ECCV 2020 Papers

Spiking Neural Networks (SNNs) are promising for enabling low-power event-driven data analytics. The best performing SNNs for image recognition tasks are obtained by converting a trained deep learning Analog Neural Network (ANN) composed of Rectified Linear Unit (ReLU) activation to SNN consisting of Integrate-and-Fire (IF) neurons with ""proper"" firing thresholds. However, this has come at the cost of accuracy loss and higher inference latency due to lack of a notion of time. In this work, we propose an ANN to SNN conversion methodology that uses a time-based coding scheme, named Temporal-Switch-Coding (TSC), and a corresponding TSC spiking neuron model. Each input image pixel is presented using two spikes and the timing between the two spiking instants is proportional to the pixel intensity. The real-valued ReLU activations in ANN are encoded using the spike-times of the TSC neurons in the converted TSC-SNN. At most two memory accesses and two addition operations are performed for each synapse during the whole inference, which significantly improves the SNN energy efficiency. We demonstrate the proposed TSC-SNN for VGG-16, ResNet-20 and ResNet-34 SNNs on datasets including CIFAR-10 (93.63% top-1), CIFAR-100 (70.97% top-1) and ImageNet (73.46% top-1 accuracy). It surpasses the best inference accuracy of the converted rate-encoded SNN with 7-14.5 times lesser inference latency, and 30-60 times fewer addition operations and memory accesses per inference across datasets."

Coded aperture is a promising approach for capturing the 4-D light field (LF), in which the 4-D data are compressively modulated into 2-D coded measurements that are further decoded by reconstruction algorithms. The bottleneck lies in the reconstruction algorithms, resulting in rather limited reconstruction quality. To tackle this challenge, we propose a novel learning-based framework for the reconstruction of high-quality LFs from acquisitions via learned coded apertures. The proposed method incorporates the measurement observation into the deep learning framework elegantly to avoid relying entirely on data-driven priors for LF reconstruction. Specifically, we first formulate the compressive LF reconstruction as an inverse problem with an implicit regularization term. Then, we construct the regularization term with an efficient deep spatial-angular convolutional sub-network to comprehensively explore the signal distribution free from the limited representation ability and inefficiency of deterministic mathematical modeling. Experimental results show that the reconstructed LFs not only achieve much higher PSNR/SSIM but also preserve the LF parallax structure better, compared with state-of-the-art methods on both real and synthetic LF benchmarks. In addition, experiments show that our method is efficient and robust to noise, which is an essential advantage for a real camera system. The code is publicly available at https://github.com/angmt2008/LFCA."

Video super-resolution (VSR) and frame interpolation (FI) are traditional computer vision problems, and the performance have been improving by incorporating deep learning recently. In this paper, we investigate the problem of jointly upsampling videos both in space and time, which is becoming more important with advances in display systems. One solution for this is to run VSR and FI, one by one, independently. This is highly inefficient as heavy deep neural networks (DNN) are involved in each solution. To this end, we propose an end-to-end DNN framework for the space-time video upsampling by efficiently merging VSR and FI into a joint framework. In our framework, a novel weighting scheme is proposed to fuse input frames effectively without explicit motion compensation for efficient processing of videos. The results show better results both quantitatively and qualitatively, while reducing the computation time (x7 faster) and the number of parameters (30%) compared to baselines. Our source code is available at https://github.com/JaeYeonKang/STVUN-Pytorch."

This paper makes a first attempt to bring the Shape from Polarization (SfP) problem to the realm of deep learning. The previous state-of-the-art methods for SfP have been purely physics-based. We see value in these principled models, and blend these physical models as priors into a neural network architecture. This proposed approach achieves results that exceed the previous state-of-the-art on a challenging dataset we introduce. This dataset consists of polarization images taken over a range of object textures, paints, and lighting conditions. We report that our proposed method achieves the lowest test error on each tested condition in our dataset, showing the value of blending data-driven and physics-driven approaches. "

In this paper, we build upon the weakly-supervised generation mechanism of intermediate attention maps in any convolutional neural networks and disclose the effectiveness of attention modules more straightforwardly to fully exploit their potential. Given an existing neural network equipped with arbitrary attention modules, we introduce a meta critic network to evaluate the quality of attention maps in the main network. Due to the discreteness of our designed reward, the proposed learning method is arranged in a reinforcement learning setting, where the attention actors and recurrent critics are alternately optimized to provide instant critique and revision for the temporary attention representation, hence coined as Deep REinforced Attention Learning (DREAL). It could be applied universally to network architectures with different types of attention modules and promotes their expressive ability by maximizing the relative gain of the final recognition performance arising from each individual attention module, as demonstrated by extensive experiments on both category and instance recognition benchmarks."

