PyTorchKR Papers

최신 논문

총 2,547편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2007.09209

People as Scene Probes

By analyzing the motion of people and other objects in a scene, we demonstrate how to infer depth, occlusion, lighting, and shadow information from video taken from a single camera viewpoint. This information is then used to composite new objects into the same scene with a high degree of automation and realism. In particular, when a user places a new object (2D cut-out) in the image, it is automatically rescaled, relit, occluded properly, and casts realistic shadows in the correct direction relative to the sun, and which conform properly to scene geometry. We demonstrate results (best viewed in supplementary video) on a range of scenes and compare to alternative methods for depth estimation and shadow compositing.

arXiv:2007.10042공식 코드 · Papers with Code

Non-Local Spatial Propagation Network for Depth Completion

In this paper, we propose a robust and efficient end-to-end non-local spatial propagation network for depth completion. The proposed network takes RGB and sparse depth images as inputs and estimates non-local neighbors and their affinities of each pixel, as well as an initial depth map with pixel-wise confidences. The initial depth prediction is then iteratively refined by its confidence and non-local spatial propagation procedure based on the predicted non-local neighbors and corresponding affinities. Unlike previous algorithms that utilize fixed-local neighbors, the proposed algorithm effectively avoids irrelevant local neighbors and concentrates on relevant non-local neighbors during propagation. In addition, we introduce a learnable affinity normalization to better learn the affinity combinations compared to conventional methods. The proposed algorithm is inherently robust to the mixed-depth problem on depth boundaries, which is one of the major issues for existing depth estimation/completion algorithms. Experimental results on indoor and outdoor datasets demonstrate that the proposed algorithm is superior to conventional algorithms in terms of depth completion accuracy and robustness to the mixed-depth problem. Our implementation is publicly available on the project page.

arXiv:2007.09836

Object-Aware Centroid Voting for Monocular 3D Object Detection

Monocular 3D object detection aims to detect objects in a 3D physical world from a single camera. However, recent approaches either rely on expensive LiDAR devices, or resort to dense pixel-wise depth estimation that causes prohibitive computational cost. In this paper, we propose an end-to-end trainable monocular 3D object detector without learning the dense depth. Specifically, the grid coordinates of a 2D box are first projected back to 3D space with the pinhole model as 3D centroids proposals. Then, a novel object-aware voting approach is introduced, which considers both the region-wise appearance attention and the geometric projection distribution, to vote the 3D centroid proposals for 3D object localization. With the late fusion and the predicted 3D orientation and dimension, the 3D bounding boxes of objects can be detected from a single RGB image. The method is straightforward yet significantly superior to other monocular-based methods. Extensive experimental results on the challenging KITTI benchmark validate the effectiveness of the proposed method.

arXiv:2007.08943공식 코드 · Papers with Code

HDNet: Human Depth Estimation for Multi-Person Camera-Space Localization

Current works on multi-person 3D pose estimation mainly focus on the estimation of the 3D joint locations relative to the root joint and ignore the absolute locations of each pose. In this paper, we propose the Human Depth Estimation Network (HDNet), an end-to-end framework for absolute root joint localization in the camera coordinate space. Our HDNet first estimates the 2D human pose with heatmaps of the joints. These estimated heatmaps serve as attention masks for pooling features from image regions corresponding to the target person. A skeleton-based Graph Neural Network (GNN) is utilized to propagate features among joints. We formulate the target depth regression as a bin index estimation problem, which can be transformed with a soft-argmax operation from the classification output of our HDNet. We evaluate our HDNet on the root joint localization and root-relative 3D pose estimation tasks with two benchmark datasets, i.e., Human3.6M and MuPoTS-3D. The experimental results show that we outperform the previous state-of-the-art consistently under multiple evaluation metrics. Our source code is available at: https://github.com/jiahaoLjh/HumanDepth.

