PyTorchKR Papers

최신 논문

총 2,547편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2204.03440공식 코드 · Papers with Code

Task-Aware Active Learning for Endoscopic Image Analysis

Semantic segmentation of polyps and depth estimation are two important research problems in endoscopic image analysis. One of the main obstacles to conduct research on these research problems is lack of annotated data. Endoscopic annotations necessitate the specialist knowledge of expert endoscopists and due to this, it can be difficult to organise, expensive and time consuming. To address this problem, we investigate an active learning paradigm to reduce the number of training examples by selecting the most discriminative and diverse unlabelled examples for the task taken into consideration. Most of the existing active learning pipelines are task-agnostic in nature and are often sub-optimal to the end task. In this paper, we propose a novel task-aware active learning pipeline and applied for two important tasks in endoscopic image analysis: semantic segmentation and depth estimation. We compared our method with the competitive baselines. From the experimental results, we observe a substantial improvement over the compared baselines. Codes are available at https://github.com/thetna/endo-active-learn.

arXiv:2204.02386

Pyramid Frequency Network with Spatial Attention Residual Refinement Module for Monocular Depth Estimation

Deep-learning-based approaches to depth estimation are rapidly advancing, offering superior performance over existing methods. To estimate the depth in real-world scenarios, depth estimation models require the robustness of various noise environments. In this work, a Pyramid Frequency Network(PFN) with Spatial Attention Residual Refinement Module(SARRM) is proposed to deal with the weak robustness of existing deep-learning methods. To reconstruct depth maps with accurate details, the SARRM constructs a residual fusion method with an attention mechanism to refine the blur depth. The frequency division strategy is designed, and the frequency pyramid network is developed to extract features from multiple frequency bands. With the frequency strategy, PFN achieves better visual accuracy than state-of-the-art methods in both indoor and outdoor scenes on Make3D, KITTI depth, and NYUv2 datasets. Additional experiments on the noisy NYUv2 dataset demonstrate that PFN is more reliable than existing deep-learning methods in high-noise scenes.

arXiv:2204.02091공식 코드 · Papers with Code

P3Depth: Monocular Depth Estimation with a Piecewise Planarity Prior

Monocular depth estimation is vital for scene understanding and downstream tasks. We focus on the supervised setup, in which ground-truth depth is available only at training time. Based on knowledge about the high regularity of real 3D scenes, we propose a method that learns to selectively leverage information from coplanar pixels to improve the predicted depth. In particular, we introduce a piecewise planarity prior which states that for each pixel, there is a seed pixel which shares the same planar 3D surface with the former. Motivated by this prior, we design a network with two heads. The first head outputs pixel-level plane coefficients, while the second one outputs a dense offset vector field that identifies the positions of seed pixels. The plane coefficients of seed pixels are then used to predict depth at each position. The resulting prediction is adaptively fused with the initial prediction from the first head via a learned confidence to account for potential deviations from precise local planarity. The entire architecture is trained end-to-end thanks to the differentiability of the proposed modules and it learns to predict regular depth maps, with sharp edges at occlusion boundaries. An extensive evaluation of our method shows that we set the new state of the art in supervised monocular depth estimation, surpassing prior methods on NYU Depth-v2 and on the Garg split of KITTI. Our method delivers depth maps that yield plausible 3D reconstructions of the input scenes. Code is available at: https://github.com/SysCV/P3Depth

arXiv:2204.01693

Monitoring social distancing with single image depth estimation

The recent pandemic emergency raised many challenges regarding the countermeasures aimed at containing the virus spread, and constraining the minimum distance between people resulted in one of the most effective strategies. Thus, the implementation of autonomous systems capable of monitoring the so-called social distance gained much interest. In this paper, we aim to address this task leveraging a single RGB frame without additional depth sensors. In contrast to existing single-image alternatives failing when ground localization is not available, we rely on single image depth estimation to perceive the 3D structure of the observed scene and estimate the distance between people. During the setup phase, a straightforward calibration procedure, leveraging a scale-aware SLAM algorithm available even on consumer smartphones, allows us to address the scale ambiguity affecting single image depth estimation. We validate our approach through indoor and outdoor images employing a calibrated LiDAR + RGB camera asset. Experimental results highlight that our proposal enables sufficiently reliable estimation of the inter-personal distance to monitor social distancing effectively. This fact confirms that despite its intrinsic ambiguity, if appropriately driven single image depth estimation can be a viable alternative to other depth perception techniques, more expensive and not always feasible in practical applications. Our evaluation also highlights that our framework can run reasonably fast and comparably to competitors, even on pure CPU systems. Moreover, its practical deployment on low-power systems is around the corner.