We present a deep learning approach to reconstruct scene appearance from unstructured images captured under collocated point lighting. At the heart of Deep Reflectance Volumes is a novel volumetric scene representation consisting of opacity, surface normal and reflectance voxel grids. We present a novel physically-based differentiable volume ray marching framework to render these scene volumes under arbitrary viewpoint and lighting. This allows us to optimize the scene volumes to minimize the error between their rendered images and the captured images. Our method is able to reconstruct real scenes with challenging non-Lambertian reflectance and complex geometry with occlusions and shadowing. Moreover, it accurately generalizes to novel viewpoints and lighting, including non-collocated lighting, rendering photorealistic images that are significantly better than state-of-the-art mesh-based methods. We also show that our learned reflectance volumes are editable, allowing for modifying the materials of the captured scenes."

In this paper we propose a rotation-invariant deep network for point clouds analysis. Point-based deep networks are commonly designed to recognize roughly aligned 3D shapes based on point coordinates, but suffer from performance drops with shape rotations. Some geometric features, e.g., distances and angles of points as inputs of network, are rotation-invariant but lose positional information of points. In this work, we propose a novel deep network for point clouds by incorporating positional information of points as inputs while yielding rotation-invariance. The network is hierarchical and relies on two modules: a positional feature embedding block and a relational feature embedding block. Both modules and the whole network are proven to be rotation-invariant when processing point clouds as input. Experiments show state-of-the-art classification and segmentation performances on benchmark datasets, and ablation studies demonstrate effectiveness of the network design."

Sketch-based image editing aims to synthesize and modify photos based on the structural information provided by the human-drawn sketches. Since sketches are difficult to collect, previous methods mainly use edge maps instead of sketches to train models (referred to as edge-based models). However, human-drawn sketches display great structural discrepancy with edge maps, thus failing edge-based models. Moreover, sketches often demonstrate huge variety among different users, demanding even higher generalizability and robustness for the editing model to work. In this paper, we propose Deep Plastic Surgery, a novel, robust and controllable image editing framework that allows users to interactively edit images using hand-drawn sketch inputs. We present a sketch refinement strategy, as inspired by the coarse-to-fine drawing process of the artists, which we show can help our model well adapt to casual and varied sketches without the need for real sketch training data. Our model further provides a refinement level control parameter that enables users to flexibly define how ``reliable'' the input sketch should be considered for the final output, balancing between sketch faithfulness and output verisimilitude (as the two goals might contradict if the input sketch is drawn poorly). To achieve the multi-level refinement, we introduce a style-based module for level conditioning, which allows adaptive feature representations for different levels in a singe network. Extensive experimental results demonstrate the superiority of our approach in improving the visual quality and user controllablity of image editing over the state-of-the-art methods. "

We propose a new deep neural network which takes a colored 3D point cloud of a scene, and directly synthesizes a photo-realistic image from an arbitrary viewpoint. Key contributions of this work include a deep point feature extraction module, an image synthesis module, and an image refinement module. Our PointEncoder network extracts discriminative features from the point cloud that contain both local and global contextual information about the scene. Next, the multi-level point features are aggregated to form multi-layer feature maps. These are fed into our ImageDecoder network in order to generate a synthetic RGB image. Finally, the coarse output of the ImageDecoder network is refined using our RefineNet module, supplying more fine details and suppressing unwanted visual artifacts. To generate virtual camera viewpoints in the scene, we rotate and translate the 3D point cloud in order to synthesize new images from novel perspectives. We conduct numerous experiments on public datasets to validate our method, with respect to the quality of the synthesized views, and outperform state-of-the-art significantly."

We propose a learning-based approach for novel view synthesis for multi-camera 360$^

Light-field cameras capture sub-views from multiple perspectives simultaneously, with possibly reflectance variations that can be used to augment material recognition in remote sensing, autonomous driving, etc. Existing approaches for light-field based material recognition suffer from the entanglement between angular and spatial domains, leading to inefficient training which in turn limits their performances. In this paper, we propose an approach that achieves decoupling of angular and spatial information by establishing correspondences in the angular domain, then employs regularization to enforce a rotational invariance. As opposed to relying on the Lambertian surface assumption, we align the angular domain by estimating sub-pixel displacements using the Fourier transform. The network takes sparse inputs, i.e. sub-views along particular directions, to gain structural information about the angular domain. A novel regularization technique further improves generalization by weight sharing and max-pooling among different directions. The proposed approach outperforms any previously reported method on multiple datasets. The accuracy gain over 2D images is improved by a factor of 1.5. Extensive ablation studies are conducted to demonstrate the significance of each component."

Efficiently reconstructing complex and intricate surfaces at scale is a long-standing goal in machine perception. To address this problem we introduce Deep Local Shapes (DeepLS), a deep shape representation that enables high-quality 3D shape representation without prohibitive memory requirements. DeepLS replaces the dense volumetric signed distance function (SDF) representation used in traditional surface reconstruction systems with a learned continuous SDF defined by a neural network, inspired by recent work such as DeepSDF. Unlike DeepSDF, which represents an object-level SDF with a neural network and a single latent code, we store a grid of independent latent codes, each responsible for storing information about surfaces in a small local neighborhood. This decomposition of scenes into local shapes simplifies the prior distribution that the network must learn, and also enables efficient inference. %We enforce global shape consistency implicitly by fitting local shape codes from an receptive field that overlaps with neighboring voxels. We demonstrate the effectiveness and generalization power of DeepLS by showing object shape encoding and reconstructions of full scenes, where DeepLS delivers high compression, accuracy, and local shape completion."

