PyTorchKR Papers

최신 논문

총 2,549편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2209.01435

A comprehensive survey on recent deep learning-based methods applied to surgical data

Minimally invasive surgery is highly operator dependant with a lengthy procedural time causing fatigue to surgeon and risks to patients such as injury to organs, infection, bleeding, and complications of anesthesia. To mitigate such risks, real-time systems are desired to be developed that can provide intra-operative guidance to surgeons. For example, an automated system for tool localization, tool (or tissue) tracking, and depth estimation can enable a clear understanding of surgical scenes preventing miscalculations during surgical procedures. In this work, we present a systematic review of recent machine learning-based approaches including surgical tool localization, segmentation, tracking, and 3D scene perception. Furthermore, we provide a detailed overview of publicly available benchmark datasets widely used for surgical navigation tasks. While recent deep learning architectures have shown promising results, there are still several open research problems such as a lack of annotated datasets, the presence of artifacts in surgical scenes, and non-textured surfaces that hinder 3D reconstruction of the anatomical structures. Based on our comprehensive review, we present a discussion on current gaps and needed steps to improve the adaptation of technology in surgery.

arXiv:2209.01194

CLONeR: Camera-Lidar Fusion for Occupancy Grid-aided Neural Representations

Recent advances in neural radiance fields (NeRFs) achieve state-of-the-art novel view synthesis and facilitate dense estimation of scene properties. However, NeRFs often fail for large, unbounded scenes that are captured under very sparse views with the scene content concentrated far away from the camera, as is typical for field robotics applications. In particular, NeRF-style algorithms perform poorly: (1) when there are insufficient views with little pose diversity, (2) when scenes contain saturation and shadows, and (3) when finely sampling large unbounded scenes with fine structures becomes computationally intensive. This paper proposes CLONeR, which significantly improves upon NeRF by allowing it to model large outdoor driving scenes that are observed from sparse input sensor views. This is achieved by decoupling occupancy and color learning within the NeRF framework into separate Multi-Layer Perceptrons (MLPs) trained using LiDAR and camera data, respectively. In addition, this paper proposes a novel method to build differentiable 3D Occupancy Grid Maps (OGM) alongside the NeRF model, and leverage this occupancy grid for improved sampling of points along a ray for volumetric rendering in metric space. Through extensive quantitative and qualitative experiments on scenes from the KITTI dataset, this paper demonstrates that the proposed method outperforms state-of-the-art NeRF models on both novel view synthesis and dense depth prediction tasks when trained on sparse input data.

arXiv:2209.00961공식 코드 · Papers with Code

LiteDepth: Digging into Fast and Accurate Depth Estimation on Mobile Devices

Monocular depth estimation is an essential task in the computer vision community. While tremendous successful methods have obtained excellent results, most of them are computationally expensive and not applicable for real-time on-device inference. In this paper, we aim to address more practical applications of monocular depth estimation, where the solution should consider not only the precision but also the inference time on mobile devices. To this end, we first develop an end-to-end learning-based model with a tiny weight size (1.4MB) and a short inference time (27FPS on Raspberry Pi 4). Then, we propose a simple yet effective data augmentation strategy, called R2 crop, to boost the model performance. Moreover, we observe that the simple lightweight model trained with only one single loss term will suffer from performance bottleneck. To alleviate this issue, we adopt multiple loss terms to provide sufficient constraints during the training stage. Furthermore, with a simple dynamic re-weight strategy, we can avoid the time-consuming hyper-parameter choice of loss terms. Finally, we adopt the structure-aware distillation to further improve the model performance. Notably, our solution named LiteDepth ranks 2nd in the MAI&AIM2022 Monocular Depth Estimation Challenge}, with a si-RMSE of 0.311, an RMSE of 3.79, and the inference time is 37$ms$ tested on the Raspberry Pi 4. Notably, we provide the fastest solution to the challenge. Codes and models will be released at \url{https://github.com/zhyever/LiteDepth}.

arXiv:2209.00082

Multi-View Reconstruction using Signed Ray Distance Functions (SRDF)

