ECCV 2020 Papers

Point cloud shape completion is a challenging problem in 3D vision and robotics. Existing learning-based frameworks leverage encoder-decoder architectures to recover the complete shape from a compactly encoded global feature vector. Though the global feature can approximately represent the overall latent shape, it discards some details of the original partial shape during the completion process. In this work, instead of using a global feature to recover the whole complete surface, we explore multi-level features by hierarchical feature learning and represent the existing-part and the missing-part respectively. We propose two different feature aggregation strategies, named global & local feature aggregation(GLFA) and residual feature aggregation(RFA), to express the two parts features and reconstruct coordinates from the combined features. In addition, we also design a refinement component to prevent the generated point from non-uniform distribution and outliers. Extensive experiments have been conducted on the ShapeNet and KITTI dataset. Qualitative and quantitative evaluations demonstrate that our proposed network is more capable of both preserving the original details."

We consider universal adversarial patches for faces --- small visual elements whose addition to a face image reliably destroys the performance of face detectors. Unlike previous work that mostly focused on the algorithmic design of adversarial examples in terms of improving the success rate as an attacker, in this work we show an interpretation of such patches that can prevent the state-of-the-art face detectors from detecting the real faces. We investigate a phenomenon: patches designed to suppress real face detection appear face-like. This phenomenon holds generally across different initialization, locations, scales of patches, backbones, and state-of-the-art face detection frameworks. We propose new optimization-based approaches to automatic design of universal adversarial patches for varying goals of the attack, including scenarios in which true positives are suppressed without introducing false positives. Our proposed algorithms perform well on real-world datasets, deceiving state-of-the-art face detectors in terms of multiple precision/recall metrics and transferability."

With the arising concerns for the AI systems provided with direct access to abundant sensitive information, researchers seek to develop more reliable AI with implicit information sources. To this end, in this paper, we introduce a new task called video description via two multi-modal cooperative dialog agents, whose ultimate goal is for one conversational agent to describe an unseen video based on the dialog and two static frames. Specifically, one of the intelligent agents - Q-BOT - is given two static frames from the beginning and the end of the video, as well as a finite number of opportunities to ask relevant natural language questions before describing the unseen video. A-BOT, the other agent who has already seen the entire video, assists Q-BOT to accomplish the goal by providing answers to those questions. We propose a QA-Cooperative Network with a dynamic dialog history update learning mechanism to transfer knowledge from A-BOT to Q-BOT, thus helping Q-BOT to better describe the video. Extensive experiments demonstrate that Q-BOT can effectively learn to describe an unseen video by the proposed model and the cooperative learning method, achieving the promising performance where Q-BOT is given the full ground truth history dialog."

Textures in natural images can be characterized by color, shape, periodicity of elements within them, and other attributes that can be described using natural language. In this paper, we study the problem of describing visual attributes of texture on a novel dataset containing rich descriptions of textures, and conduct a systematic study of current generative and discriminative models for grounding language to images on this dataset. We find that while these models capture some properties of texture, they fail to capture several compositional properties, such as the colors of dots. We provide critical analysis of existing models by generating synthetic but realistic textures with different descriptions. Our dataset also allows us to train interpretable models and generate language-based explanations of what discriminative features are learned by deep networks for fine-grained categorization where texture plays a key role. We present visualizations of several fine-grained domains and show that texture attributes learned on our dataset offer improvements over expert-designed attributes on the Caltech-UCSD Birds dataset."

We present a new object representation, called Dense Rep-Points, which utilize a large number of points to describe the multi-grainedobject representation of both box level and pixel level. Techniques are pro-posed to efficiently process these dense points, which maintains nearconstant complexity with increasing point number. The dense RepPointsis proved to represent and learn object segment well, by a novel dis-tance transform sampling method combined with a set-to-set supervision.The novel distance transform sampling method combines the strengthof contour and grid representation, which significantly outperforms thecounter-parts using contour or grid representations. On COCO, it achieves39.6 mask AP and 48.3 bbox AP."

