a noisy real-world remote-sensing dataset. Furthermore, our method achieves great performance gains on two datasets with synthetic noise. Code is available at \url{https://github.com/mxbh/robust_object_detection}.

arXiv:2210.12918공식 코드 · Papers with Code

Unsupervised Object Representation Learning using Translation and Rotation Group Equivariant VAE

In many imaging modalities, objects of interest can occur in a variety of locations and poses (i.e. are subject to translations and rotations in 2d or 3d), but the location and pose of an object does not change its semantics (i.e. the object's essence). That is, the specific location and rotation of an airplane in satellite imagery, or the 3d rotation of a chair in a natural image, or the rotation of a particle in a cryo-electron micrograph, do not change the intrinsic nature of those objects. Here, we consider the problem of learning semantic representations of objects that are invariant to pose and location in a fully unsupervised manner. We address shortcomings in previous approaches to this problem by introducing TARGET-VAE, a translation and rotation group-equivariant variational autoencoder framework. TARGET-VAE combines three core innovations: 1) a rotation and translation group-equivariant encoder architecture, 2) a structurally disentangled distribution over latent rotation, translation, and a rotation-translation-invariant semantic object representation, which are jointly inferred by the approximate inference network, and 3) a spatially equivariant generator network. In comprehensive experiments, we show that TARGET-VAE learns disentangled representations without supervision that significantly improve upon, and avoid the pathologies of, previous methods. When trained on images highly corrupted by rotation and translation, the semantic representations learned by TARGET-VAE are similar to those learned on consistently posed objects, dramatically improving clustering in the semantic latent space. Furthermore, TARGET-VAE is able to perform remarkably accurate unsupervised pose and location inference. We expect methods like TARGET-VAE will underpin future approaches for unsupervised object generation, pose prediction, and object detection.

arXiv:2210.12878

IDD-3D: Indian Driving Dataset for 3D Unstructured Road Scenes

Autonomous driving and assistance systems rely on annotated data from traffic and road scenarios to model and learn the various object relations in complex real-world scenarios. Preparation and training of deploy-able deep learning architectures require the models to be suited to different traffic scenarios and adapt to different situations. Currently, existing datasets, while large-scale, lack such diversities and are geographically biased towards mainly developed cities. An unstructured and complex driving layout found in several developing countries such as India poses a challenge to these models due to the sheer degree of variations in the object types, densities, and locations. To facilitate better research toward accommodating such scenarios, we build a new dataset, IDD-3D, which consists of multi-modal data from multiple cameras and LiDAR sensors with 12k annotated driving LiDAR frames across various traffic scenarios. We discuss the need for this dataset through statistical comparisons with existing datasets and highlight benchmarks on standard 3D object detection and tracking tasks in complex layouts. Code and data available at https://github.com/shubham1810/idd3d_kit.git

arXiv:2210.12733

Self-supervised Amodal Video Object Segmentation

Amodal perception requires inferring the full shape of an object that is partially occluded. This task is particularly challenging on two levels: (1) it requires more information than what is contained in the instant retina or imaging sensor, (2) it is difficult to obtain enough well-annotated amodal labels for supervision. To this end, this paper develops a new framework of Self-supervised amodal Video object segmentation (SaVos). Our method efficiently leverages the visual information of video temporal sequences to infer the amodal mask of objects. The key intuition is that the occluded part of an object can be explained away if that part is visible in other frames, possibly deformed as long as the deformation can be reasonably learned. Accordingly, we derive a novel self-supervised learning paradigm that efficiently utilizes the visible object parts as the supervision to guide the training on videos. In addition to learning type prior to complete masks for known types, SaVos also learns the spatiotemporal prior, which is also useful for the amodal task and could generalize to unseen types. The proposed framework achieves the state-of-the-art performance on the synthetic amodal segmentation benchmark FISHBOWL and the real world benchmark KINS-Video-Car. Further, it lends itself well to being transferred to novel distributions using test-time adaptation, outperforming existing models even after the transfer to a new distribution.

