PyTorchKR Papers

최신 논문

총 2,547편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1601.07649

Discriminative Training of Deep Fully-connected Continuous CRF with Task-specific Loss

Recent works on deep conditional random fields (CRF) have set new records on many vision tasks involving structured predictions. Here we propose a fully-connected deep continuous CRF model for both discrete and continuous labelling problems. We exemplify the usefulness of the proposed model on multi-class semantic labelling (discrete) and the robust depth estimation (continuous) problems. In our framework, we model both the unary and the pairwise potential functions as deep convolutional neural networks (CNN), which are jointly learned in an end-to-end fashion. The proposed method possesses the main advantage of continuously-valued CRF, which is a closed-form solution for the Maximum a posteriori (MAP) inference. To better adapt to different tasks, instead of using the commonly employed maximum likelihood CRF parameter learning protocol, we propose task-specific loss functions for learning the CRF parameters. It enables direct optimization of the quality of the MAP estimates during the course of learning. Specifically, we optimize the multi-class classification loss for the semantic labelling task and the Turkey's biweight loss for the robust depth estimation problem. Experimental results on the semantic labelling and robust depth estimation tasks demonstrate that the proposed method compare favorably against both baseline and state-of-the-art methods. In particular, we show that although the proposed deep CRF model is continuously valued, with the equipment of task-specific loss, it achieves impressive results even on discrete labelling tasks.

arXiv:1501.04537

Coupled Depth Learning

In this paper we propose a method for estimating depth from a single image using a coarse to fine approach. We argue that modeling the fine depth details is easier after a coarse depth map has been computed. We express a global (coarse) depth map of an image as a linear combination of a depth basis learned from training examples. The depth basis captures spatial and statistical regularities and reduces the problem of global depth estimation to the task of predicting the input-specific coefficients in the linear combination. This is formulated as a regression problem from a holistic representation of the image. Crucially, the depth basis and the regression function are {\bf coupled} and jointly optimized by our learning scheme. We demonstrate that this results in a significant improvement in accuracy compared to direct regression of depth pixel values or approaches learning the depth basis disjointly from the regression function. The global depth estimate is then used as a guidance by a local refinement method that introduces depth details that were not captured at the global level. Experiments on the NYUv2 and KITTI datasets show that our method outperforms the existing state-of-the-art at a considerably lower computational cost for both training and testing.

arXiv:1603.04046

Image and Depth from a Single Defocused Image Using Coded Aperture Photography

Depth from defocus and defocus deblurring from a single image are two challenging problems that are derived from the finite depth of field in conventional cameras. Coded aperture imaging is one of the techniques that is used for improving the results of these two problems. Up to now, different methods have been proposed for improving the results of either defocus deblurring or depth estimation. In this paper, a multi-objective function is proposed for evaluating and designing aperture patterns with the aim of improving the results of both depth from defocus and defocus deblurring. Pattern evaluation is performed by considering the scene illumination condition and camera system specification. Based on the proposed criteria, a single asymmetric pattern is designed that is used for restoring a sharp image and a depth map from a single input. Since the designed pattern is asymmetric, defocus objects on the two sides of the focal plane can be distinguished. Depth estimation is performed by using a new algorithm, which is based on image quality assessment criteria and can distinguish between blurred objects lying in front or behind the focal plane. Extensive simulations as well as experiments on a variety of real scenes are conducted to compare our aperture with previously proposed ones.

arXiv:1603.06359

Unified Depth Prediction and Intrinsic Image Decomposition from a Single Image via Joint Convolutional Neural Fields

We present a method for jointly predicting a depth map and intrinsic images from single-image input. The two tasks are formulated in a synergistic manner through a joint conditional random field (CRF) that is solved using a novel convolutional neural network (CNN) architecture, called the joint convolutional neural field (JCNF) model. Tailored to our joint estimation problem, JCNF differs from previous CNNs in its sharing of convolutional activations and layers between networks for each task, its inference in the gradient domain where there exists greater correlation between depth and intrinsic images, and the incorporation of a gradient scale network that learns the confidence of estimated gradients in order to effectively balance them in the solution. This approach is shown to surpass state-of-the-art methods both on single-image depth estimation and on intrinsic image decomposition.