In this paper, we propose an efficient and effective dense hybrid recurrent multi-view stereo net with dynamic consistency checking, namely $D^{2}$HC-RMVSNet, for accurate dense point cloud reconstruction. Our novel hybrid recurrent multi-view stereo net consists of two core modules: 1) a light DRENet (Dense Reception Expanded) module to extract dense feature maps of original size with multi-scale context information, 2) a hybrid HRU-LSTM (Hybrid Recurrent U-LSTM) to regularize 3D matching volume into predicted depth map, which efficiently aggregates different scale information by coupling LSTM and U-Net architecture. To further improve the accuracy and completeness of reconstructed point clouds, we leverage a dynamic consistency checking strategy instead of prefixed parameters and strategies widely adopted in existing methods for dense point cloud reconstruction. In doing so, we dynamically aggregate geometric consistency matching error among all the views. Our method ranks extbf{$1^{st}$} on the complex outdoor extsl{Tanks and Temples} benchmark over all the methods. Extensive experiments on the in-door extsl{DTU} dataset show our method exhibits competitive performance to the state-of-the-art method while dramatically reduces memory consumption, which costs only $19.4\%$ of R-MVSNet memory consumption. The codebase is available at \hyperlink{https://github.com/yhw-yhw/D2HC-RMVSNet}{https://github.com/yhw-yhw/D2HC-RMVSNet}."

We introduce a new problem of mph{retrieving} 3D models that are mph{deformable} to a given query shape and present a novel deep mph{deformation-aware} embedding to solve this retrieval task. 3D model retrieval is a fundamental operation for recovering a clean and complete 3D model from a noisy and partial 3D scan. However, given a finite collection of 3D shapes, even the closest model to a query may not be satisfactory. This motivates us to apply 3D model deformation techniques to adapt the retrieved model so as to better fit the query. Yet, certain restrictions are enforced in most 3D deformation techniques to preserve important features of the original model that prevent a perfect fitting of the deformed model to the query. This gap between the deformed model and the query induces mph{asymmetric} relationships among the models, which cannot be handled by typical metric learning techniques. Thus, to retrieve the best models for fitting, we propose a novel deep embedding approach that learns the asymmetric relationships by leveraging location-dependent egocentric distance fields. We also propose two strategies for training the embedding network. We demonstrate that both of these approaches outperform other baselines in our experiments with both synthetic and real data. Our project page can be found at \href{https://deformscan2cad.github.io/}{deformscan2cad.github.io}."

Both geometry and texture are fundamental aspects of visual style. Existing style transfer methods, however, primarily focus on texture, almost entirely ignoring geometry. We propose deformable style transfer (DST), an optimization-based approach that jointly stylizes the texture and geometry of a content image to better match a style image. Unlike previous geometry-aware stylization methods, our approach is neither restricted to a particular domain (such as human faces), nor does it require training sets of matching style/content pairs. We demonstrate our method on a diverse set of content and style images including portraits, animals, objects, scenes, and paintings. Code has been made publicly available at https://github.com/sunniesuhyoung/DST."

Defocus blur arises in images that are captured with a shallow depth of field due to the use of a wide aperture. Correcting defocus blur is challenging because the blur is spatially varying and difficult to estimate. We propose an effective defocus deblurring method that exploits data available on dual-pixel (DP) sensors found on most modern cameras. DP sensors are used to assist a camera's auto-focus by capturing two sub-aperture views of the scene in a single image shot. The two sub-aperture images are used to calculate the appropriate lens position to focus on a particular scene region and are discarded afterwards. We introduce a deep neural network (DNN) architecture that uses these discarded sub-aperture images to reduce defocus blur. A key contribution of our effort is a carefully captured dataset of 500 scenes (2000 images) where each scene has: (i) an image with defocus blur captured at a large aperture; (ii) the two associated DP sub-aperture views; and (iii) the corresponding all-in-focus image captured with a small aperture. Our proposed DNN produces results that are significantly better than conventional single image methods in terms of both quantitative and perceptual metrics -- all from data that is already available on the camera but ignored.

