ECCV 2020 论文列表

Topology change is a challenging problem for 4D reconstruction of dynamic scenes. In the classic volumetric fusion-based framework, a mesh is usually extracted from the TSDF volume as the canonical surface representation to help estimating deformation field. However, the surface and Embedded Deformation Graph (EDG) representations bring conflicts under topology changes since the surface mesh has fixed-connectivity but the deformation field can be discontinuous. In this paper, the classic framework is re-designed to enable 4D reconstruction of dynamic scene under topology changes, by introducing a novel structure of Non-manifold Volumetric Grid to the re-design of both TSDF and EDG, which allows connectivity updates by cell splitting and replication. Experiments show convincing reconstruction results for dynamic scenes of topology changes, as compared to the state-of-the-art methods."

Existing generative adversarial networks (GANs) focus on generating realistic images based on CNN-derived image features, but fail to preserve the structural properties of real images. This can be fatal in applications where the underlying structure (e.g., neurons, vessels, membranes, and road networks) of the image carries crucial semantic meaning. In this paper, we propose a novel GAN model that learns the topology of real images, i.e., connectedness and loopy-ness. In particular, we introduce a new loss that bridges the gap between synthetic image distribution and real image distribution in the topological feature space. By optimizing this loss, the generator produces images with the same structural topology as real images. We also propose new GAN evaluation metrics that measure the topological realism of the synthetic images. We show in experiments that our method generates synthetic images with realistic topology. We also highlight the increased performance that our method brings to downstream tasks such as segmentation."

Most state-of-the-art approaches to road extraction from aerial images rely on a CNN trained to label road pixels as foreground and remainder of the image as background. The CNN is usually trained by minimizing pixel-wise losses, which is less than ideal to produce binary masks that preserve the road network's global connectivity. To address this issue, we introduce an Adversarial Learning (AL) strategy tailored for our purposes. A naive one would treat the segmentation network as a generator and would feed its output along with ground-truth segmentations to a discriminator. It would then train the generator and discriminator jointly. We will show that this is not enough because it does not capture the fact that most errors are local and need to be treated as such. Instead, we use a more sophisticated discriminator that returns a label pyramid describing what portions of the road network are correct at several different scales. This discriminator and the structured labels it returns are what gives our approach its edge and we will show that it outperforms state-of-the-art ones on the challenging RoadTracer dataset."

As realistic facial manipulation technologies have achieved remarkable progress, social concerns about potential malicious abuse of these technologies bring out an emerging research topic of face forgery detection. However, it is extremely challenging since recent advances are able to forge faces beyond the perception ability of human eyes, especially in compressed images and videos. We find that mining forgery patterns with the awareness of frequency could be a cure, as frequency provides a complementary viewpoint where either subtle forgery artifacts or compression errors could be well described. To introduce frequency into the face forgery detection, we propose a novel Frequency in Face Forgery Network (F$^3$-Net), taking advantages of two different but complementary frequency-aware clues, 1) frequency-aware decomposed image components, and 2) local frequency statistics, to deeply mine the forgery patterns via our two-stream collaborative learning framework. We apply DCT as the applied frequency-domain transformation. Through comprehensive studies, we show that the proposed F$^3$-Net significantly outperforms competing state-of-the-art methods on all compression qualities in the challenging FaceForensics++ dataset, especially wins a big lead upon low-quality media."

Realtime perceptual and interaction capabilities in mixed reality require a range of 3D tracking problems to be solved at low latency on resource-constrained hardware such as head-mounted devices. Indeed, for devices such as HoloLens 2 where the CPU and GPU are left available for applications, multiple tracking subsystems are required to run on a continuous, real-time basis while sharing a single Digital Signal Processor. To solve model-fitting problems for HoloLens 2 hand tracking, where the computational budget is approximately 100 times smaller than an iPhone 7, we introduce a new surface model: the `Phong surface'. Using ideas from computer graphics, the Phong surface describes the same 3D shape as a triangulated mesh model, but with continuous surface normals which enable the use of lifting-based optimization, providing significant efficiency gains over ICP-based methods. We show that Phong surfaces retain the convergence benefits of smoother surface models, while triangle meshes do not."

