We propose a method to recover the shape of a 3D room from a full-view indoor panorama. Our algorithm can automatically infer a 3D shape from a collection of partially oriented superpixel facets and line segments. The core part of the algorithm is a constraint graph, which includes lines and superpixels as vertices, and encodes their geometric relations as edges. A novel approach is proposed to perform 3D reconstruction based on the constraint graph by solving all the geometric constraints as constrained linear least-squares. The selected constraints used for reconstruction are identified using an occlusion detection method with a Markov random field. Experiments show that our method can recover room shapes that can not be addressed by previous approaches. Our method is also efficient, that is, the inference time for each panorama is less than 1 minute.
{"title":"Efficient 3D Room Shape Recovery from a Single Panorama","authors":"Hao Yang, Hui Zhang","doi":"10.1109/CVPR.2016.585","DOIUrl":"https://doi.org/10.1109/CVPR.2016.585","url":null,"abstract":"We propose a method to recover the shape of a 3D room from a full-view indoor panorama. Our algorithm can automatically infer a 3D shape from a collection of partially oriented superpixel facets and line segments. The core part of the algorithm is a constraint graph, which includes lines and superpixels as vertices, and encodes their geometric relations as edges. A novel approach is proposed to perform 3D reconstruction based on the constraint graph by solving all the geometric constraints as constrained linear least-squares. The selected constraints used for reconstruction are identified using an occlusion detection method with a Markov random field. Experiments show that our method can recover room shapes that can not be addressed by previous approaches. Our method is also efficient, that is, the inference time for each panorama is less than 1 minute.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"12 1","pages":"5422-5430"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75344881","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper presents a novel unsupervised method to transfer the style of an example image to a source image. The complex notion of image style is here considered as a local texture transfer, eventually coupled with a global color transfer. For the local texture transfer, we propose a new method based on an adaptive patch partition that captures the style of the example image and preserves the structure of the source image. More precisely, this example-based partition predicts how well a source patch matches an example patch. Results on various images show that our method outperforms the most recent techniques.
{"title":"Split and Match: Example-Based Adaptive Patch Sampling for Unsupervised Style Transfer","authors":"Oriel Frigo, Neus Sabater, J. Delon, P. Hellier","doi":"10.1109/CVPR.2016.66","DOIUrl":"https://doi.org/10.1109/CVPR.2016.66","url":null,"abstract":"This paper presents a novel unsupervised method to transfer the style of an example image to a source image. The complex notion of image style is here considered as a local texture transfer, eventually coupled with a global color transfer. For the local texture transfer, we propose a new method based on an adaptive patch partition that captures the style of the example image and preserves the structure of the source image. More precisely, this example-based partition predicts how well a source patch matches an example patch. Results on various images show that our method outperforms the most recent techniques.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"30 1","pages":"553-561"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75429578","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Kenichiro Tanaka, Y. Mukaigawa, Hiroyuki Kubo, Y. Matsushita, Y. Yagi
This paper presents a method for recovering shape and normal of a transparent object from a single viewpoint using a Time-of-Flight (ToF) camera. Our method is built upon the fact that the speed of light varies with the refractive index of the medium and therefore the depth measurement of a transparent object with a ToF camera may be distorted. We show that, from this ToF distortion, the refractive light path can be uniquely determined by estimating a single parameter. We estimate this parameter by introducing a surface normal consistency between the one determined by a light path candidate and the other computed from the corresponding shape. The proposed method is evaluated by both simulation and real-world experiments and shows faithful transparent shape recovery.