arXiv:2210.13232

A Complete Recipe for Bayesian Knowledge Transfer: Object Tracking

The problem of sequentially transferring from a source object track and a model to another Bayesian filter has become ubiquitous. Due to the lack of a structural model that can capture the dependence among different models, the transfer may not be fully specified. In this paper, we introduce a novel Bayesian model that accounts for the model-jump from which the object can choose a model and follow. We aim to track the trajectory of the object while sequentially transferring from the source object to the target object. The main idea is to impute the dynamical model while tracking the object and estimating the state parameters of the moving object according to discretized dynamic systems. We demonstrate this procedure can handle the model mismatch as it sequentially corrects the predictive model. Particularly, for a fixed number of motion models, the object can learn what motion to follow at each time step. We employ a prior model for each model and then adaptively correct for changing one model to another to robustly estimate object trajectory under various motions. More concretely, we propose a robust Bayesian recipe to handle the model-jump and then integrate it with a Markov chain Monte Carlo (MCMC) approach to sample from the posterior distribution. We demonstrate through experiments the advantage of accounting for model-jump in our proposed method for knowledge transfer between learning tasks in Bayesian transfer learning.

arXiv:2210.12596

DMODE: Differential Monocular Object Distance Estimation Module without Class Specific Information

Utilizing a single camera for measuring object distances is a cost-effective alternative to stereo-vision and LiDAR. Although monocular distance estimation has been explored in the literature, most existing techniques rely on object class knowledge to achieve high performance. Without this contextual data, monocular distance estimation becomes more challenging, lacking reference points and object-specific cues. However, these cues can be misleading for objects with wide-range variation or adversarial situations, which is a challenging aspect of object-agnostic distance estimation. In this paper, we propose DMODE, a class-agnostic method for monocular distance estimation that does not require object class knowledge. DMODE estimates an object's distance by fusing its fluctuation in size over time with the camera's motion, making it adaptable to various object detectors and unknown objects, thus addressing these challenges. We evaluate our model on the KITTI MOTS dataset using ground-truth bounding box annotations and outputs from TrackRCNN and EagerMOT. The object's location is determined using the change in bounding box sizes and camera position without measuring the object's detection source or class attributes. Our approach demonstrates superior performance in multi-class object distance detection scenarios compared to conventional methods.

arXiv:2210.11718공식 코드 · Papers with Code

CRT-6D: Fast 6D Object Pose Estimation with Cascaded Refinement Transformers

Learning based 6D object pose estimation methods rely on computing large intermediate pose representations and/or iteratively refining an initial estimation with a slow render-compare pipeline. This paper introduces a novel method we call Cascaded Pose Refinement Transformers, or CRT-6D. We replace the commonly used dense intermediate representation with a sparse set of features sampled from the feature pyramid we call OSKFs(Object Surface Keypoint Features) where each element corresponds to an object keypoint. We employ lightweight deformable transformers and chain them together to iteratively refine proposed poses over the sampled OSKFs. We achieve inference runtimes 2x faster than the closest real-time state of the art methods while supporting up to 21 objects on a single model. We demonstrate the effectiveness of CRT-6D by performing extensive experiments on the LM-O and YCBV datasets. Compared to real-time methods, we achieve state of the art on LM-O and YCB-V, falling slightly behind methods with inference runtimes one order of magnitude higher. The source code is available at: https://github.com/PedroCastro/CRT-6D

arXiv:2210.12148

Unsupervised Multi-object Segmentation by Predicting Probable Motion Patterns

We propose a new approach to learn to segment multiple image objects without manual supervision. The method can extract objects form still images, but uses videos for supervision. While prior works have considered motion for segmentation, a key insight is that, while motion can be used to identify objects, not all objects are necessarily in motion: the absence of motion does not imply the absence of objects. Hence, our model learns to predict image regions that are likely to contain motion patterns characteristic of objects moving rigidly. It does not predict specific motion, which cannot be done unambiguously from a still image, but a distribution of possible motions, which includes the possibility that an object does not move at all. We demonstrate the advantage of this approach over its deterministic counterpart and show state-of-the-art unsupervised object segmentation performance on simulated and real-world benchmarks, surpassing methods that use motion even at test time. As our approach is applicable to variety of network architectures that segment the scenes, we also apply it to existing image reconstruction-based models showing drastic improvement. Project page and code: https://www.robots.ox.ac.uk/~vgg/research/ppmp .