Defocus Blur Detection (DBD) aims to separate in-focus and out-of-focus regions from a single image pixel-wisely. This task has been paid much attention since bokeh effects are widely used in digital cameras and smartphone photography. However, identifying obscure homogeneous regions and borderline transitions in partially defocus images are still challenging. To solve these problems, we introduce depth information into DBD for the first time. When the camera parameters are fixed, we argue that the accuracy of DBD is highly related to scene depth. Hence, we consider the depth information as the approximate soft label of DBD and propose a joint learning framework inspired by knowledge distillation. In detail, we learn the defocus blur from ground truth and the depth distilled from a well-trained depth estimation network at the same time. Thus, the sharp region will provide a strong prior for depth estimation while the blur detection also gains benefits from the distilled depth. Besides, we propose a novel decoder in the fully convolutional network (FCN) as our network structure. In each level of decoder, we design the Selective Reception Field Block (SRFB) for merging multi-scale features efficiently and reuse the side outputs as Supervision-guided Attention Block(SAB). Unlike previous methods, the proposed decoder builds reception field pyramids and emphasizes salient regions simply and efficiently. Experiments show that our approach outperforms 11 other state-of-the-art methods on two popular datasets. Our method also runs at over 30 fps on a single GPU, which is 2x faster than previous works."

Deep neural networks are vulnerable to adversarial attacks. Though various attempts have been made, it is still largely open to fully understand the existence of adversarial samples and thereby develop effective defense strategies. In this paper, we present a new perspective, namely gradient leaking hypothesis, to understand the existence of adversarial examples and to further motivate effective defense strategies. Specifically, we consider the low dimensional manifold structure of natural images, and empirically verify that the leakage of the gradient (w.r.t input) along the (approximately) perpendicular direction to the tangent space of data manifold is a reason for the vulnerability over adversarial attacks. Based on our investigation, we further present a new robust learning algorithm which encourages a larger gradient component in the tangent space of data manifold, suppressing the gradient leaking phenomenon consequently. Experiments on various tasks demonstrate the effectiveness of our algorithm despite its simplicity."

Structure from motion (SfM) is an essential computer vision problem which has not been well handled by deep learning. One of the promising trends is to apply explicit structural constraint, e.g. 3D cost volume, into the network. However, existing methods usually assume accurate camera poses either from GT or other methods, which is unrealistic in practice. In this work, we design a physical driven architecture, namely DeepSFM, inspired by traditional Bundle Adjustment (BA), which consists of two cost volume based architectures for depth and pose estimation respectively, iteratively running to improve both. The explicit constraints on both depth (structure) and pose (motion), when combined with the learning components, bring the merit from both traditional BA and emerging deep learning technology. Extensive experiments on various datasets show that our model achieves the state-of-the-art performance on both depth and pose estimation with superior robustness against less number of inputs and the noise in initialization."

We build a new model of landscape videos that can be trained on a mixture of static landscape images as well as landscape animations. Our architecture extends StyleGAN model by augmenting it with parts that allow to model dynamic changes in a scene. Once trained, our model can be used to generate realistic time-lapse landscape videos with moving objects and time-of-the-day changes. Furthermore, by fitting the learned models to a static landscape image, the latter can be reenacted in a realistic way. We propose simple but necessary modifications to StyleGAN inversion procedure, which lead to in-domain latent codes and allow to manipulate real images. Quantitative comparisons and user studies suggest that our model produces more compelling animations of given photographs than previously proposed methods. The results of our approach including comparisons with prior art can be seen in supplementary materials and on the project page https://saic-mdal.github.io/deep-landscape/."

Human hands play a central role in interacting with other people and objects. For realistic replication of such hand motions, high-fidelity hand meshes have to be reconstructed. In this study, we firstly propose DeepHandMesh, a weakly-supervised deep encoder-decoder framework for high-fidelity hand mesh modeling. We design our system to be trained in an end-to-end and weakly-supervised manner; therefore, it does not require groundtruth meshes. Instead, it relies on weaker supervisions such as 3D joint coordinates and multi-view depth maps, which are easier to get than groundtruth meshes and do not dependent on the mesh topology. Although the proposed DeepHandMesh is trained in a weakly-supervised way, it provides significantly more realistic hand mesh than previous fully-supervised hand models. Our newly introduced penetration avoidance loss further improves results by replicating physical interaction between hand parts. Finally, we demonstrate that our system can also be applied successfully to the 3D hand mesh estimation from general images. Our hand model, dataset, and codes are publicly availableootnote{\url{https://mks0601.github.io/DeepHandMesh/}}."