{"title":"Recovering Transparent Shape from Time-of-Flight Distortion","authors":"Kenichiro Tanaka, Y. Mukaigawa, Hiroyuki Kubo, Y. Matsushita, Y. Yagi","doi":"10.1109/CVPR.2016.475","DOIUrl":"https://doi.org/10.1109/CVPR.2016.475","url":null,"abstract":"This paper presents a method for recovering shape and normal of a transparent object from a single viewpoint using a Time-of-Flight (ToF) camera. Our method is built upon the fact that the speed of light varies with the refractive index of the medium and therefore the depth measurement of a transparent object with a ToF camera may be distorted. We show that, from this ToF distortion, the refractive light path can be uniquely determined by estimating a single parameter. We estimate this parameter by introducing a surface normal consistency between the one determined by a light path candidate and the other computed from the corresponding shape. The proposed method is evaluated by both simulation and real-world experiments and shows faithful transparent shape recovery.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"25 1","pages":"4387-4395"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74334763","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Conventional representation based classifiers, ranging from the classical nearest neighbor classifier and nearest subspace classifier to the recently developed sparse representation based classifier (SRC) and collaborative representation based classifier (CRC), are essentially distance based classifiers. Though SRC and CRC have shown interesting classification results, their intrinsic classification mechanism remains unclear. In this paper we propose a probabilistic collaborative representation framework, where the probability that a test sample belongs to the collaborative subspace of all classes can be well defined and computed. Consequently, we present a probabilistic collaborative representation based classifier (ProCRC), which jointly maximizes the likelihood that a test sample belongs to each of the multiple classes. The final classification is performed by checking which class has the maximum likelihood. The proposed ProCRC has a clear probabilistic interpretation, and it shows superior performance to many popular classifiers, including SRC, CRC and SVM. Coupled with the CNN features, it also leads to state-of-the-art classification results on a variety of challenging visual datasets.
{"title":"A Probabilistic Collaborative Representation Based Approach for Pattern Classification","authors":"Sijia Cai, Lei Zhang, W. Zuo, Xiangchu Feng","doi":"10.1109/CVPR.2016.322","DOIUrl":"https://doi.org/10.1109/CVPR.2016.322","url":null,"abstract":"Conventional representation based classifiers, ranging from the classical nearest neighbor classifier and nearest subspace classifier to the recently developed sparse representation based classifier (SRC) and collaborative representation based classifier (CRC), are essentially distance based classifiers. Though SRC and CRC have shown interesting classification results, their intrinsic classification mechanism remains unclear. In this paper we propose a probabilistic collaborative representation framework, where the probability that a test sample belongs to the collaborative subspace of all classes can be well defined and computed. Consequently, we present a probabilistic collaborative representation based classifier (ProCRC), which jointly maximizes the likelihood that a test sample belongs to each of the multiple classes. The final classification is performed by checking which class has the maximum likelihood. The proposed ProCRC has a clear probabilistic interpretation, and it shows superior performance to many popular classifiers, including SRC, CRC and SVM. Coupled with the CNN features, it also leads to state-of-the-art classification results on a variety of challenging visual datasets.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"45 1","pages":"2950-2959"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74355017","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Rendering the semantic content of an image in different styles is a difficult image processing task. Arguably, a major limiting factor for previous approaches has been the lack of image representations that explicitly represent semantic information and, thus, allow to separate image content from style. Here we use image representations derived from Convolutional Neural Networks optimised for object recognition, which make high level image information explicit. We introduce A Neural Algorithm of Artistic Style that can separate and recombine the image content and style of natural images. The algorithm allows us to produce new images of high perceptual quality that combine the content of an arbitrary photograph with the appearance of numerous wellknown artworks. Our results provide new insights into the deep image representations learned by Convolutional Neural Networks and demonstrate their potential for high level image synthesis and manipulation.
