Author
Luc Van Gool
Other affiliations: Microsoft, ETH Zurich, Politehnica University of Timișoara ...read more
Bio: Luc Van Gool is an academic researcher from Katholieke Universiteit Leuven. The author has contributed to research in topics: Computer science & Object detection. The author has an hindex of 133, co-authored 1307 publications receiving 107743 citations. Previous affiliations of Luc Van Gool include Microsoft & ETH Zurich.
Papers published on a yearly basis
Papers
More filters
••
14 Jun 2020
TL;DR: In this article, the authors leverage the powerful lossy image compression algorithm BPG to build a lossless image compression system, where the original image is first decomposed into the lossy reconstruction obtained after compressing it with BPG and the corresponding residual.
Abstract: We leverage the powerful lossy image compression algorithm BPG to build a lossless image compression system. Specifically, the original image is first decomposed into the lossy reconstruction obtained after compressing it with BPG and the corresponding residual. We then model the distribution of the residual with a convolutional neural network-based probabilistic model that is conditioned on the BPG reconstruction, and combine it with entropy coding to losslessly encode the residual. Finally, the image is stored using the concatenation of the bitstreams produced by BPG and the learned residual coder. The resulting compression system achieves state-of-the-art performance in learned lossless full-resolution image compression, outperforming previous learned approaches as well as PNG, WebP, and JPEG2000.
31 citations
••
15 Jun 2019TL;DR: Wang et al. as mentioned in this paper proposed a 3D appearance super-resolution (3DASR) dataset based on the existing ETH3D [42], SyB3R [31], MiddleBury, and our Collection of 3D scenes from TUM [21], Fountain [51] and Relief [53].
Abstract: We tackle the problem of retrieving high-resolution (HR) texture maps of objects that are captured from multiple view points. In the multi-view case, model-based super-resolution (SR) methods have been recently proved to recover high quality texture maps. On the other hand, the advent of deep learning-based methods has already a significant impact on the problem of video and image SR. Yet, a deep learning-based approach to super-resolve the appearance of 3D objects is still missing. The main limitation of exploiting the power of deep learning techniques in the multi-view case is the lack of data. We introduce a 3D appearance SR (3DASR) dataset based on the existing ETH3D [42], SyB3R [31], MiddleBury, and our Collection of 3D scenes from TUM [21], Fountain [51] and Relief [53]. We provide the high- and low-resolution texture maps, the 3D geometric model, images and projection matrices. We exploit the power of 2D learning-based SR methods and design networks suitable for the 3D multi-view case. We incorporate the geometric information by introducing normal maps and further improve the learning process. Experimental results demonstrate that our proposed networks successfully incorporate the 3D geometric information and super-resolve the texture maps.
30 citations
••
01 Jan 2011TL;DR: A new multi-class version of transfer learning which requires minimal human interaction but still provides semantic labels of the new classes is developed, which is based on human tracking with multiple activity trackers.
Abstract: One of the great open challenges in visual recognition is the ability to cope with unexpected stimuli. In this work, we present a technique to interpret detected anomalies and update the existing knowledge of normal situations. The addressed context is the analysis of human behavior in indoor surveillance scenarios, where new activities might need to be learned, once the system is already in operation. Our approach is based on human tracking with multiple activity trackers. The main contribution is to integrate a learning stage, where labeled and unlabeled information is collected and analyzed. To this end we develop a new multi-class version of transfer learning which requires minimal human interaction but still provides semantic labels of the new classes. The activity model is then updated with the new activities. Experiments show promising results.
30 citations
••
11 Dec 2017TL;DR: A pipeline that enables multiple users to collaboratively acquire images with monocular smartphones and derive a 3D point cloud using a remote reconstruction server and on-the-fly feedback to the user to be generated about current reconstruction progress is presented.
Abstract: This article presents a pipeline that enables multiple users to collaboratively acquire images with monocular smartphones and derive a 3D point cloud using a remote reconstruction server. A set of key images are automatically selected from each smartphone's camera video feed as multiple users record different viewpoints of an object, concurrently or at different time instants. Selected images are automatically processed and registered with an incremental Structure from Motion (SfM) algorithm in order to create a 3D model. Our incremental SfM approach enables on-the-fly feedback to the user to be generated about current reconstruction progress. Feedback is provided in the form of a preview window showing the current 3D point cloud, enabling users to see if parts of a surveyed scene need further attention/coverage whilst they are still in situ. We evaluate our 3D reconstruction pipeline by performing experiments in uncontrolled and unconstrained real-world scenarios. Datasets are publicly available.
30 citations
••
23 Jun 2013TL;DR: This work proposes a novel procedural modelling method to automatically learn a grammar from a set of facades, generate new facade instances and compare facades and demonstrates its automatic rule inference on datasets of two different architectural styles.
Abstract: Urban models are key to navigation, architecture and entertainment. Apart from visualizing facades, a number of tedious tasks remain largely manual (e.g. compression, generating new facade designs and structurally comparing facades for classification, retrieval and clustering). We propose a novel procedural modelling method to automatically learn a grammar from a set of facades, generate new facade instances and compare facades. To deal with the difficulty of grammatical inference, we reformulate the problem. Instead of inferring a compromising, one-size-fits-all, single grammar for all tasks, we infer a model whose successive refinements are production rules tailored for each task. We demonstrate our automatic rule inference on datasets of two different architectural styles. Our method supercedes manual expert work and cuts the time required to build a procedural model of a facade from several days to a few milliseconds.
30 citations
Cited by
More filters
••
27 Jun 2016TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Abstract: Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers—8× deeper than VGG nets [40] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions1, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.
123,388 citations
•
04 Sep 2014TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Abstract: In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.
55,235 citations
•
01 Jan 2015TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Abstract: In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.
49,914 citations
•
TL;DR: This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.
Abstract: Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers---8x deeper than VGG nets but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers.
The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.
44,703 citations
••
07 Jun 2015TL;DR: Inception as mentioned in this paper is a deep convolutional neural network architecture that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14).
Abstract: We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.
40,257 citations