arXiv:2007.08113공식 코드 · Papers with Code

Defocus Blur Detection via Depth Distillation

Defocus Blur Detection(DBD) aims to separate in-focus and out-of-focus regions from a single image pixel-wisely. This task has been paid much attention since bokeh effects are widely used in digital cameras and smartphone photography. However, identifying obscure homogeneous regions and borderline transitions in partially defocus images is still challenging. To solve these problems, we introduce depth information into DBD for the first time. When the camera parameters are fixed, we argue that the accuracy of DBD is highly related to scene depth. Hence, we consider the depth information as the approximate soft label of DBD and propose a joint learning framework inspired by knowledge distillation. In detail, we learn the defocus blur from ground truth and the depth distilled from a well-trained depth estimation network at the same time. Thus, the sharp region will provide a strong prior for depth estimation while the blur detection also gains benefits from the distilled depth. Besides, we propose a novel decoder in the fully convolutional network(FCN) as our network structure. In each level of the decoder, we design the Selective Reception Field Block(SRFB) for merging multi-scale features efficiently and reuse the side outputs as Supervision-guided Attention Block(SAB). Unlike previous methods, the proposed decoder builds reception field pyramids and emphasizes salient regions simply and efficiently. Experiments show that our approach outperforms 11 other state-of-the-art methods on two popular datasets. Our method also runs at over 30 fps on a single GPU, which is 2x faster than previous works. The code is available at: https://github.com/vinthony/depth-distillation

arXiv:2007.07696공식 코드 · Papers with Code

P$^{2}$Net: Patch-match and Plane-regularization for Unsupervised Indoor Depth Estimation

This paper tackles the unsupervised depth estimation task in indoor environments. The task is extremely challenging because of the vast areas of non-texture regions in these scenes. These areas could overwhelm the optimization process in the commonly used unsupervised depth estimation framework proposed for outdoor environments. However, even when those regions are masked out, the performance is still unsatisfactory. In this paper, we argue that the poor performance suffers from the non-discriminative point-based matching. To this end, we propose P$^2$Net. We first extract points with large local gradients and adopt patches centered at each point as its representation. Multiview consistency loss is then defined over patches. This operation significantly improves the robustness of the network training. Furthermore, because those textureless regions in indoor scenes (e.g., wall, floor, roof, \etc) usually correspond to planar regions, we propose to leverage superpixels as a plane prior. We enforce the predicted depth to be well fitted by a plane within each superpixel. Extensive experiments on NYUv2 and ScanNet show that our P$^2$Net outperforms existing approaches by a large margin. Code is available at \url{https://github.com/svip-lab/Indoor-SfMLearner}.

arXiv:2007.07567

P2D: a self-supervised method for depth estimation from polarimetry

Monocular depth estimation is a recurring subject in the field of computer vision. Its ability to describe scenes via a depth map while reducing the constraints related to the formulation of perspective geometry tends to favor its use. However, despite the constant improvement of algorithms, most methods exploit only colorimetric information. Consequently, robustness to events to which the modality is not sensitive to, like specularity or transparency, is neglected. In response to this phenomenon, we propose using polarimetry as an input for a self-supervised monodepth network. Therefore, we propose exploiting polarization cues to encourage accurate reconstruction of scenes. Furthermore, we include a term of polarimetric regularization to state-of-the-art method to take specific advantage of the data. Our method is evaluated both qualitatively and quantitatively demonstrating that the contribution of this new information as well as an enhanced loss function improves depth estimation results, especially for specular areas.

arXiv:2007.07502

Monocular Retinal Depth Estimation and Joint Optic Disc and Cup Segmentation using Adversarial Networks

One of the important parameters for the assessment of glaucoma is optic nerve head (ONH) evaluation, which usually involves depth estimation and subsequent optic disc and cup boundary extraction. Depth is usually obtained explicitly from imaging modalities like optical coherence tomography (OCT) and is very challenging to estimate depth from a single RGB image. To this end, we propose a novel method using adversarial network to predict depth map from a single image. The proposed depth estimation technique is trained and evaluated using individual retinal images from INSPIRE-stereo dataset. We obtain a very high average correlation coefficient of 0.92 upon five fold cross validation outperforming the state of the art. We then use the depth estimation process as a proxy task for joint optic disc and cup segmentation.

arXiv:2007.06705

Unsupervised object-centric video generation and decomposition in 3D

A natural approach to generative modeling of videos is to represent them as a composition of moving objects. Recent works model a set of 2D sprites over a slowly-varying background, but without considering the underlying 3D scene that gives rise to them. We instead propose to model a video as the view seen while moving through a scene with multiple 3D objects and a 3D background. Our model is trained from monocular videos without any supervision, yet learns to generate coherent 3D scenes containing several moving objects. We conduct detailed experiments on two datasets, going beyond the visual complexity supported by state-of-the-art generative approaches. We evaluate our method on depth-prediction and 3D object detection -- tasks which cannot be addressed by those earlier works -- and show it out-performs them even on 2D instance segmentation and tracking.

arXiv:2007.06676

UnRectDepthNet: Self-Supervised Monocular Depth Estimation using a Generic Framework for Handling Common Camera Distortion Models