{"title":"Image Style Transfer Using Convolutional Neural Networks","authors":"Leon A. Gatys, Alexander S. Ecker, M. Bethge","doi":"10.1109/CVPR.2016.265","DOIUrl":"https://doi.org/10.1109/CVPR.2016.265","url":null,"abstract":"Rendering the semantic content of an image in different styles is a difficult image processing task. Arguably, a major limiting factor for previous approaches has been the lack of image representations that explicitly represent semantic information and, thus, allow to separate image content from style. Here we use image representations derived from Convolutional Neural Networks optimised for object recognition, which make high level image information explicit. We introduce A Neural Algorithm of Artistic Style that can separate and recombine the image content and style of natural images. The algorithm allows us to produce new images of high perceptual quality that combine the content of an arbitrary photograph with the appearance of numerous wellknown artworks. Our results provide new insights into the deep image representations learned by Convolutional Neural Networks and demonstrate their potential for high level image synthesis and manipulation.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"16 1","pages":"2414-2423"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74728119","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Wangjiang Zhu, Jie Hu, Gang Sun, Xudong Cao, Y. Qiao
Recently, deep learning approaches have demonstrated remarkable progresses for action recognition in videos. Most existing deep frameworks equally treat every volume i.e. spatial-temporal video clip, and directly assign a video label to all volumes sampled from it. However, within a video, discriminative actions may occur sparsely in a few key volumes, and most other volumes are irrelevant to the labeled action category. Training with a large proportion of irrelevant volumes will hurt performance. To address this issue, we propose a key volume mining deep framework to identify key volumes and conduct classification simultaneously. Specifically, our framework is trained is optimized in an alternative way integrated to the forward and backward stages of Stochastic Gradient Descent (SGD). In the forward pass, our network mines key volumes for each action class. In the backward pass, it updates network parameters with the help of these mined key volumes. In addition, we propose "Stochastic out" to model key volumes from multi-modalities, and an effective yet simple "unsupervised key volume proposal" method for high quality volume sampling. Our experiments show that action recognition performance can be significantly improved by mining key volumes, and we achieve state-of-the-art performance on HMDB51 and UCF101 (93.1%).
{"title":"A Key Volume Mining Deep Framework for Action Recognition","authors":"Wangjiang Zhu, Jie Hu, Gang Sun, Xudong Cao, Y. Qiao","doi":"10.1109/CVPR.2016.219","DOIUrl":"https://doi.org/10.1109/CVPR.2016.219","url":null,"abstract":"Recently, deep learning approaches have demonstrated remarkable progresses for action recognition in videos. Most existing deep frameworks equally treat every volume i.e. spatial-temporal video clip, and directly assign a video label to all volumes sampled from it. However, within a video, discriminative actions may occur sparsely in a few key volumes, and most other volumes are irrelevant to the labeled action category. Training with a large proportion of irrelevant volumes will hurt performance. To address this issue, we propose a key volume mining deep framework to identify key volumes and conduct classification simultaneously. Specifically, our framework is trained is optimized in an alternative way integrated to the forward and backward stages of Stochastic Gradient Descent (SGD). In the forward pass, our network mines key volumes for each action class. In the backward pass, it updates network parameters with the help of these mined key volumes. In addition, we propose \"Stochastic out\" to model key volumes from multi-modalities, and an effective yet simple \"unsupervised key volume proposal\" method for high quality volume sampling. Our experiments show that action recognition performance can be significantly improved by mining key volumes, and we achieve state-of-the-art performance on HMDB51 and UCF101 (93.1%).","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"34 1","pages":"1991-1999"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79152167","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Fine grained video action analysis often requires reliable detection and tracking of various interacting objects and human body parts, denoted as Interactional Object Parsing. However, most of the previous methods based on either independent or joint object detection might suffer from high model complexity and challenging image content, e.g., illumination/pose/appearance/scale variation, motion, and occlusion etc. In this work, we propose an end-to-end system based on recurrent neural network to perform frame by frame interactional object parsing, which can alleviate the difficulty through an incremental/progressive manner. Our key innovation is that: instead of jointly outputting all object detections at once, for each frame we use a set of long-short term memory (LSTM) nodes to incrementally refine the detections. After passing through each LSTM node, more object detections are consolidated and thus more contextual information could be utilized to localize more difficult objects. The object parsing results are further utilized to form object specific action representation for fine grained action detection. Extensive experiments on two benchmark fine grained activity datasets demonstrate that our proposed algorithm achieves better interacting object detection performance, which in turn boosts the action recognition performance over the state-of-the-art.