arXiv:2204.01678공식 코드 · Papers with Code

MultiMAE: Multi-modal Multi-task Masked Autoencoders

We propose a pre-training strategy called Multi-modal Multi-task Masked Autoencoders (MultiMAE). It differs from standard Masked Autoencoding in two key aspects: I) it can optionally accept additional modalities of information in the input besides the RGB image (hence "multi-modal"), and II) its training objective accordingly includes predicting multiple outputs besides the RGB image (hence "multi-task"). We make use of masking (across image patches and input modalities) to make training MultiMAE tractable as well as to ensure cross-modality predictive coding is indeed learned by the network. We show this pre-training strategy leads to a flexible, simple, and efficient framework with improved transfer results to downstream tasks. In particular, the same exact pre-trained network can be flexibly used when additional information besides RGB images is available or when no information other than RGB is available - in all configurations yielding competitive to or significantly better results than the baselines. To avoid needing training datasets with multiple modalities and tasks, we train MultiMAE entirely using pseudo labeling, which makes the framework widely applicable to any RGB dataset. The experiments are performed on multiple transfer tasks (image classification, semantic segmentation, depth estimation) and datasets (ImageNet, ADE20K, Taskonomy, Hypersim, NYUv2). The results show an intriguingly impressive capability by the model in cross-modal/task predictive coding and transfer.

arXiv:2204.01268

Improving Monocular Visual Odometry Using Learned Depth

Monocular visual odometry (VO) is an important task in robotics and computer vision. Thus far, how to build accurate and robust monocular VO systems that can work well in diverse scenarios remains largely unsolved. In this paper, we propose a framework to exploit monocular depth estimation for improving VO. The core of our framework is a monocular depth estimation module with a strong generalization capability for diverse scenes. It consists of two separate working modes to assist the localization and mapping. With a single monocular image input, the depth estimation module predicts a relative depth to help the localization module on improving the accuracy. With a sparse depth map and an RGB image input, the depth estimation module can generate accurate scale-consistent depth for dense mapping. Compared with current learning-based VO methods, our method demonstrates a stronger generalization ability to diverse scenes. More significantly, our framework is able to boost the performances of existing geometry-based VO methods by a large margin.

arXiv:2204.01027

Distortion-Aware Self-Supervised 360° Depth Estimation from A Single Equirectangular Projection Image

360{\deg} images are widely available over the last few years. This paper proposes a new technique for single 360{\deg} image depth prediction under open environments. Depth prediction from a 360{\deg} single image is not easy for two reasons. One is the limitation of supervision datasets - the currently available dataset is limited to indoor scenes. The other is the problems caused by Equirectangular Projection Format (ERP), commonly used for 360{\deg} images, that are coordinate and distortion. There is only one method existing that uses cube map projection to produce six perspective images and apply self-supervised learning using motion pictures for perspective depth prediction to deal with these problems. Different from the existing method, we directly use the ERP format. We propose a framework of direct use of ERP with coordinate conversion of correspondences and distortion-aware upsampling module to deal with the ERP related problems and extend a self-supervised learning method for open environments. For the experiments, we firstly built a dataset for the evaluation, and quantitatively evaluate the depth prediction in outdoor scenes. We show that it outperforms the state-of-the-art technique

arXiv:2204.00987공식 코드 · Papers with Code

BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimation

Monocular depth estimation is a fundamental task in computer vision and has drawn increasing attention. Recently, some methods reformulate it as a classification-regression task to boost the model performance, where continuous depth is estimated via a linear combination of predicted probability distributions and discrete bins. In this paper, we present a novel framework called BinsFormer, tailored for the classification-regression-based depth estimation. It mainly focuses on two crucial components in the specific task: 1) proper generation of adaptive bins and 2) sufficient interaction between probability distribution and bins predictions. To specify, we employ the Transformer decoder to generate bins, novelly viewing it as a direct set-to-set prediction problem. We further integrate a multi-scale decoder structure to achieve a comprehensive understanding of spatial geometry information and estimate depth maps in a coarse-to-fine manner. Moreover, an extra scene understanding query is proposed to improve the estimation accuracy, which turns out that models can implicitly learn useful information from an auxiliary environment classification task. Extensive experiments on the KITTI, NYU, and SUN RGB-D datasets demonstrate that BinsFormer surpasses state-of-the-art monocular depth estimation methods with prominent margins. Code and pretrained models will be made publicly available at \url{https://github.com/zhyever/Monocular-Depth-Estimation-Toolbox}.