arXiv:1604.00730

Waterdrop Stereo

This paper introduces depth estimation from water drops. The key idea is that a single water drop adhered to window glass is totally transparent and convex, and thus optically acts like a fisheye lens. If we have more than one water drop in a single image, then through each of them we can see the environment with different view points, similar to stereo. To realize this idea, we need to rectify every water drop imagery to make radially distorted planar surfaces look flat. For this rectification, we consider two physical properties of water drops: (1) A static water drop has constant volume, and its geometric convex shape is determined by the balance between the tension force and gravity. This implies that the 3D geometric shape can be obtained by minimizing the overall potential energy, which is the sum of the tension energy and the gravitational potential energy. (2) The imagery inside a water-drop is determined by the water-drop 3D shape and total reflection at the boundary. This total reflection generates a dark band commonly observed in any adherent water drops. Hence, once the 3D shape of water drops are recovered, we can rectify the water drop images through backward raytracing. Subsequently, we can compute depth using stereo. In addition to depth estimation, we can also apply image refocusing. Experiments on real images and a quantitative evaluation show the effectiveness of our proposed method. To our best knowledge, never before have adherent water drops been used to estimate depth.

arXiv:1604.03650공식 코드 · Papers with Code

Deep3D: Fully Automatic 2D-to-3D Video Conversion with Deep Convolutional Neural Networks

As 3D movie viewing becomes mainstream and Virtual Reality (VR) market emerges, the demand for 3D contents is growing rapidly. Producing 3D videos, however, remains challenging. In this paper we propose to use deep neural networks for automatically converting 2D videos and images to stereoscopic 3D format. In contrast to previous automatic 2D-to-3D conversion algorithms, which have separate stages and need ground truth depth map as supervision, our approach is trained end-to-end directly on stereo pairs extracted from 3D movies. This novel training scheme makes it possible to exploit orders of magnitude more data and significantly increases performance. Indeed, Deep3D outperforms baselines in both quantitative and human subject evaluations.

arXiv:1605.09673

Dynamic Filter Networks

In a traditional convolutional layer, the learned filters stay fixed after training. In contrast, we introduce a new framework, the Dynamic Filter Network, where filters are generated dynamically conditioned on an input. We show that this architecture is a powerful one, with increased flexibility thanks to its adaptive nature, yet without an excessive increase in the number of model parameters. A wide variety of filtering operations can be learned this way, including local spatial transformations, but also others like selective (de)blurring or adaptive feature extraction. Moreover, multiple such layers can be combined, e.g. in a recurrent architecture. We demonstrate the effectiveness of the dynamic filter network on the tasks of video and stereo prediction, and reach state-of-the-art performance on the moving MNIST dataset with a much smaller model. By visualizing the learned filters, we illustrate that the network has picked up flow information by only looking at unlabelled training data. This suggests that the network can be used to pretrain networks for various supervised tasks in an unsupervised way, like optical flow and depth estimation.

arXiv:1604.06079

Symmetry-aware Depth Estimation using Deep Neural Networks

Due to the abundance of 2D product images from the Internet, developing efficient and scalable algorithms to recover the missing depth information is central to many applications. Recent works have addressed the single-view depth estimation problem by utilizing convolutional neural networks. In this paper, we show that exploring symmetry information, which is ubiquitous in man made objects, can significantly boost the quality of such depth predictions. Specifically, we propose a new convolutional neural network architecture to first estimate dense symmetric correspondences in a product image and then propose an optimization which utilizes this information explicitly to significantly improve the quality of single-view depth estimations. We have evaluated our approach extensively, and experimental results show that this approach outperforms state-of-the-art depth estimation techniques.

arXiv:1606.08315

Depth Estimation from Single Image using Sparse Representations

Monocular depth estimation is an interesting and challenging problem as there is no analytic mapping known between an intensity image and its depth map. Recently there has been a lot of data accumulated through depth-sensing cameras, in parallel to that researchers started to tackle this task using various learning algorithms. In this paper, a deep sparse coding method is proposed for monocular depth estimation along with an approach for deterministic dictionary initialization.

arXiv:1607.06349

Fast Robust Monocular Depth Estimation for Obstacle Detection with Fully Convolutional Networks

Obstacle Detection is a central problem for any robotic system, and critical for autonomous systems that travel at high speeds in unpredictable environment. This is often achieved through scene depth estimation, by various means. When fast motion is considered, the detection range must be longer enough to allow for safe avoidance and path planning. Current solutions often make assumption on the motion of the vehicle that limit their applicability, or work at very limited ranges due to intrinsic constraints. We propose a novel appearance-based Object Detection system that is able to detect obstacles at very long range and at a very high speed (~300Hz), without making assumptions on the type of motion. We achieve these results using a Deep Neural Network approach trained on real and synthetic images and trading some depth accuracy for fast, robust and consistent operation. We show how photo-realistic synthetic images are able to solve the problem of training set dimension and variety typical of machine learning approaches, and how our system is robust to massive blurring of test images.