{"title":"Progressively Parsing Interactional Objects for Fine Grained Action Detection","authors":"Bingbing Ni, Xiaokang Yang, Shenghua Gao","doi":"10.1109/CVPR.2016.116","DOIUrl":"https://doi.org/10.1109/CVPR.2016.116","url":null,"abstract":"Fine grained video action analysis often requires reliable detection and tracking of various interacting objects and human body parts, denoted as Interactional Object Parsing. However, most of the previous methods based on either independent or joint object detection might suffer from high model complexity and challenging image content, e.g., illumination/pose/appearance/scale variation, motion, and occlusion etc. In this work, we propose an end-to-end system based on recurrent neural network to perform frame by frame interactional object parsing, which can alleviate the difficulty through an incremental/progressive manner. Our key innovation is that: instead of jointly outputting all object detections at once, for each frame we use a set of long-short term memory (LSTM) nodes to incrementally refine the detections. After passing through each LSTM node, more object detections are consolidated and thus more contextual information could be utilized to localize more difficult objects. The object parsing results are further utilized to form object specific action representation for fine grained action detection. Extensive experiments on two benchmark fine grained activity datasets demonstrate that our proposed algorithm achieves better interacting object detection performance, which in turn boosts the action recognition performance over the state-of-the-art.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"71 1","pages":"1020-1028"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73611077","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We present a new method for approximate nearest neighbour search on large datasets of high dimensional feature vectors, such as SIFT or GIST descriptors. Our approach constructs a directed graph that can be efficiently explored for nearest neighbour queries. Each vertex in this graph represents a feature vector from the dataset being searched. The directed edges are computed by exploiting the fact that, for these datasets, the intrinsic dimensionality of the local manifold-like structure formed by the elements of the dataset is significantly lower than the embedding space. We also provide an efficient search algorithm that uses this graph to rapidly find the nearest neighbour to a query with high probability. We show how the method can be adapted to give a strong guarantee of 100% recall where the query is within a threshold distance of its nearest neighbour. We demonstrate that our method is significantly more efficient than existing state of the art methods. In particular, our GPU implementation can deliver 90% recall for queries on a data set of 1 million SIFT descriptors at a rate of over 1.2 million queries per second on a Titan X. Finally we also demonstrate how our method scales to datasets of 5M and 20M entries.
{"title":"FANNG: Fast Approximate Nearest Neighbour Graphs","authors":"Ben Harwood, T. Drummond","doi":"10.1109/CVPR.2016.616","DOIUrl":"https://doi.org/10.1109/CVPR.2016.616","url":null,"abstract":"We present a new method for approximate nearest neighbour search on large datasets of high dimensional feature vectors, such as SIFT or GIST descriptors. Our approach constructs a directed graph that can be efficiently explored for nearest neighbour queries. Each vertex in this graph represents a feature vector from the dataset being searched. The directed edges are computed by exploiting the fact that, for these datasets, the intrinsic dimensionality of the local manifold-like structure formed by the elements of the dataset is significantly lower than the embedding space. We also provide an efficient search algorithm that uses this graph to rapidly find the nearest neighbour to a query with high probability. We show how the method can be adapted to give a strong guarantee of 100% recall where the query is within a threshold distance of its nearest neighbour. We demonstrate that our method is significantly more efficient than existing state of the art methods. In particular, our GPU implementation can deliver 90% recall for queries on a data set of 1 million SIFT descriptors at a rate of over 1.2 million queries per second on a Titan X. Finally we also demonstrate how our method scales to datasets of 5M and 20M entries.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"3 1","pages":"5713-5722"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75359725","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Over the past ten years, metric learning allowed the improvement of numerous machine learning approaches that manipulate distances or similarities. In this field, local metric learning has been shown to be very efficient, especially to take into account non linearities in the data and better capture the peculiarities of the application of interest. However, it is well known that local metric learning (i) can entail overfitting and (ii) face difficulties to compare two instances that are assigned to two different local models. In this paper, we address these two issues by introducing a novel metric learning algorithm that linearly combines local models (C2LM). Starting from a partition of the space in regions and a model (a score function) for each region, C2LM defines a metric between points as a weighted combination of the models. A weight vector is learned for each pair of regions, and a spatial regularization ensures that the weight vectors evolve smoothly and that nearby models are favored in the combination. The proposed approach has the particularity of working in a regression setting, of working implicitly at different scales, and of being generic enough so that it is applicable to similarities and distances. We prove theoretical guarantees of the approach using the framework of algorithmic robustness. We carry out experiments with datasets using both distances (perceptual color distances, using Mahalanobis-like distances) and similarities (semantic word similarities, using bilinear forms), showing that C2LM consistently improves regression accuracy even in the case where the amount of training data is small.