In this paper, we investigate a new optimization framework for multi-view 3D shape reconstructions. Recent differentiable rendering approaches have provided breakthrough performances with implicit shape representations though they can still lack precision in the estimated geometries. On the other hand multi-view stereo methods can yield pixel wise geometric accuracy with local depth predictions along viewing rays. Our approach bridges the gap between the two strategies with a novel volumetric shape representation that is implicit but parameterized with pixel depths to better materialize the shape surface with consistent signed distances along viewing rays. The approach retains pixel-accuracy while benefiting from volumetric integration in the optimization. To this aim, depths are optimized by evaluating, at each 3D location within the volumetric discretization, the agreement between the depth prediction consistency and the photometric consistency for the corresponding pixels. The optimization is agnostic to the associated photo-consistency term which can vary from a median-based baseline to more elaborate criteria learned functions. Our experiments demonstrate the benefit of the volumetric integration with depth predictions. They also show that our approach outperforms existing approaches over standard 3D benchmarks with better geometry estimations.

arXiv:2208.14743

SimpleRecon: 3D Reconstruction Without 3D Convolutions

Traditionally, 3D indoor scene reconstruction from posed images happens in two phases: per-image depth estimation, followed by depth merging and surface reconstruction. Recently, a family of methods have emerged that perform reconstruction directly in final 3D volumetric feature space. While these methods have shown impressive reconstruction results, they rely on expensive 3D convolutional layers, limiting their application in resource-constrained environments. In this work, we instead go back to the traditional route, and show how focusing on high quality multi-view depth prediction leads to highly accurate 3D reconstructions using simple off-the-shelf depth fusion. We propose a simple state-of-the-art multi-view depth estimator with two main contributions: 1) a carefully-designed 2D CNN which utilizes strong image priors alongside a plane-sweep feature volume and geometric losses, combined with 2) the integration of keyframe and geometric metadata into the cost volume which allows informed depth plane scoring. Our method achieves a significant lead over the current state-of-the-art for depth estimation and close or better for 3D reconstruction on ScanNet and 7-Scenes, yet still allows for online real-time low-memory reconstruction. Code, models and results are available at https://nianticlabs.github.io/simplerecon

arXiv:2208.14167공식 코드 · Papers with Code

Synthehicle: Multi-Vehicle Multi-Camera Tracking in Virtual Cities

Smart City applications such as intelligent traffic routing or accident prevention rely on computer vision methods for exact vehicle localization and tracking. Due to the scarcity of accurately labeled data, detecting and tracking vehicles in 3D from multiple cameras proves challenging to explore. We present a massive synthetic dataset for multiple vehicle tracking and segmentation in multiple overlapping and non-overlapping camera views. Unlike existing datasets, which only provide tracking ground truth for 2D bounding boxes, our dataset additionally contains perfect labels for 3D bounding boxes in camera- and world coordinates, depth estimation, and instance, semantic and panoptic segmentation. The dataset consists of 17 hours of labeled video material, recorded from 340 cameras in 64 diverse day, rain, dawn, and night scenes, making it the most extensive dataset for multi-target multi-camera tracking so far. We provide baselines for detection, vehicle re-identification, and single- and multi-camera tracking. Code and data are publicly available.

arXiv:2208.13714

SphereDepth: Panorama Depth Estimation from Spherical Domain

The panorama image can simultaneously demonstrate complete information of the surrounding environment and has many advantages in virtual tourism, games, robotics, etc. However, the progress of panorama depth estimation cannot completely solve the problems of distortion and discontinuity caused by the commonly used projection methods. This paper proposes SphereDepth, a novel panorama depth estimation method that predicts the depth directly on the spherical mesh without projection preprocessing. The core idea is to establish the relationship between the panorama image and the spherical mesh and then use a deep neural network to extract features on the spherical domain to predict depth. To address the efficiency challenges brought by the high-resolution panorama data, we introduce two hyper-parameters for the proposed spherical mesh processing framework to balance the inference speed and accuracy. Validated on three public panorama datasets, SphereDepth achieves comparable results with the state-of-the-art methods of panorama depth estimation. Benefiting from the spherical domain setting, SphereDepth can generate a high-quality point cloud and significantly alleviate the issues of distortion and discontinuity.

