ECCV 2020 Papers

We present a generalized and scalable method, called Gen-LaneNet, to detect 3D lanes from a single image. The method, inspired by the latest state-of-the-art 3D-LaneNet, is a unified framework solving image encoding, spatial transform of features and 3D lane prediction in a single network. However, we propose unique designs for Gen-LaneNet in two folds. First, we introduce a new geometry-guided lane anchor representation in a new coordinate frame and apply a specific geometric transformation to directly calculate real 3D lane points from the network output. We demonstrate that aligning the lane points with the underlying top-view features in the new coordinate frame is critical towards a generalized method in handling unfamiliar scenes. Second, we present a scalable two-stage framework that decouples the learning of image segmentation subnetwork and geometry encoding subnetwork. Compared to 3D-LaneNet, the proposed Gen-LaneNet drastically reduces the amount of 3D lane labels required to achieve a robust solution in real-world applications. Moreover, we release a new synthetic dataset and its construction strategy to encourage the development and evaluation of 3D lane detection methods. In experiments, we conduct extensive ablation study to substantiate the proposed Gen-LaneNet significantly outperforms 3D-LaneNet in average precision(AP) and F-measure."

Accurate modeling of 3D objects exhibiting transparency, reflections and thin structures is an extremely challenging problem. Inspired by billboards and geometric proxies used in computer graphics, this paper proposes Generative Latent Textured Objects (GeLaTO), a compact representation that combines a set of coarse shape proxies defining low frequency geometry with learned neural textures, to encode both medium and fine scale geometry as well as view-dependent appearance. To generate the proxies' textures, we learn a joint latent space allowing category-level appearance and geometry interpolation. The proxies are independently rasterized with their corresponding neural texture and composited using a U-Net, which generates an output photorealistic image including an alpha map. We demonstrate the effectiveness of our approach by reconstructing complex objects from a sparse set of views. We show results on a dataset of real images of eyeglasses frames, which are particularly challenging to reconstruct using classical methods. We also demonstrate that these coarse proxies can be handcrafted when the underlying object geometry is easy to model, like eyeglasses, or generated using a neural network for more complex categories, such as cars."

We propose a method of gait recognition just from a single image for the first time, which enables latency-free gait recognition. To mitigate large intra-subject variations caused by a phase (gait pose) difference between a matching pair of input single images, we first reconstruct full gait cycles of image sequences from the single images using an auto-encoder framework, and then feed them into a state-of-the-art gait recognition network for matching. Specifically, a phase estimation network is introduced for the input single image, and the gait cycle reconstruction network exploits the estimated phase to mitigate the dependence of an encoded feature on the phase of that single image. This is called phase-aware gait cycle reconstructor (PA-GCR). In the training phase, the PA-GCR and recognition network are simultaneously optimized to achieve a good trade-off between reconstruction and recognition accuracies. Experiments on three gait datasets demonstrate the significant performance improvement of this method."

Gait recognition aims at identifying different people by the walking patterns, which can be conducted at a long distance without the cooperation of subjects. A key challenge for gait recognition is to learn representations from the silhouettes that are invariant to the factors such as clothing, carrying conditions and camera viewpoints. Besides being discriminative for identification, the gait representations should also be compact for storage to keep millions of subjects registered in the gallery. In this work, we propose a novel network named Gait Lateral Network (GLN) which can learn both discriminative and compact representations from the silhouettes for gait recognition. Specifically, GLN leverages the inherent feature pyramid in deep convolutional neural networks to enhance the gait representations. The silhouette-level and set-level features extracted by different stages are merged with the lateral connections in a top-down manner. Besides, GLN is equipped with a Compact Block which can significantly reduce the dimension of the gait representations without hindering the accuracy. Extensive experiments on CASIA-B and OUMVLP show that GLN can achieve state-of-the-art performance using the $256$-dimensional representations. Under the most challenging condition of walking in different clothes on CASIA-B, our method improves the rank-1 accuracy by $6.45\%$."

We revisit the benefits of merging classical vision concepts with deep learning models. In particular, we explore the effect of replacing the first layers of various deep architectures with Gabor layers (i.e. convolutional layers with filters that are based on learnable Gabor parameters) on robustness against adversarial attacks. We observe that architectures with Gabor layers gain a consistent boost in robustness over regular models and maintain high generalizing test performance. We then exploit the analytical expression of Gabor filters to derive a compact expression for a Lipschitz constant of such filters, and harness this theoretical result to develop a regularizer we use during training to further enhance network robustness. We conduct extensive experiments with various architectures (LeNet, AlexNet, VGG16, and WideResNet) on several datasets (MNIST, SVHN, CIFAR10 and CIFAR100) and demonstrate large empirical robustness gains. Furthermore, we experimentally show how our regularizer provides consistent robustness improvements."