arXiv:2203.16542

Towards Multimodal Depth Estimation from Light Fields

Light field applications, especially light field rendering and depth estimation, developed rapidly in recent years. While state-of-the-art light field rendering methods handle semi-transparent and reflective objects well, depth estimation methods either ignore these cases altogether or only deliver a weak performance. We argue that this is due current methods only considering a single "true" depth, even when multiple objects at different depths contributed to the color of a single pixel. Based on the simple idea of outputting a posterior depth distribution instead of only a single estimate, we develop and explore several different deep-learning-based approaches to the problem. Additionally, we contribute the first "multimodal light field depth dataset" that contains the depths of all objects which contribute to the color of a pixel. This allows us to supervise the multimodal depth prediction and also validate all methods by measuring the KL divergence of the predicted posteriors. With our thorough analysis and novel dataset, we aim to start a new line of depth estimation research that overcomes some of the long-standing limitations of this field.

arXiv:2203.16756

Casual 6-DoF: free-viewpoint panorama using a handheld 360 camera

Six degrees-of-freedom (6-DoF) video provides telepresence by enabling users to move around in the captured scene with a wide field of regard. Compared to methods requiring sophisticated camera setups, the image-based rendering method based on photogrammetry can work with images captured with any poses, which is more suitable for casual users. However, existing image-based rendering methods are based on perspective images. When used to reconstruct 6-DoF views, it often requires capturing hundreds of images, making data capture a tedious and time-consuming process. In contrast to traditional perspective images, 360{\deg} images capture the entire surrounding view in a single shot, thus, providing a faster capturing process for 6-DoF view reconstruction. This paper presents a novel method to provide 6-DoF experiences over a wide area using an unstructured collection of 360{\deg} panoramas captured by a conventional 360{\deg} camera. Our method consists of 360{\deg} data capturing, novel depth estimation to produce a high-quality spherical depth panorama, and high-fidelity free-viewpoint generation. We compared our method against state-of-the-art methods, using data captured in various environments. Our method shows better visual quality and robustness in the tested scenes.

arXiv:2203.15089

Learning Optical Flow, Depth, and Scene Flow without Real-World Labels

Self-supervised monocular depth estimation enables robots to learn 3D perception from raw video streams. This scalable approach leverages projective geometry and ego-motion to learn via view synthesis, assuming the world is mostly static. Dynamic scenes, which are common in autonomous driving and human-robot interaction, violate this assumption. Therefore, they require modeling dynamic objects explicitly, for instance via estimating pixel-wise 3D motion, i.e. scene flow. However, the simultaneous self-supervised learning of depth and scene flow is ill-posed, as there are infinitely many combinations that result in the same 3D point. In this paper we propose DRAFT, a new method capable of jointly learning depth, optical flow, and scene flow by combining synthetic data with geometric self-supervision. Building upon the RAFT architecture, we learn optical flow as an intermediate task to bootstrap depth and scene flow learning via triangulation. Our algorithm also leverages temporal and geometric consistency losses across tasks to improve multi-task learning. Our DRAFT architecture simultaneously establishes a new state of the art in all three tasks in the self-supervised monocular setting on the standard KITTI benchmark. Project page: https://sites.google.com/tri.global/draft.

arXiv:2203.15485

Learning Structured Gaussians to Approximate Deep Ensembles

This paper proposes using a sparse-structured multivariate Gaussian to provide a closed-form approximator for the output of probabilistic ensemble models used for dense image prediction tasks. This is achieved through a convolutional neural network that predicts the mean and covariance of the distribution, where the inverse covariance is parameterised by a sparsely structured Cholesky matrix. Similarly to distillation approaches, our single network is trained to maximise the probability of samples from pre-trained probabilistic models, in this work we use a fixed ensemble of networks. Once trained, our compact representation can be used to efficiently draw spatially correlated samples from the approximated output distribution. Importantly, this approach captures the uncertainty and structured correlations in the predictions explicitly in a formal distribution, rather than implicitly through sampling alone. This allows direct introspection of the model, enabling visualisation of the learned structure. Moreover, this formulation provides two further benefits: estimation of a sample probability, and the introduction of arbitrary spatial conditioning at test time. We demonstrate the merits of our approach on monocular depth estimation and show that the advantages of our approach are obtained with comparable quantitative performance.