In classical computer vision, rectification is an integral part of multi-view depth estimation. It typically includes epipolar rectification and lens distortion correction. This process simplifies the depth estimation significantly, and thus it has been adopted in CNN approaches. However, rectification has several side effects, including a reduced field of view (FOV), resampling distortion, and sensitivity to calibration errors. The effects are particularly pronounced in case of significant distortion (e.g., wide-angle fisheye cameras). In this paper, we propose a generic scale-aware self-supervised pipeline for estimating depth, euclidean distance, and visual odometry from unrectified monocular videos. We demonstrate a similar level of precision on the unrectified KITTI dataset with barrel distortion comparable to the rectified KITTI dataset. The intuition being that the rectification step can be implicitly absorbed within the CNN model, which learns the distortion model without increasing complexity. Our approach does not suffer from a reduced field of view and avoids computational costs for rectification at inference time. To further illustrate the general applicability of the proposed framework, we apply it to wide-angle fisheye cameras with 190$^\circ$ horizontal field of view. The training framework UnRectDepthNet takes in the camera distortion model as an argument and adapts projection and unprojection functions accordingly. The proposed algorithm is evaluated further on the KITTI rectified dataset, and we achieve state-of-the-art results that improve upon our previous work FisheyeDistanceNet. Qualitative results on a distorted test scene video sequence indicate excellent performance https://youtu.be/K6pbx3bU4Ss.

arXiv:2007.06936공식 코드 · Papers with Code

Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance

Self-supervised monocular depth estimation presents a powerful method to obtain 3D scene information from single camera images, which is trainable on arbitrary image sequences without requiring depth labels, e.g., from a LiDAR sensor. In this work we present a new self-supervised semantically-guided depth estimation (SGDepth) method to deal with moving dynamic-class (DC) objects, such as moving cars and pedestrians, which violate the static-world assumptions typically made during training of such models. Specifically, we propose (i) mutually beneficial cross-domain training of (supervised) semantic segmentation and self-supervised depth estimation with task-specific network heads, (ii) a semantic masking scheme providing guidance to prevent moving DC objects from contaminating the photometric loss, and (iii) a detection method for frames with non-moving DC objects, from which the depth of DC objects can be learned. We demonstrate the performance of our method on several benchmarks, in particular on the Eigen split, where we exceed all baselines without test-time refinement.

arXiv:2007.06891공식 코드 · Papers with Code

360$^\circ$ Depth Estimation from Multiple Fisheye Images with Origami Crown Representation of Icosahedron

In this study, we present a method for all-around depth estimation from multiple omnidirectional images for indoor environments. In particular, we focus on plane-sweeping stereo as the method for depth estimation from the images. We propose a new icosahedron-based representation and ConvNets for omnidirectional images, which we name "CrownConv" because the representation resembles a crown made of origami. CrownConv can be applied to both fisheye images and equirectangular images to extract features. Furthermore, we propose icosahedron-based spherical sweeping for generating the cost volume on an icosahedron from the extracted features. The cost volume is regularized using the three-dimensional CrownConv, and the final depth is obtained by depth regression from the cost volume. Our proposed method is robust to camera alignments by using the extrinsic camera parameters; therefore, it can achieve precise depth estimation even when the camera alignment differs from that in the training dataset. We evaluate the proposed model on synthetic datasets and demonstrate its effectiveness. As our proposed method is computationally efficient, the depth is estimated from four fisheye images in less than a second using a laptop with a GPU. Therefore, it is suitable for real-world robotics applications. Our source code is available at https://github.com/matsuren/crownconv360depth.

arXiv:2007.06153공식 코드 · Papers with Code

AI Playground: Unreal Engine-based Data Ablation Tool for Deep Learning

Machine learning requires data, but acquiring and labeling real-world data is challenging, expensive, and time-consuming. More importantly, it is nearly impossible to alter real data post-acquisition (e.g., change the illumination of a room), making it very difficult to measure how specific properties of the data affect performance. In this paper, we present AI Playground (AIP), an open-source, Unreal Engine-based tool for generating and labeling virtual image data. With AIP, it is trivial to capture the same image under different conditions (e.g., fidelity, lighting, etc.) and with different ground truths (e.g., depth or surface normal values). AIP is easily extendable and can be used with or without code. To validate our proposed tool, we generated eight datasets of otherwise identical but varying lighting and fidelity conditions. We then trained deep neural networks to predict (1) depth values, (2) surface normals, or (3) object labels and assessed each network's intra- and cross-dataset performance. Among other insights, we verified that sensitivity to different settings is problem-dependent. We confirmed the findings of other studies that segmentation models are very sensitive to fidelity, but we also found that they are just as sensitive to lighting. In contrast, depth and normal estimation models seem to be less sensitive to fidelity or lighting and more sensitive to the structure of the image. Finally, we tested our trained depth-estimation networks on two real-world datasets and obtained results comparable to training on real data alone, confirming that our virtual environments are realistic enough for real-world tasks.