In augmented reality (AR) or virtual reality (VR) systems, eye tracking is a key technology and requires significant accuracy as well as real-time operation. Many techniques for detecting pupil centers with error range of iris radius have been developed, but few techniques have precise performance with error range of pupil radius. In addition, the conventional methods rarely guarantee real-time pupil center detection in a general-purpose computer environment due to high complexity. Thus, we propose more accurate pupil center detection by improving the representation quality of the network in charge of pupil center detection. This is realized by representation learning based on mutual information. Also, the latency of the entire system is greatly reduced by using non-local block and self-attention block with large receptive field, which makes it accomplish real-time operation. The proposed system not only shows real-time performance of 52 FPS in a general-purpose computer environment but also provides state-of-the-art accuracy in terms of fine level index of 96.71%, 99.84% and 96.38% for BioID, GI4E and Talking Face Video datasets, respectively."

We present a Deep Image Compression neural network that relies on side information, which is only available to the decoder. We base our algorithm on the assumption that the image available to the encoder and the image available to the decoder are correlated, and we let the network learn these correlations in the training phase.

Deep clustering which adopts deep neural networks to obtain optimal representations for clustering has been widely studied recently. In this paper, we propose a novel deep image clustering framework to learn a category-style latent representation in which the category information is disentangled from image style and can be directly used as the cluster assignment. To achieve this goal, mutual information maximization is applied to embed relevant information in the latent representation. Moreover, augmentation-invariant loss is employed to disentangle the representation into category part and style part. Last but not least, a prior distribution is imposed on the latent representation to ensure the elements of the category vector can be used as the probabilities over clusters. Comprehensive experiments demonstrate that the proposed approach outperforms state-of-the-art methods significantly on five public datasets."

Classical work on line segment detection is knowledge-based; it uses carefully designed geometric priors using either image gradients, pixel groupings, or Hough transform variants. Instead, current deep learning methods do away with all prior knowledge and replace priors by training deep networks on large manually annotated datasets. Here, we reduce the dependency on labeled data by building on the classic knowledge-based priors while using deep networks to learn features. We add line priors through a trainable Hough transform block into a deep network. Hough transform provides the prior knowledge about global line parameterizations, while the convolutional layers can learn the local gradient-like line features. On the Wireframe (ShanghaiTech) and York Urban datasets we show that adding prior knowledge improves data efficiency as line priors no longer need to be learned from data."

In this paper, we put forward a simple yet effective method to detect meaningful straight lines, a.k.a. semantic lines, in given scenes. Prior methods take line detection as a special case of object detection, while neglect the inherent characteristics of lines, leading to less efficient and suboptimal results. We propose a one-shot end-to-end framework by incorporating the classical Hough transform into deeply learned representations. By parameterizing lines with slopes and biases, we perform Hough transform to translate deep representations to the parametric space and then directly detect lines in the parametric space. More concretely, we aggregate features along candidate lines on the feature map plane and then assign the aggregated features to corresponding locations in the parametric domain. Consequently, the problem of detecting semantic lines in the spatial domain is transformed to spotting individual points in the parametric domain, making the post-processing steps, i.e. non-maximal suppression, more efficient. Furthermore, our method makes it easy to extract contextual line features, that are critical to accurate line detection. Experimental results on a public dataset demonstrate the advantages of our method over state-of-the-arts. Code and models will be publicly released."

n this paper, we propose a Deep Hashing method with Active Pairwise Supervision(DH-APS). Conventional methods with passive pairwise supervision obtain labeled data for training and require large amount of annotations to reach their full potential, which are not feasible in realistic retrieval tasks. On the contrary, we actively select a small quantity of informative samples for annotation to provide effective pairwise supervision so that discriminative hash codes can be obtained with limited annotation budget. Specifically, we generalize the structural risk minimization principle and obtain three criteria for the pairwise supervision acquisition: uncertainty, representativeness and diversity. Accordingly, samples involved in the following training pairs should be labeled: pairs with most uncertain similarity, pairs that minimize the discrepancy between labeled and unlabeled data, and pairs which are most different from the annotated data, so that the discriminality and generalization ability of the learned hash codes are significantly strengthened. Moreover, our DH-APS can also be employed as a plug-and-play module for semi-supervised hashing methods to further enhance the performance. Experiments demonstrate that the presented DH-APS achieves the accuracy of supervised hashing methods with only $30\%$ labeled training samples and improves the semi-supervised binary codes by a sizable margin."

Building on recent progress at the intersection of combinatorial optimization and deep learning, we propose an end-to-end trainable architecture for deep graph matching that contains unmodified combinatorial solvers. Using the presence of heavily optimized combinatorial solvers together with some improvements in architecture design, we advance state-of-the-art on deep graph matching benchmarks for keypoint correspondence. In addition, we highlight conceptual advantages of incorporating solvers into deep learning architectures, such as the possibility of post-processing with a strong multi-graph matching solver or the indifference to changes in the training setting. Finally, we propose two new challenging experimental setups."