arXiv:1606.05002

3DFS: Deformable Dense Depth Fusion and Segmentation for Object Reconstruction from a Handheld Camera

We propose an approach for 3D reconstruction and segmentation of a single object placed on a flat surface from an input video. Our approach is to perform dense depth map estimation for multiple views using a proposed objective function that preserves detail. The resulting depth maps are then fused using a proposed implicit surface function that is robust to estimation error, producing a smooth surface reconstruction of the entire scene. Finally, the object is segmented from the remaining scene using a proposed 2D-3D segmentation that incorporates image and depth cues with priors and regularization over the 3D volume and 2D segmentations. We evaluate 3D reconstructions qualitatively on our Object-Videos dataset, comparing to fusion, multiview stereo, and segmentation baselines. We also quantitatively evaluate the dense depth estimation using the RGBD Scenes V2 dataset [Henry et al. 2013] and the segmentation using keyframe annotations of the Object-Videos dataset.

arXiv:1603.04992공식 코드 · Papers with Code

Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue

A significant weakness of most current deep Convolutional Neural Networks is the need to train them using vast amounts of manu- ally labelled data. In this work we propose a unsupervised framework to learn a deep convolutional neural network for single view depth predic- tion, without requiring a pre-training stage or annotated ground truth depths. We achieve this by training the network in a manner analogous to an autoencoder. At training time we consider a pair of images, source and target, with small, known camera motion between the two such as a stereo pair. We train the convolutional encoder for the task of predicting the depth map for the source image. To do so, we explicitly generate an inverse warp of the target image using the predicted depth and known inter-view displacement, to reconstruct the source image; the photomet- ric error in the reconstruction is the reconstruction loss for the encoder. The acquisition of this training data is considerably simpler than for equivalent systems, requiring no manual annotation, nor calibration of depth sensor to camera. We show that our network trained on less than half of the KITTI dataset (without any further augmentation) gives com- parable performance to that of the state of art supervised methods for single view depth estimation.

arXiv:1608.01745

Play and Learn: Using Video Games to Train Computer Vision Models

Video games are a compelling source of annotated data as they can readily provide fine-grained groundtruth for diverse tasks. However, it is not clear whether the synthetically generated data has enough resemblance to the real-world images to improve the performance of computer vision models in practice. We present experiments assessing the effectiveness on real-world data of systems trained on synthetic RGB images that are extracted from a video game. We collected over 60000 synthetic samples from a modern video game with similar conditions to the real-world CamVid and Cityscapes datasets. We provide several experiments to demonstrate that the synthetically generated RGB images can be used to improve the performance of deep neural networks on both image segmentation and depth estimation. These results show that a convolutional network trained on synthetic data achieves a similar test error to a network that is trained on real-world data for dense image classification. Furthermore, the synthetically generated RGB images can provide similar or better results compared to the real-world datasets if a simple domain adaptation technique is applied. Our results suggest that collaboration with game developers for an accessible interface to gather data is potentially a fruitful direction for future work in computer vision.

arXiv:1608.04187

Occlusion-Model Guided Anti-Occlusion Depth Estimation in Light Field

Occlusion is one of the most challenging problems in depth estimation. Previous work has modeled the single-occluder occlusion in light field and get good results, however it is still difficult to obtain accurate depth for multi-occluder occlusion. In this paper, we explore the multi-occluder occlusion model in light field, and derive the occluder-consistency between the spatial and angular space which is used as a guidance to select the un-occluded views for each candidate occlusion point. Then an anti-occlusion energy function is built to regularize depth map. The experimental results on public light field datasets have demonstrated the advantages of the proposed algorithm compared with other state-of-the-art light field depth estimation algorithms, especially in multi-occluder areas.

arXiv:1609.01499

Depth Estimation Through a Generative Model of Light Field Synthesis

Light field photography captures rich structural information that may facilitate a number of traditional image processing and computer vision tasks. A crucial ingredient in such endeavors is accurate depth recovery. We present a novel framework that allows the recovery of a high quality continuous depth map from light field data. To this end we propose a generative model of a light field that is fully parametrized by its corresponding depth map. The model allows for the integration of powerful regularization techniques such as a non-local means prior, facilitating accurate depth map estimation.