arXiv:2007.05233공식 코드 · Papers with Code

Continual Adaptation for Deep Stereo

Depth estimation from stereo images is carried out with unmatched results by convolutional neural networks trained end-to-end to regress dense disparities. Like for most tasks, this is possible if large amounts of labelled samples are available for training, possibly covering the whole data distribution encountered at deployment time. Being such an assumption systematically unmet in real applications, the capacity of adapting to any unseen setting becomes of paramount importance. Purposely, we propose a continual adaptation paradigm for deep stereo networks designed to deal with challenging and ever-changing environments. We design a lightweight and modular architecture, Modularly ADaptive Network (MADNet), and formulate Modular ADaptation algorithms (MAD, MAD++) which permit efficient optimization of independent sub-portions of the entire network. In our paradigm, the learning signals needed to continuously adapt models online can be sourced from self-supervision via right-to-left image warping or from traditional stereo algorithms. With both sources, no other data than the input images being gathered at deployment time are needed. Thus, our network architecture and adaptation algorithms realize the first real-time self-adaptive deep stereo system and pave the way for a new paradigm that can facilitate practical deployment of end-to-end architectures for dense disparity regression.

arXiv:2007.04538공식 코드 · Papers with Code

EPI-based Oriented Relation Networks for Light Field Depth Estimation

Light field cameras record not only the spatial information of observed scenes but also the directions of all incoming light rays. The spatial and angular information implicitly contain geometrical characteristics such as multi-view or epipolar geometry, which can be exploited to improve the performance of depth estimation. An Epipolar Plane Image (EPI), the unique 2D spatial-angular slice of the light field, contains patterns of oriented lines. The slope of these lines is associated with the disparity. Benefiting from this property of EPIs, some representative methods estimate depth maps by analyzing the disparity of each line in EPIs. However, these methods often extract the optimal slope of the lines from EPIs while ignoring the relationship between neighboring pixels, which leads to inaccurate depth map predictions. Based on the observation that an oriented line and its neighboring pixels in an EPI share a similar linear structure, we propose an end-to-end fully convolutional network (FCN) to estimate the depth value of the intersection point on the horizontal and vertical EPIs. Specifically, we present a new feature-extraction module, called Oriented Relation Module (ORM), that constructs the relationship between the line orientations. To facilitate training, we also propose a refocusing-based data augmentation method to obtain different slopes from EPIs of the same scene point. Extensive experiments verify the efficacy of learning relations and show that our approach is competitive to other state-of-the-art methods. The code and the trained models are available at https://github.com/lkyahpu/EPI_ORM.git.

arXiv:2007.03887공식 코드 · Papers with Code

Camera Pose Matters: Improving Depth Prediction by Mitigating Pose Distribution Bias

Monocular depth predictors are typically trained on large-scale training sets which are naturally biased w.r.t the distribution of camera poses. As a result, trained predictors fail to make reliable depth predictions for testing examples captured under uncommon camera poses. To address this issue, we propose two novel techniques that exploit the camera pose during training and prediction. First, we introduce a simple perspective-aware data augmentation that synthesizes new training examples with more diverse views by perturbing the existing ones in a geometrically consistent manner. Second, we propose a conditional model that exploits the per-image camera pose as prior knowledge by encoding it as a part of the input. We show that jointly applying the two methods improves depth prediction on images captured under uncommon and even never-before-seen camera poses. We show that our methods improve performance when applied to a range of different predictor architectures. Lastly, we show that explicitly encoding the camera pose distribution improves the generalization performance of a synthetically trained depth predictor when evaluated on real images.

arXiv:2007.03085공식 코드 · Papers with Code

Wasserstein Distances for Stereo Disparity Estimation

Existing approaches to depth or disparity estimation output a distribution over a set of pre-defined discrete values. This leads to inaccurate results when the true depth or disparity does not match any of these values. The fact that this distribution is usually learned indirectly through a regression loss causes further problems in ambiguous regions around object boundaries. We address these issues using a new neural network architecture that is capable of outputting arbitrary depth values, and a new loss function that is derived from the Wasserstein distance between the true and the predicted distributions. We validate our approach on a variety of tasks, including stereo disparity and depth estimation, and the downstream 3D object detection. Our approach drastically reduces the error in ambiguous regions, especially around object boundaries that greatly affect the localization of objects in 3D, achieving the state-of-the-art in 3D object detection for autonomous driving. Our code will be available at https://github.com/Div99/W-Stereo-Disp.