Traffic signs are essential map features for smart cities and navigation. To develop accurate and robust algorithms for traffic sign detection and classification, a large-scale and diverse benchmark dataset is required. In this paper, we introduce a new traffic sign dataset of 105K street-level images around the world covering 400 manually annotated traffic sign classes in diverse scenes, wide range of geographical locations, and varying weather and lighting conditions. The dataset includes 52K fully annotated images. Additionally, we show how to augment the dataset with 53K semi-supervised, partially annotated images. This is the largest and the most diverse traffic sign dataset consisting of images from all over the world with fine-grained annotations of traffic sign classes. We run extensive experiments to establish strong baselines for both detection and classification tasks. In addition, we verify that the diversity of this dataset enables effective transfer learning for existing large-scale benchmark datasets on traffic sign detection and classification. The dataset is freely available for academic research at https://www.mapillary.com/dataset/trafficsign."

Existing popular methods for disentanglement rely on hand-picked priors and complex encoder-based architectures. In this paper, we propose the Hessian Penalty, a simple regularization function that encourages the input Hessian of a function to be diagonal. Our method is completely model-agnostic and can be applied to any deep generator with just a few lines of code. We show that our method automatically uncovers meaningful factors of variation in the standard basis when applied to ProgressiveGAN across several datasets. Additionally, we demonstrate that our regularization term can be used to identify interpretable directions in BigGAN's latent space in a fully unsupervised fashion. Finally, we provide provide empirical evidence that our regularization term encourages sparsity when applied to overparameterized latent spaces."

Deep metric learning has yielded impressive results in tasks such as clustering and image retrieval by leveraging neural networks to obtain highly discriminative feature embeddings, which can be used to group samples into different classes. Much research has been devoted to the design of smart loss functions or data mining strategies for training such networks. Most methods consider only pairs or triplets of samples within a mini-batch to compute the loss function, which is commonly based on the distance between embeddings. We propose Group Loss, a loss function based on a differentiable label-propagation method that enforces embedding similarity across all samples of a group while promoting, at the same time, low-density regions amongst data points belonging to different groups. Guided by the smoothness assumption that ``""similar objects should belong to the same group"", the proposed loss trains the neural network for a classification task, enforcing a consistent labelling amongst samples within a class. We show state-of-the-art results on clustering and image retrieval on several datasets, and show the potential of our method when combined with other techniques such as ensembles."

In recent years, the research community has approached the problem of vehicle re-identification (re-id) with attention-based models, specifically focusing on regions of a vehicle containing discriminative information. These re-id methods rely on expensive key-point labels, part annotations, and additional attributes including vehicle make, model, and color. Given the large number of vehicle re-id datasets with various levels of annotations, strongly-supervised methods are unable to scale across different domains. In this paper, we present Self-supervised Attention for Vehicle Re-identification (SAVER), a novel approach to effectively learn vehicle-specific discriminative features. Through extensive experimentation, we show that SAVER improves upon the state-of-the-art on challenging VeRi, VehicleID, Vehicle-1M and VERI-Wild datasets. "

Most existing object instance detection and segmentation models only work well on fairly balanced benchmarks where per-category training sample numbers are comparable, such as COCO. They tend to suffer performance drop on realistic datasets that are usually long-tailed. This work aims to study and address such open challenges. Specifically, we systematically investigate performance drop of the state-of-the-art two-stage instance segmentation model Mask R-CNN on the recent long-tail LVIS dataset, and unveil that a major cause is the inaccurate classification of object proposals. Based on such an observation, we first consider various techniques for improving long-tail classification performance which indeed enhance instance segmentation results. We then propose a simple calibration framework to more effectively alleviate classification head bias with a bi-level class balanced sampling approach. Without bells and whistles, it significantly boosts the performance of instance segmentation for tail classes on the recent LVIS dataset and our sampled COCO-LT dataset. Our analysis provides useful insights for solving long-tail instance detection and segmentation problems, and the straightforward mph{SimCal} method can serve as a simple but strong baseline. With the method we have won the 2019 LVIS challenge. Codes and models are available at \url{https://github.com/twangnh/SimCal}. "