arXiv:1605.07081

Depth from a Single Image by Harmonizing Overcomplete Local Network Predictions

A single color image can contain many cues informative towards different aspects of local geometric structure. We approach the problem of monocular depth estimation by using a neural network to produce a mid-level representation that summarizes these cues. This network is trained to characterize local scene geometry by predicting, at every image location, depth derivatives of different orders, orientations and scales. However, instead of a single estimate for each derivative, the network outputs probability distributions that allow it to express confidence about some coefficients, and ambiguity about others. Scene depth is then estimated by harmonizing this overcomplete set of network predictions, using a globalization procedure that finds a single consistent depth map that best matches all the local derivative distributions. We demonstrate the efficacy of this approach through evaluation on the NYU v2 depth data set.

arXiv:1606.00373공식 코드 · Papers with Code

Deeper Depth Prediction with Fully Convolutional Residual Networks

This paper addresses the problem of estimating the depth map of a scene given a single RGB image. We propose a fully convolutional architecture, encompassing residual learning, to model the ambiguous mapping between monocular images and depth maps. In order to improve the output resolution, we present a novel way to efficiently learn feature map up-sampling within the network. For optimization, we introduce the reverse Huber loss that is particularly suited for the task at hand and driven by the value distributions commonly present in depth maps. Our model is composed of a single architecture that is trained end-to-end and does not rely on post-processing techniques, such as CRFs or other additional refinement steps. As a result, it runs in real-time on images or videos. In the evaluation, we show that the proposed model contains fewer parameters and requires fewer training data than the current state of the art, while outperforming all approaches on depth estimation. Code and models are publicly available.

arXiv:1604.07480

Joint Semantic Segmentation and Depth Estimation with Deep Convolutional Networks

Multi-scale deep CNNs have been used successfully for problems mapping each pixel to a label, such as depth estimation and semantic segmentation. It has also been shown that such architectures are reusable and can be used for multiple tasks. These networks are typically trained independently for each task by varying the output layer(s) and training objective. In this work we present a new model for simultaneous depth estimation and semantic segmentation from a single RGB image. Our approach demonstrates the feasibility of training parts of the model for each task and then fine tuning the full, combined model on both tasks simultaneously using a single loss function. Furthermore we couple the deep CNN with fully connected CRF, which captures the contextual relationships and interactions between the semantic and depth cues improving the accuracy of the final results. The proposed model is trained and evaluated on NYUDepth V2 dataset outperforming the state of the art methods on semantic segmentation and achieving comparable results on the task of depth estimation.

arXiv:1609.09545공식 코드 · Papers with Code

Two-stage Convolutional Part Heatmap Regression for the 1st 3D Face Alignment in the Wild (3DFAW) Challenge

This paper describes our submission to the 1st 3D Face Alignment in the Wild (3DFAW) Challenge. Our method builds upon the idea of convolutional part heatmap regression [1], extending it for 3D face alignment. Our method decomposes the problem into two parts: (a) X,Y (2D) estimation and (b) Z (depth) estimation. At the first stage, our method estimates the X,Y coordinates of the facial landmarks by producing a set of 2D heatmaps, one for each landmark, using convolutional part heatmap regression. Then, these heatmaps, alongside the input RGB image, are used as input to a very deep subnetwork trained via residual learning for regressing the Z coordinate. Our method ranked 1st in the 3DFAW Challenge, surpassing the second best result by more than 22%.

arXiv:1610.01706

Exploiting Depth from Single Monocular Images for Object Detection and Semantic Segmentation

Augmenting RGB data with measured depth has been shown to improve the performance of a range of tasks in computer vision including object detection and semantic segmentation. Although depth sensors such as the Microsoft Kinect have facilitated easy acquisition of such depth information, the vast majority of images used in vision tasks do not contain depth information. In this paper, we show that augmenting RGB images with estimated depth can also improve the accuracy of both object detection and semantic segmentation. Specifically, we first exploit the recent success of depth estimation from monocular images and learn a deep depth estimation model. Then we learn deep depth features from the estimated depth and combine with RGB features for object detection and semantic segmentation. Additionally, we propose an RGB-D semantic segmentation method which applies a multi-task training scheme: semantic label prediction and depth value regression. We test our methods on several datasets and demonstrate that incorporating information from estimated depth improves the performance of object detection and semantic segmentation remarkably.