arXiv:2210.12126

One-Shot Neural Fields for 3D Object Understanding

We present a unified and compact scene representation for robotics, where each object in the scene is depicted by a latent code capturing geometry and appearance. This representation can be decoded for various tasks such as novel view rendering, 3D reconstruction (e.g. recovering depth, point clouds, or voxel maps), collision checking, and stable grasp prediction. We build our representation from a single RGB input image at test time by leveraging recent advances in Neural Radiance Fields (NeRF) that learn category-level priors on large multiview datasets, then fine-tune on novel objects from one or few views. We expand the NeRF model for additional grasp outputs and explore ways to leverage this representation for robotics. At test-time, we build the representation from a single RGB input image observing the scene from only one viewpoint. We find that the recovered representation allows rendering from novel views, including of occluded object parts, and also for predicting successful stable grasps. Grasp poses can be directly decoded from our latent representation with an implicit grasp decoder. We experimented in both simulation and real world and demonstrated the capability for robust robotic grasping using such compact representation. Website: https://nerfgrasp.github.io

arXiv:2210.12080

Monitoring Constraints in Business Processes Using Object-Centric Constraint Graphs

Constraint monitoring aims to monitor the violation of constraints in business processes, e.g., an invoice should be cleared within 48 hours after the corresponding goods receipt, by analyzing event data. Existing techniques for constraint monitoring assume that a single case notion exists in a business process, e.g., a patient in a healthcare process, and each event is associated with the case notion. However, in reality, business processes are object-centric, i.e., multiple case notions (objects) exist, and an event may be associated with multiple objects. For instance, an Order-To-Cash (O2C) process involves order, item, delivery, etc., and they interact when executing an event, e.g., packing multiple items together for a delivery. The existing techniques produce misleading insights when applied to such object-centric business processes. In this work, we propose an approach to monitoring constraints in object-centric business processes. To this end, we introduce Object-Centric Constraint Graphs (OCCGs) to represent constraints that consider the interaction of objects. Next, we evaluate the constraints represented by OCCGs by analyzing Object-Centric Event Logs (OCELs) that store the interaction of different objects in events. We have implemented a web application to support the proposed approach and conducted two case studies using a real-life SAP ERP system.

arXiv:2210.11468

ObSynth: An Interactive Synthesis System for Generating Object Models from Natural Language Specifications

We introduce ObSynth, an interactive system leveraging the domain knowledge embedded in large language models (LLMs) to help users design object models from high level natural language prompts. This is an example of specification reification, the process of taking a high-level, potentially vague specification and reifying it into a more concrete form. We evaluate ObSynth via a user study, leading to three key findings: first, object models designed using ObSynth are more detailed, showing that it often synthesizes fields users might have otherwise omitted. Second, a majority of objects, methods, and fields generated by ObSynth are kept by the user in the final object model, highlighting the quality of generated components. Third, ObSynth altered the workflow of participants: they focus on checking that synthesized components were correct rather than generating them from scratch, though ObSynth did not reduce the time participants took to generate object models.

arXiv:2210.11463공식 코드 · Papers with Code

Breaking Bad: A Dataset for Geometric Fracture and Reassembly

We introduce Breaking Bad, a large-scale dataset of fractured objects. Our dataset consists of over one million fractured objects simulated from ten thousand base models. The fracture simulation is powered by a recent physically based algorithm that efficiently generates a variety of fracture modes of an object. Existing shape assembly datasets decompose objects according to semantically meaningful parts, effectively modeling the construction process. In contrast, Breaking Bad models the destruction process of how a geometric object naturally breaks into fragments. Our dataset serves as a benchmark that enables the study of fractured object reassembly and presents new challenges for geometric shape understanding. We analyze our dataset with several geometry measurements and benchmark three state-of-the-art shape assembly deep learning methods under various settings. Extensive experimental results demonstrate the difficulty of our dataset, calling on future research in model designs specifically for the geometric shape assembly task. We host our dataset at https://breaking-bad-dataset.github.io/.