arXiv:2007.02361

Self-supervised Depth Estimation to Regularise Semantic Segmentation in Knee Arthroscopy

Intra-operative automatic semantic segmentation of knee joint structures can assist surgeons during knee arthroscopy in terms of situational awareness. However, due to poor imaging conditions (e.g., low texture, overexposure, etc.), automatic semantic segmentation is a challenging scenario, which justifies the scarce literature on this topic. In this paper, we propose a novel self-supervised monocular depth estimation to regularise the training of the semantic segmentation in knee arthroscopy. To further regularise the depth estimation, we propose the use of clean training images captured by the stereo arthroscope of routine objects (presenting none of the poor imaging conditions and with rich texture information) to pre-train the model. We fine-tune such model to produce both the semantic segmentation and self-supervised monocular depth using stereo arthroscopic images taken from inside the knee. Using a data set containing 3868 arthroscopic images captured during cadaveric knee arthroscopy with semantic segmentation annotations, 2000 stereo image pairs of cadaveric knee arthroscopy, and 2150 stereo image pairs of routine objects, we show that our semantic segmentation regularised by self-supervised depth estimation produces a more accurate segmentation than a state-of-the-art semantic segmentation approach modeled exclusively with semantic segmentation annotation.

arXiv:2007.01711

Synergistic saliency and depth prediction for RGB-D saliency detection

Depth information available from an RGB-D camera can be useful in segmenting salient objects when figure/ground cues from RGB channels are weak. This has motivated the development of several RGB-D saliency datasets and algorithms that use all four channels of the RGB-D data for both training and inference. Unfortunately, existing RGB-D saliency datasets are small, which may lead to overfitting and limited generalization for diverse scenarios. Here we propose a semi-supervised system for RGB-D saliency detection that can be trained on smaller RGB-D saliency datasets without saliency ground truth, while also make effective joint use of a large RGB saliency dataset with saliency ground truth together. To generalize our method on RGB-D saliency datasets, a novel prediction-guided cross-refinement module which jointly estimates both saliency and depth by mutual refinement between two respective tasks, and an adversarial learning approach are employed. Critically, our system does not require saliency ground-truth for the RGB-D datasets, which saves the massive human labor for hand labeling, and does not require the depth data for inference, allowing the method to be used for the much broader range of applications where only RGB data are available. Evaluation on seven RGB-D datasets demonstrates that even without saliency ground truth for RGB-D datasets and using only the RGB data of RGB-D datasets at inference, our semi-supervised system performs favorable against state-of-the-art fully-supervised RGB-D saliency detection methods that use saliency ground truth for RGB-D datasets at training and depth data at inference on two largest testing datasets. Our approach also achieves comparable results on other popular RGB-D saliency benchmarks.

arXiv:2007.01164

Data-Driven Method for Enhanced Corrosion Assessment of Reinforced Concrete Structures

Corrosion is a major problem affecting the durability of reinforced concrete structures. Corrosion related maintenance and repair of reinforced concrete structures cost multibillion USD per annum globally. It is often triggered by the ingression of carbon dioxide and/or chloride into the pores of concrete. Estimation of these corrosion causing factors using the conventional models results in suboptimal assessment since they are incapable of capturing the complex interaction of parameters. Hygrothermal interaction also plays a role in aggravating the corrosion of reinforcement bar and this is usually counteracted by applying surface-protection systems. These systems have different degree of protection and they may even cause deterioration to the structure unintentionally. The overall objective of this dissertation is to provide a framework that enhances the assessment reliability of the corrosion controlling factors. The framework is realized through the development of data-driven carbonation depth, chloride profile and hygrothermal performance prediction models. The carbonation depth prediction model integrates neural network, decision tree, boosted and bagged ensemble decision trees. The ensemble tree based chloride profile prediction models evaluate the significance of chloride ingress controlling variables from various perspectives. The hygrothermal interaction prediction models are developed using neural networks to evaluate the status of corrosion and other unexpected deteriorations in surface-treated concrete elements. Long-term data for all models were obtained from three different field experiments. The performance comparison of the developed carbonation depth prediction model with the conventional one confirmed the prediction superiority of the data-driven model. The variable ...