arXiv:2208.13485공식 코드 · Papers with Code

A Practical Calibration Method for RGB Micro-Grid Polarimetric Cameras

Polarimetric imaging has been applied in a growing number of applications in robotic vision (ex. underwater navigation, glare removal, de-hazing, object classification, and depth estimation). One can find on the market RGB Polarization cameras that can capture both color and polarimetric state of the light in a single snapshot. Due to the sensor's characteristic dispersion, and the use of lenses, it is crucial to calibrate these types of cameras so as to obtain correct polarization measurements. The calibration methods that have been developed so far are either not adapted to this type of cameras, or they require complex equipment and time consuming experiments in strict setups. In this paper, we propose a new method to overcome the need for complex optical systems to efficiently calibrate these cameras. We show that the proposed calibration method has several advantages such as that any user can easily calibrate the camera using a uniform, linearly polarized light source without any a priori knowledge of its polarization state, and with a limited number of acquisitions. We will make our calibration code publicly available.

arXiv:2208.13241공식 코드 · Papers with Code

Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular Image

Despite significant progress made in the past few years, challenges remain for depth estimation using a single monocular image. First, it is nontrivial to train a metric-depth prediction model that can generalize well to diverse scenes mainly due to limited training data. Thus, researchers have built large-scale relative depth datasets that are much easier to collect. However, existing relative depth estimation models often fail to recover accurate 3D scene shapes due to the unknown depth shift caused by training with the relative depth data. We tackle this problem here and attempt to estimate accurate scene shapes by training on large-scale relative depth data, and estimating the depth shift. To do so, we propose a two-stage framework that first predicts depth up to an unknown scale and shift from a single monocular image, and then exploits 3D point cloud data to predict the depth shift and the camera's focal length that allow us to recover 3D scene shapes. As the two modules are trained separately, we do not need strictly paired training data. In addition, we propose an image-level normalized regression loss and a normal-based geometry loss to improve training with relative depth annotation. We test our depth model on nine unseen datasets and achieve state-of-the-art performance on zero-shot evaluation. Code is available at: https://git.io/Depth

arXiv:2208.12903

Neural Camera Models

Modern computer vision has moved beyond the domain of internet photo collections and into the physical world, guiding camera-equipped robots and autonomous cars through unstructured environments. To enable these embodied agents to interact with real-world objects, cameras are increasingly being used as depth sensors, reconstructing the environment for a variety of downstream reasoning tasks. Machine-learning-aided depth perception, or depth estimation, predicts for each pixel in an image the distance to the imaged scene point. While impressive strides have been made in depth estimation, significant challenges remain: (1) ground truth depth labels are difficult and expensive to collect at scale, (2) camera information is typically assumed to be known, but is often unreliable and (3) restrictive camera assumptions are common, even though a great variety of camera types and lenses are used in practice. In this thesis, we focus on relaxing these assumptions, and describe contributions toward the ultimate goal of turning cameras into truly generic depth sensors.

arXiv:2208.13441

Rethinking Skip Connections in Encoder-decoder Networks for Monocular Depth Estimation

Skip connections are fundamental units in encoder-decoder networks, which are able to improve the feature propagtion of the neural networks. However, most methods with skip connections just connected features with the same resolution in the encoder and the decoder, which ignored the information loss in the encoder with the layers going deeper. To leverage the information loss of the features in shallower layers of the encoder, we propose a full skip connection network (FSCN) for monocular depth estimation task. In addition, to fuse features within skip connections more closely, we present an adaptive concatenation module (ACM). Further more, we conduct extensive experiments on the ourdoor and indoor datasets (i.e., the KITTI dataste and the NYU Depth V2 dataset) for FSCN and FSCN gets the state-of-the-art results.

arXiv:2208.12653

Uncertainty Guided Depth Fusion for Spike Camera

Depth estimation is essential for various important real-world applications such as autonomous driving. However, it suffers from severe performance degradation in high-velocity scenario since traditional cameras can only capture blurred images. To deal with this problem, the spike camera is designed to capture the pixel-wise luminance intensity at high frame rate. However, depth estimation with spike camera remains very challenging using traditional monocular or stereo depth estimation algorithms, which are based on the photometric consistency. In this paper, we propose a novel Uncertainty-Guided Depth Fusion (UGDF) framework to fuse the predictions of monocular and stereo depth estimation networks for spike camera. Our framework is motivated by the fact that stereo spike depth estimation achieves better results at close range while monocular spike depth estimation obtains better results at long range. Therefore, we introduce a dual-task depth estimation architecture with a joint training strategy and estimate the distributed uncertainty to fuse the monocular and stereo results. In order to demonstrate the advantage of spike depth estimation over traditional camera depth estimation, we contribute a spike-depth dataset named CitySpike20K, which contains 20K paired samples, for spike depth estimation. UGDF achieves state-of-the-art results on CitySpike20K, surpassing all monocular or stereo spike depth estimation baselines. We conduct extensive experiments to evaluate the effectiveness and generalization of our method on CitySpike20K. To the best of our knowledge, our framework is the first dual-task fusion framework for spike camera depth estimation. Code and dataset will be released.