We introduce the Average Mixing Kernel Signature (AMKS), a novel signature for points on non-rigid three-dimensional shapes based on the average mixing kernel and continuous-time quantum walks. The average mixing kernel holds information on the average transition probabilities of a quantum walk between each pair of vertices of the mesh until a time $T$. We define the AMKS by decomposing the spectral contributions of the kernel into several bands, allowing us to limit the influence of noise-dominated high-frequency components and obtain a more descriptive signature. We also show through a perturbation theory analysis of the kernel that choosing a finite stopping time $T$ leads to noise and deformation robustness for the AMKS. We perform an extensive experimental evaluation on two widely used shape matching datasets under varying level of noise, showing that the AMKS outperforms two state-of-the-art descriptors, namely the Heat Kernel Signature (HKS) and the similarly quantum-walk based Wave Kernel Signature (WKS)."

Convolutional neural networks (CNNs) introduce state-of-the-art results for various tasks with the price of high computational demands. Inspired by the observation that spatial correlation exists in CNN output feature maps (ofms), we propose a method to dynamically predict whether ofm activations are zero-valued or not according to their neighboring activation values, thereby avoiding zero-valued activations and reducing the number of convolution operations. We implement the zero activation predictor (ZAP) with a lightweight CNN, which imposes negligible overheads and is easy to deploy on existing models. ZAPs are trained by mimicking hidden layer ouputs; thereby, enabling a parallel and label-free training. Furthermore, without retraining, each ZAP can be tuned to a different operating point trading accuracy for MAC reduction."

We aim to super-resolve digital paintings, synthesizing realistic details from high-resolution reference painting materials for very large scaling factors (g 8$ imes$, 16$ imes$). However, previous single image super-resolution (SISR) methods would either lose textural details or introduce unpleasing artifacts. On the other hand, reference-based SR (Ref-SR) methods can transfer textures to some extent, but is still impractical to handle very large factors and keep fidelity with original input. To solve these problems, we propose an efficient high-resolution hallucination network for very large scaling factors with efficient network structure and feature transferring. To transfer more detailed textures, we design a wavelet texture loss, which helps to enhance more high-frequency components. At the same time, to reduce the smoothing effect brought by the image reconstruction loss, we further relax the reconstruction constraint with a degradation loss which ensures the consistency between downscaled super-resolution results and low-resolution inputs. We also collected a high-resolution (g 4K resolution) painting dataset PaintHD by considering both physical size and image resolution. We demonstrate the effectiveness of our method with extensive experiments on PaintHD by comparing with SISR and Ref-SR state-of-the-art methods."

Image descriptions can help visually impaired people to quickly understand the image content. While we made significant progress in automatically describing images and optical character recognition, current approaches are unable to include written text in their descriptions, although text is omnipresent in human environments and frequently critical to understand our surroundings. To study how to comprehend text in the context of an image we collect a novel dataset, TextCaps, with 145k captions for 28k images. Our dataset challenges a model to recognize text, relate it to its visual context, and decide what part of the text to copy or paraphrase, requiring spatial, semantic, and visual reasoning between multiple text tokens and visual entities, such as objects. We study baselines and adapt existing approaches to this new task, which we refer to as image captioning with reading comprehension. Our analysis with automatic and human studies shows that our new TextCaps dataset provides many new technical challenges over previous datasets."

We present TexMesh, a novel approach to reconstruct detailed human meshes with high-resolution full-body texture from RGB-D video. TexMesh enables high quality free-viewpoint rendering of humans. Given the RGB frames, the captured environment map, and the coarse per-frame human mesh from RGB-D tracking, our method reconstructs spatiotemporally consistent and detailed per-frame meshes along with a high-resolution albedo texture. By using the incident illumination we are able to accurately estimate local surface geometry and albedo, which allows us to further use photometric constraints to adapt a synthetically trained model to real-world sequences in a self-supervised manner for detailed surface geometry and high-resolution texture estimation. In practice, we train our models on a short example sequence for self-adaptation and the model runs at interactive framerate afterwards. We validate TexMesh on synthetic and real-world data, and show it outperforms the state of art quantitatively and qualitatively."