arXiv:2210.11387

Transformer-based Action recognition in hand-object interacting scenarios

This report describes the 2nd place solution to the ECCV 2022 Human Body, Hands, and Activities (HBHA) from Egocentric and Multi-view Cameras Challenge: Action Recognition. This challenge aims to recognize hand-object interaction in an egocentric view. We propose a framework that estimates keypoints of two hands and an object with a Transformer-based keypoint estimator and recognizes actions based on the estimated keypoints. We achieved a top-1 accuracy of 87.19% on the testset.

arXiv:2210.11169공식 코드 · Papers with Code

Content-based Graph Privacy Advisor

People may be unaware of the privacy risks of uploading an image online. In this paper, we present Graph Privacy Advisor, an image privacy classifier that uses scene information and object cardinality as cues to predict whether an image is private. Graph Privacy Advisor simplifies a state-of-the-art graph model and improves its performance by refining the relevance of the information extracted from the image. We determine the most informative visual features to be used for the privacy classification task and reduce the complexity of the model by replacing high-dimensional image feature vectors with lower-dimensional, more effective features. We also address the problem of biased prior information by modelling object co-occurrences instead of the frequency of object occurrences in each class.

arXiv:2210.11233

Context-driven Visual Object Recognition based on Knowledge Graphs

Current deep learning methods for object recognition are purely data-driven and require a large number of training samples to achieve good results. Due to their sole dependence on image data, these methods tend to fail when confronted with new environments where even small deviations occur. Human perception, however, has proven to be significantly more robust to such distribution shifts. It is assumed that their ability to deal with unknown scenarios is based on extensive incorporation of contextual knowledge. Context can be based either on object co-occurrences in a scene or on memory of experience. In accordance with the human visual cortex which uses context to form different object representations for a seen image, we propose an approach that enhances deep learning methods by using external contextual knowledge encoded in a knowledge graph. Therefore, we extract different contextual views from a generic knowledge graph, transform the views into vector space and infuse it into a DNN. We conduct a series of experiments to investigate the impact of different contextual views on the learned object representations for the same image dataset. The experimental results provide evidence that the contextual views influence the image representations in the DNN differently and therefore lead to different predictions for the same images. We also show that context helps to strengthen the robustness of object recognition models for out-of-distribution images, usually occurring in transfer learning tasks or real-world scenarios.

arXiv:2210.10992

NIFT: Neural Interaction Field and Template for Object Manipulation

We introduce NIFT, Neural Interaction Field and Template, a descriptive and robust interaction representation of object manipulations to facilitate imitation learning. Given a few object manipulation demos, NIFT guides the generation of the interaction imitation for a new object instance by matching the Neural Interaction Template (NIT) extracted from the demos in the target Neural Interaction Field (NIF) defined for the new object. Specifically, the NIF is a neural field that encodes the relationship between each spatial point and a given object, where the relative position is defined by a spherical distance function rather than occupancies or signed distances, which are commonly adopted by conventional neural fields but less informative. For a given demo interaction, the corresponding NIT is defined by a set of spatial points sampled in the demo NIF with associated neural features. To better capture the interaction, the points are sampled on the Interaction Bisector Surface (IBS), which consists of points that are equidistant to the two interacting objects and has been used extensively for interaction representation. With both point selection and pointwise features defined for better interaction encoding, NIT effectively guides the feature matching in the NIFs of the new object instances such that the relative poses are optimized to realize the manipulation while imitating the demo interactions. Experiments show that our NIFT solution outperforms state-of-the-art imitation learning methods for object manipulation and generalizes better to objects from new categories.