arXiv:2208.12527공식 코드 · Papers with Code

Unsupervised Spike Depth Estimation via Cross-modality Cross-domain Knowledge Transfer

Neuromorphic spike data, an upcoming modality with high temporal resolution, has shown promising potential in autonomous driving by mitigating the challenges posed by high-velocity motion blur. However, training the spike depth estimation network holds significant challenges in two aspects: sparse spatial information for pixel-wise tasks and difficulties in achieving paired depth labels for temporally intensive spike streams. Therefore, we introduce open-source RGB data to support spike depth estimation, leveraging its annotations and spatial information. The inherent differences in modalities and data distribution make it challenging to directly apply transfer learning from open-source RGB to target spike data. To this end, we propose a cross-modality cross-domain (BiCross) framework to realize unsupervised spike depth estimation by introducing simulated mediate source spike data. Specifically, we design a Coarse-to-Fine Knowledge Distillation (CFKD) approach to facilitate comprehensive cross-modality knowledge transfer while preserving the unique strengths of both modalities, utilizing a spike-oriented uncertainty scheme. Then, we propose a Self-Correcting Teacher-Student (SCTS) mechanism to screen out reliable pixel-wise pseudo labels and ease the domain shift of the student model, which avoids error accumulation in target spike data. To verify the effectiveness of BiCross, we conduct extensive experiments on four scenarios, including Synthetic to Real, Extreme Weather, Scene Changing, and Real Spike. Our method achieves state-of-the-art (SOTA) performances, compared with RGB-oriented unsupervised depth estimation methods. Code and dataset: https://github.com/Theia-4869/BiCross

arXiv:2208.12464

Dense Depth Distillation with Out-of-Distribution Simulated Images

We study data-free knowledge distillation (KD) for monocular depth estimation (MDE), which learns a lightweight model for real-world depth perception tasks by compressing it from a trained teacher model while lacking training data in the target domain. Owing to the essential difference between image classification and dense regression, previous methods of data-free KD are not applicable to MDE. To strengthen its applicability in real-world tasks, in this paper, we propose to apply KD with out-of-distribution simulated images. The major challenges to be resolved are i) lacking prior information about scene configurations of real-world training data and ii) domain shift between simulated and real-world images. To cope with these difficulties, we propose a tailored framework for depth distillation. The framework generates new training samples for embracing a multitude of possible object arrangements in the target domain and utilizes a transformation network to efficiently adapt them to the feature statistics preserved in the teacher model. Through extensive experiments on various depth estimation models and two different datasets, we show that our method outperforms the baseline KD by a good margin and even achieves slightly better performance with as few as 1/6 of training images, demonstrating a clear superiority.

arXiv:2208.11993

A Compacted Structure for Cross-domain learning on Monocular Depth and Flow Estimation

Accurate motion and depth recovery is important for many robot vision tasks including autonomous driving. Most previous studies have achieved cooperative multi-task interaction via either pre-defined loss functions or cross-domain prediction. This paper presents a multi-task scheme that achieves mutual assistance by means of our Flow to Depth (F2D), Depth to Flow (D2F), and Exponential Moving Average (EMA). F2D and D2F mechanisms enable multi-scale information integration between optical flow and depth domain based on differentiable shallow nets. A dual-head mechanism is used to predict optical flow for rigid and non-rigid motion based on a divide-and-conquer manner, which significantly improves the optical flow estimation performance. Furthermore, to make the prediction more robust and stable, EMA is used for our multi-task training. Experimental results on KITTI datasets show that our multi-task scheme outperforms other multi-task schemes and provide marked improvements on the prediction results.