We present a novel method for testing the safety of self-driving vehicles in simulation. We propose an alternative to sensor simulation, as sensor simulation is expensive and has large domain gaps. Instead, we directly simulate the outputs of the self-driving vehicle’s perception and prediction system, enabling realistic motion planning testing. Specifically, we use paired data in the form of ground truth labels and real perception and prediction outputs to train a model that predicts what the online system will produce. Importantly, the inputs to our system consists of high definition maps, bounding boxes, and trajectories, which can be easily sketched by a test engineer in a matter of minutes. This makes our approach a much more scalable solution. Quantitative results on two large-scale datasets demonstrate that we can realistically test motion planning using our simulations"

Context information plays an indispensable role in the success of semantic segmentation. Recently, non-local self-attention based methods are proved to be effective for context information collection. Since desired context consists of spatial-wise and channel-wise attentions, the 3D representation is an appropriate formulation. However, these non-local methods describe 3D context information based on a 2D similarity matrix, where space compression may lead to channel-wise attention missing. An alternative is to model the contextual information directly without compression. However, this effort confronts a fundamental difficulty, namely the high-rank property of context information. In this paper, we propose a new approach to model the 3D context representations,which not only avoids the space compression, but also tackles the high-rank difficulty. Here, inspired by tensor canonical-polyadic decomposition theory (i.e, a high-rank tensor can be expressed as a combination of rank-1 tensors.), we design a low-rank-to-high-rank con-text reconstruction framework (i.e., RecoNet). Specifically, we first introduce the tensor generation module (TGM), which generates a number of rank-1 tensors to capture fragments of context feature. Then we use these rank-1 tensors to recover the high-rank context features through our proposed tensor reconstruction module (TRM). Extensive experiments show that our method achieves state-of-the-art on various public datasets. Additionally, our proposed method has more than 100 times less computational cost compared with conventional non-local-based methods."

Multi-person pose estimation and tracking in realistic videos is very challenging due to factors such as occlusions, fast motion and pose variations. Top-down approaches are commonly used for this task, which involves three stages: person detection, single-person pose estimation, and pose association across time. Recently, significant progress has been made in person detection and single-person pose estimation. In this paper, we mainly focus on improving pose association and estimation in a video to build a strong pose estimator and tracker. To this end, we propose a novel temporal keypoint matching and refinement network. Specifically, we propose two network modules, temporal keypoint matching and temporal keypoint refinement, which are incorporated into a single-person pose estimatin network. The temporal keypoint matching module learns a simialrity metric for matching keypoints across frames. Pose matching is performed by aggregating keypoint similarities between poses in adjacent frames. The temporal keypoint refinement module serves to correct individual poses by utilizing their associated poses in neighboring frames as temporal context. We validate the effectiveness of our proposed network on two benchmark datasets: PoseTrack 2017 and PoseTrack 2018. Exprimental results show that our approach achieves state-of-the-art performance on both datasets."

Motivated by the previous success of Two-Dimensional Convolutional Neural Network (2D CNN) on image recognition, researchers endeavor to leverage it to characterize videos. However, one limitation of applying 2D CNN to analyze videos is that different frames of a video share the same 2D CNN kernels, which may result in repeated and redundant information utilization, especially in the spatial semantics extraction process, hence neglecting the critical variations among frames. In this paper, we attempt to tackle this issue through two ways. 1) Design a sequential channel filtering mechanism, Progressive Enhancement Module (PEM), to excite the discriminative channels of features from different frames step by step, and thus avoid repeated information extraction. 2) Create a Temporal Diversity Loss (TD Loss) to force the kernels to concentrate on and capture the variations among frames rather than the image regions with similar appearance. Our method is evaluated on the temporal reasoning datasets Something-Something V1 and V2, and it achieves visible improvements against the best competitor by 2.4% and 1.3%. Besides, performance improvements over the 2D-CNN-based state-of-the-arts on the large-scale dataset Kinetics are also witnessed."