Point cloud registration is a fundamental problem in 3D computer vision, graphics and robotics. For the last few decades, existing registration algorithms have struggled in situations with large transformations, noise, and time constraints. In this paper, we introduce Deep Gaussian Mixture Registration (DeepGMR), the first learning-based registration method that explicitly leverages a probabilistic registration paradigm by formulating registration as the minimization of KL-divergence between two probability distributions modeled as mixtures of Gaussians. We design a neural network that extracts pose-invariant correspondences between raw point clouds and Gaussian Mixture Model (GMM) parameters and two differentiable compute blocks that recover the optimal transformation from matched GMM parameters. This construction allows the network learn an SE(3)-invariant feature space, producing a global registration method that is real-time, generalizable, and robust to noise. Across synthetic and real-world data, our proposed method shows favorable performance when compared with state-of-the-art geometry-based and learning-based registration methods."

We propose a surface fitting method for unstructured 3D point clouds. This method, called DeepFit, incorporates a neural network to learn point-wise weights for weighted least squares polynomial surface fitting. The learned weights act as a soft selection for the neighborhood of surface points thus avoiding the scale selection required of previous methods. To train the network we propose a novel surface consistency loss that improves point weight estimation. The method enables extracting normal vectors and other geometrical properties, such as principal curvatures, the latter were not presented as ground truth during training. We achieve state-of-the-art results on a benchmark normal and curvature estimation dataset,demonstrate robustness to noise, outliers and density variations, and show its application on noise removal."

This paper presents a near-light photometric stereo method for spatially varying reflectances. Recent studies in photometric stereo proposed learning-based approaches to handle diverse real-world reflectances and achieve high accuracy compared to conventional methods. However, they assume distant (i.e., parallel) lights, which can in practical settings only be approximately realized, and they fail in near-light conditions. Near-light photometric stereo methods address near-light conditions but previous works are limited to over-simplified reflectances, such as Lambertian reflectance. The proposed method takes a hybrid approach of distant- and near-light models, where the surface normal of a small area (corresponding to a pixel) is computed locally with a distant light assumption, and the reconstruction error is assessed based on a near-light image formation model. This paper is the first work to solve unknown, spatially varying, diverse reflectances in near-light photometric stereo. "

We present a new method for vectorization of technical line drawings, such as floor plans, architectural drawings, and 2D CAD images. Our method includes (1) a deep learning-based cleaning stage to eliminate the background and imperfections in the image and fill in missing parts, (2) a transformer-based network to estimate vector primitives, and (3) optimization procedure to obtain the final primitive configurations. We train the networks on synthetic data, renderings of vector line drawings, and manually vectorized scans of line drawings. Our method quantitatively and qualitatively outperforms a number of existing techniques on a collection of representative technical drawings."

Network quantization is an effective method for network compression. Existing methods train a low-precision network by fine-tuning from a pre-trained model. However, training a low-precision network often requires large-scale labeled data to achieve superior performance. In many real-world scenarios, only limited labeled data are available due to expensive labeling costs or privacy protection. With limited training data, fine-tuning methods may suffer from the overfitting issue and substantial accuracy loss. To alleviate these issues, we introduce transfer learning into network quantization to obtain an accurate low-precision model. Specifically, we propose a method named deep transferring quantization (DTQ) to effectively exploit the knowledge in a pre-trained full-precision model. To this end, we propose a learnable attentive transfer module to identify the informative channels for alignment. In addition, we introduce the Kullback–Leibler (KL) divergence to further help train a low-precision model. Extensive experiments on both image classification and face recognition demonstrate the effectiveness of DTQ."