arXiv:2208.11074

DepthFake: a depth-based strategy for detecting Deepfake videos

Fake content has grown at an incredible rate over the past few years. The spread of social media and online platforms makes their dissemination on a large scale increasingly accessible by malicious actors. In parallel, due to the growing diffusion of fake image generation methods, many Deep Learning-based detection techniques have been proposed. Most of those methods rely on extracting salient features from RGB images to detect through a binary classifier if the image is fake or real. In this paper, we proposed DepthFake, a study on how to improve classical RGB-based approaches with depth-maps. The depth information is extracted from RGB images with recent monocular depth estimation techniques. Here, we demonstrate the effective contribution of depth-maps to the deepfake detection task on robust pre-trained architectures. The proposed RGBD approach is in fact able to achieve an average improvement of 3.20% and up to 11.7% for some deepfake attacks with respect to standard RGB architectures over the FaceForensic++ dataset.

arXiv:2208.10771공식 코드 · Papers with Code

Learning an Efficient Multimodal Depth Completion Model

With the wide application of sparse ToF sensors in mobile devices, RGB image-guided sparse depth completion has attracted extensive attention recently, but still faces some problems. First, the fusion of multimodal information requires more network modules to process different modalities. But the application scenarios of sparse ToF measurements usually demand lightweight structure and low computational cost. Second, fusing sparse and noisy depth data with dense pixel-wise RGB data may introduce artifacts. In this paper, a light but efficient depth completion network is proposed, which consists of a two-branch global and local depth prediction module and a funnel convolutional spatial propagation network. The two-branch structure extracts and fuses cross-modal features with lightweight backbones. The improved spatial propagation module can refine the completed depth map gradually. Furthermore, corrected gradient loss is presented for the depth completion problem. Experimental results demonstrate the proposed method can outperform some state-of-the-art methods with a lightweight architecture. The proposed method also wins the championship in the MIPI2022 RGB+TOF depth completion challenge.

arXiv:2208.10762공식 코드 · Papers with Code

Depth Map Decomposition for Monocular Depth Estimation

We propose a novel algorithm for monocular depth estimation that decomposes a metric depth map into a normalized depth map and scale features. The proposed network is composed of a shared encoder and three decoders, called G-Net, N-Net, and M-Net, which estimate gradient maps, a normalized depth map, and a metric depth map, respectively. M-Net learns to estimate metric depths more accurately using relative depth features extracted by G-Net and N-Net. The proposed algorithm has the advantage that it can use datasets without metric depth labels to improve the performance of metric depth estimation. Experimental results on various datasets demonstrate that the proposed algorithm not only provides competitive performance to state-of-the-art algorithms but also yields acceptable results even when only a small amount of metric depth data is available for its training.

arXiv:2208.10500

Towards an AI-based Early Warning System for Bridge Scour

Scour is the number one cause of bridge failure in many parts of the world. Considering the lack of reliability in existing empirical equations for scour depth estimation and the complexity and uncertainty of scour as a physical phenomenon, it is essential to develop more reliable solutions for scour risk assessment. This study introduces a novel AI approach for early forecast of scour based on real-time monitoring data obtained from sonar and stage sensors installed at bridge piers. Long-short Term Memory networks (LSTMs), a prominent Deep Learning algorithm successfully used for time-series forecasting in other fields, were developed and trained using river stage and bed elevation readings for more than 11 years obtained from Alaska scour monitoring program. The capability of the AI models in scour prediction is shown for three case-study bridges. Results show that LSTMs can capture the temporal and seasonal patterns of both flow and river bed variations around bridge piers, through cycles of scour and filling and can provide reasonable predictions of upcoming scour depth as early as seven days in advance. It is expected that the proposed solution can be implemented by transportation authorities for development of emerging AI-based early warning systems, enabling superior bridge scour management.

arXiv:2208.10390

Minimizing the Effect of Noise and Limited Dataset Size in Image Classification Using Depth Estimation as an Auxiliary Task with Deep Multitask Learning

Generalizability is the ultimate goal of Machine Learning (ML) image classifiers, for which noise and limited dataset size are among the major concerns. We tackle these challenges through utilizing the framework of deep Multitask Learning (dMTL) and incorporating image depth estimation as an auxiliary task. On a customized and depth-augmented derivation of the MNIST dataset, we show a) multitask loss functions are the most effective approach of implementing dMTL, b) limited dataset size primarily contributes to classification inaccuracy, and c) depth estimation is mostly impacted by noise. In order to further validate the results, we manually labeled the NYU Depth V2 dataset for scene classification tasks. As a contribution to the field, we have made the data in python native format publicly available as an open-source dataset and provided the scene labels. Our experiments on MNIST and NYU-Depth-V2 show dMTL improves generalizability of the classifiers when the dataset is noisy and the number of examples is limited.