{"title":"Metric Learning as Convex Combinations of Local Models with Generalization Guarantees","authors":"Valentina Zantedeschi, R. Emonet, M. Sebban","doi":"10.1109/CVPR.2016.164","DOIUrl":"https://doi.org/10.1109/CVPR.2016.164","url":null,"abstract":"Over the past ten years, metric learning allowed the improvement of numerous machine learning approaches that manipulate distances or similarities. In this field, local metric learning has been shown to be very efficient, especially to take into account non linearities in the data and better capture the peculiarities of the application of interest. However, it is well known that local metric learning (i) can entail overfitting and (ii) face difficulties to compare two instances that are assigned to two different local models. In this paper, we address these two issues by introducing a novel metric learning algorithm that linearly combines local models (C2LM). Starting from a partition of the space in regions and a model (a score function) for each region, C2LM defines a metric between points as a weighted combination of the models. A weight vector is learned for each pair of regions, and a spatial regularization ensures that the weight vectors evolve smoothly and that nearby models are favored in the combination. The proposed approach has the particularity of working in a regression setting, of working implicitly at different scales, and of being generic enough so that it is applicable to similarities and distances. We prove theoretical guarantees of the approach using the framework of algorithmic robustness. We carry out experiments with datasets using both distances (perceptual color distances, using Mahalanobis-like distances) and similarities (semantic word similarities, using bilinear forms), showing that C2LM consistently improves regression accuracy even in the case where the amount of training data is small.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"162 1","pages":"1478-1486"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75937520","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
S. Fanello, Christoph Rhemann, V. Tankovich, Adarsh Kowdle, Sergio Orts, David Kim, S. Izadi
Structured light sensors are popular due to their robustness to untextured scenes and multipath. These systems triangulate depth by solving a correspondence problem between each camera and projector pixel. This is often framed as a local stereo matching task, correlating patches of pixels in the observed and reference image. However, this is computationally intensive, leading to reduced depth accuracy and framerate. We contribute an algorithm for solving this correspondence problem efficiently, without compromising depth accuracy. For the first time, this problem is cast as a classification-regression task, which we solve extremely efficiently using an ensemble of cascaded random forests. Our algorithm scales in number of disparities, and each pixel can be processed independently, and in parallel. No matching or even access to the corresponding reference pattern is required at runtime, and regressed labels are directly mapped to depth. Our GPU-based algorithm runs at a 1KHz for 1.3MP input/output images, with disparity error of 0.1 subpixels. We show a prototype high framerate depth camera running at 375Hz, useful for solving tracking-related problems. We demonstrate our algorithmic performance, creating high resolution real-time depth maps that surpass the quality of current state of the art depth technologies, highlighting quantization-free results with reduced holes, edge fattening and other stereo-based depth artifacts.
{"title":"HyperDepth: Learning Depth from Structured Light without Matching","authors":"S. Fanello, Christoph Rhemann, V. Tankovich, Adarsh Kowdle, Sergio Orts, David Kim, S. Izadi","doi":"10.1109/CVPR.2016.587","DOIUrl":"https://doi.org/10.1109/CVPR.2016.587","url":null,"abstract":"Structured light sensors are popular due to their robustness to untextured scenes and multipath. These systems triangulate depth by solving a correspondence problem between each camera and projector pixel. This is often framed as a local stereo matching task, correlating patches of pixels in the observed and reference image. However, this is computationally intensive, leading to reduced depth accuracy and framerate. We contribute an algorithm for solving this correspondence problem efficiently, without compromising depth accuracy. For the first time, this problem is cast as a classification-regression task, which we solve extremely efficiently using an ensemble of cascaded random forests. Our algorithm scales in number of disparities, and each pixel can be processed independently, and in parallel. No matching or even access to the corresponding reference pattern is required at runtime, and regressed labels are directly mapped to depth. Our GPU-based algorithm runs at a 1KHz for 1.3MP input/output images, with disparity error of 0.1 subpixels. We show a prototype high framerate depth camera running at 375Hz, useful for solving tracking-related problems. We demonstrate our algorithmic performance, creating high resolution real-time depth maps that surpass the quality of current state of the art depth technologies, highlighting quantization-free results with reduced holes, edge fattening and other stereo-based depth artifacts.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"33 1","pages":"5441-5450"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73853615","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：