arXiv:2203.15201공식 코드 · Papers with Code

Light Field Depth Estimation via Stitched Epipolar Plane Images

Depth estimation is a fundamental problem in light field processing. Epipolar-plane image (EPI)-based methods often encounter challenges such as low accuracy in slope computation due to discretization errors and limited angular resolution. Besides, existing methods perform well in most regions but struggle to produce sharp edges in occluded regions and resolve ambiguities in texture-less regions. To address these issues, we propose the concept of stitched-EPI (SEPI) to enhance slope computation. SEPI achieves this by shifting and concatenating lines from different EPIs that correspond to the same 3D point. Moreover, we introduce the half-SEPI algorithm, which focuses exclusively on the non-occluded portion of lines to handle occlusion. Additionally, we present a depth propagation strategy aimed at improving depth estimation in texture-less regions. This strategy involves determining the depth of such regions by progressing from the edges towards the interior, prioritizing accurate regions over coarse regions. Through extensive experimental evaluations and ablation studies, we validate the effectiveness of our proposed method. The results demonstrate its superior ability to generate more accurate and robust depth maps across all regions compared to state-of-the-art methods. The source code will be publicly available at https://github.com/PingZhou-LF/Light-Field-Depth-Estimation-Based-on-Stitched-EPIs.

arXiv:2203.15171

Self-Supervised Light Field Depth Estimation Using Epipolar Plane Images

Exploiting light field data makes it possible to obtain dense and accurate depth map. However, synthetic scenes with limited disparity range cannot contain the diversity of real scenes. By training in synthetic data, current learning-based methods do not perform well in real scenes. In this paper, we propose a self-supervised learning framework for light field depth estimation. Different from the existing end-to-end training methods using disparity label per pixel, our approach implements network training by estimating EPI disparity shift after refocusing, which extends the disparity range of epipolar lines. To reduce the sensitivity of EPI to noise, we propose a new input mode called EPI-Stack, which stacks EPIs in the view dimension. This method is less sensitive to noise scenes than traditional input mode and improves the efficiency of estimation. Compared with other state-of-the-art methods, the proposed method can also obtain higher quality results in real-world scenarios, especially in the complex occlusion and depth discontinuity.

arXiv:2203.15132공식 코드 · Papers with Code

LocalBins: Improving Depth Estimation by Learning Local Distributions

We propose a novel architecture for depth estimation from a single image. The architecture itself is based on the popular encoder-decoder architecture that is frequently used as a starting point for all dense regression tasks. We build on AdaBins which estimates a global distribution of depth values for the input image and evolve the architecture in two ways. First, instead of predicting global depth distributions, we predict depth distributions of local neighborhoods at every pixel. Second, instead of predicting depth distributions only towards the end of the decoder, we involve all layers of the decoder. We call this new architecture LocalBins. Our results demonstrate a clear improvement over the state-of-the-art in all metrics on the NYU-Depth V2 dataset. Code and pretrained models will be made publicly available.

arXiv:2203.15174공식 코드 · Papers with Code

Disentangling Object Motion and Occlusion for Unsupervised Multi-frame Monocular Depth

Conventional self-supervised monocular depth prediction methods are based on a static environment assumption, which leads to accuracy degradation in dynamic scenes due to the mismatch and occlusion problems introduced by object motions. Existing dynamic-object-focused methods only partially solved the mismatch problem at the training loss level. In this paper, we accordingly propose a novel multi-frame monocular depth prediction method to solve these problems at both the prediction and supervision loss levels. Our method, called DynamicDepth, is a new framework trained via a self-supervised cycle consistent learning scheme. A Dynamic Object Motion Disentanglement (DOMD) module is proposed to disentangle object motions to solve the mismatch problem. Moreover, novel occlusion-aware Cost Volume and Re-projection Loss are designed to alleviate the occlusion effects of object motions. Extensive analyses and experiments on the Cityscapes and KITTI datasets show that our method significantly outperforms the state-of-the-art monocular depth prediction methods, especially in the areas of dynamic objects. Code is available at https://github.com/AutoAILab/DynamicDepth

arXiv:2203.13987공식 코드 · Papers with Code

On the Viability of Monocular Depth Pre-training for Semantic Segmentation

The question of whether pre-training on geometric tasks is viable for downstream transfer to semantic tasks is important for two reasons, one practical and the other scientific. If the answer is positive, we may be able to reduce pre-training cost and bias from human annotators significantly. If the answer is negative, it may shed light on the role of embodiment in the emergence of language and other cognitive functions in evolutionary history. To frame the question in a way that is testable with current means, we pre-train a model on a geometric task, and test whether that can be used to prime a notion of 'object' that enables inference of semantics as soon as symbols (labels) are assigned. We choose monocular depth prediction as the geometric task, and semantic segmentation as the downstream semantic task, and design a collection of empirical tests by exploring different forms of supervision, training pipelines, and data sources for both depth pre-training and semantic fine-tuning. We find that monocular depth is a viable form of pre-training for semantic segmentation, validated by improvements over common baselines. Based on the findings, we propose several possible mechanisms behind the improvements, including their relation to dataset size, resolution, architecture, in/out-of-domain source data, and validate them through a wide range of ablation studies. We also find that optical flow, which at first glance may seem as good as depth prediction since it optimizes the same photometric reprojection error, is considerably less effective, as it does not explicitly aim to infer the latent structure of the scene, but rather the raw phenomenology of temporally adjacent images.

arXiv:2203.14005

Learn to Adapt for Monocular Depth Estimation

Monocular depth estimation is one of the fundamental tasks in environmental perception and has achieved tremendous progress in virtue of deep learning. However, the performance of trained models tends to degrade or deteriorate when employed on other new datasets due to the gap between different datasets. Though some methods utilize domain adaptation technologies to jointly train different domains and narrow the gap between them, the trained models cannot generalize to new domains that are not involved in training. To boost the transferability of depth estimation models, we propose an adversarial depth estimation task and train the model in the pipeline of meta-learning. Our proposed adversarial task mitigates the issue of meta-overfitting, since the network is trained in an adversarial manner and aims to extract domain invariant representations. In addition, we propose a constraint to impose upon cross-task depth consistency to compel the depth estimation to be identical in different adversarial tasks, which improves the performance of our method and smoothens the training process. Experiments demonstrate that our method adapts well to new datasets after few training steps during the test procedure.

arXiv:2203.14211공식 코드 · Papers with Code

DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimation

This paper aims to address the problem of supervised monocular depth estimation. We start with a meticulous pilot study to demonstrate that the long-range correlation is essential for accurate depth estimation. Therefore, we propose to leverage the Transformer to model this global context with an effective attention mechanism. We also adopt an additional convolution branch to preserve the local information as the Transformer lacks the spatial inductive bias in modeling such contents. However, independent branches lead to a shortage of connections between features. To bridge this gap, we design a hierarchical aggregation and heterogeneous interaction module to enhance the Transformer features via element-wise interaction and model the affinity between the Transformer and the CNN features in a set-to-set translation manner. Due to the unbearable memory cost caused by global attention on high-resolution feature maps, we introduce the deformable scheme to reduce the complexity. Extensive experiments on the KITTI, NYU, and SUN RGB-D datasets demonstrate that our proposed model, termed DepthFormer, surpasses state-of-the-art monocular depth estimation methods with prominent margins. Notably, it achieves the most competitive result on the highly competitive KITTI depth estimation benchmark. Our codes and models are available at https://github.com/zhyever/Monocular-Depth-Estimation-Toolbox.

arXiv:2203.12804

Unsupervised Simultaneous Learning for Camera Re-Localization and Depth Estimation from Video

We present an unsupervised simultaneous learning framework for the task of monocular camera re-localization and depth estimation from unlabeled video sequences. Monocular camera re-localization refers to the task of estimating the absolute camera pose from an instance image in a known environment, which has been intensively studied for alternative localization in GPS-denied environments. In recent works, camera re-localization methods are trained via supervised learning from pairs of camera images and camera poses. In contrast to previous works, we propose a completely unsupervised learning framework for camera re-localization and depth estimation, requiring only monocular video sequences for training. In our framework, we train two networks that estimate the scene coordinates using directions and the depth map from each image which are then combined to estimate the camera pose. The networks can be trained through the minimization of loss functions based on our loop closed view synthesis. In experiments with the 7-scenes dataset, the proposed method outperformed the re-localization of the state-of-the-art visual SLAM, ORB-SLAM3. Our method also outperforms state-of-the-art monocular depth estimation in a trained environment.