We present a novel end-to-end framework named as GSNet ( extbf{\underline{G}}eometric and extbf{\underline{S}}cene-aware \underline{ extbf{Net}}work), which jointly estimates 6DoF poses and reconstructs detailed 3D car shapes from single urban street view. GSNet utilizes a unique four-way feature extraction and fusion scheme and directly regresses 6DoF poses and shapes in a single forward pass. Extensive experiments show that our diverse feature extraction and fusion scheme can greatly improve model performance. Based on a divide-and-conquer 3D shape representation strategy, GSNet reconstructs 3D vehicle shape with great detail (1352 vertices and 2700 faces). This dense mesh representation further leads us to consider geometrical consistency and scene context, and inspires a new multi-objective loss function to regularize network training, which in turn improves the accuracy of 6D pose estimation and validates the merit of jointly performing both tasks. We evaluate GSNet on the largest multi-task ApolloCar3D benchmark and achieve state-of-the-art performance both quantitatively and qualitatively."

Single image 3D shape interpretation and reconstruction are closely related to each other but have long been studied separately and often end up with priors that are highly biased by training classes. Here we present an algorithm extit{(GSIR)}, designed to joint learning these two tasks to capture generic, class-agnostic shape priors for a better understanding of 3D geometry. We propose to recover 3D shape structures as cuboids from partially reconstructed objects and use the predicted structures to further guide 3D reconstruction. The unified framework is trained simultaneously offline to learn a generic notion and can be fine-tuned online for specific objects without any annotations. Extensive experiments on both synthetic and real data demonstrate that introducing 3D shape interpretation improves the performance of 3D reconstruction and vice versa, against the state-of-the-art algorithms on both seen and unseen categories."

Estimating the complete 3D point cloud from an incomplete one is a key problem in many vision and robotics applications. Mainstream methods (e.g., PCN and TopNet) use Multi-layer Perceptrons (MLPs) to directly process point clouds, which may cause the loss of details because the structural and context of point clouds are not fully considered. To solve this problem, we introduce 3D grids as intermediate representations to regularize unordered point clouds. We therefore propose a novel Gridding Residual Network (GRNet) for point cloud completion. In particular, we devise two novel differentiable layers, named Gridding and Gridding Reverse, to convert between point clouds and 3D grids without losing structural information. We also present the differentiable Cubic Feature Sampling layer to extract features of neighboring points, which preserves context information. In addition, we design a new loss function, namely Gridding Loss, to calculate the L1 distance between the 3D grids of the predicted and ground truth point clouds, which is helpful to recover details. Experimental results indicate that the proposed GRNet performs favorably against state-of-the-art methods on the ShapeNet, Completion3D, and KITTI benchmarks."

Training computers to understand, model, and synthesize human grasping requires a rich dataset containing complex 3D object shapes, detailed contact information, hand pose and shape, and the 3D body motion over time. While ""grasping"" is commonly thought of as a single hand stably lifting an object, we capture the motion of the entire body and adopt the generalized notion of ""whole-body grasps"". Thus, we collect a new dataset, called GRAB (GRasping Actions with Bodies), of whole-body grasps, containing full 3D shape and pose sequences of 10 subjects interacting with 51 everyday objects of varying shape and size. Given MoCap markers, we fit the full 3D body shape and pose, including the articulated face and hands, as well as the 3D object pose. This gives detailed 3D meshes over time, from which we compute contact between the body and object. This is a unique dataset, that goes well beyond existing ones for modeling and understanding how humans grasp and manipulate objects, how their full body is involved, and how interaction varies with the task. We illustrate the practical value of GRAB with an example application; we train GrabNet, a conditional generative network, to predict 3D hand grasps for unseen 3D object shapes. The dataset and code are available for research purposes at https://grab.is.tue.mpg.de."

The semantic segmentation of parts of objects in the wild is a challenging task in which multiple instances of objects and multiple parts within those objects must be detected in the scene. This problem remains nowadays very marginally explored, despite its fundamental importance towards detailed object understanding. In this work, we propose a novel framework combining higher object-level context conditioning and part-level spatial relationships to address the task. To tackle object-level ambiguity, a class-conditioning module is introduced to retain class-level semantics when learning parts-level semantics. In this way, mid-level features carry also this information prior to the decoding stage. To tackle part-level ambiguity and localization we propose a novel adjacency graph-based module that aims at matching the relative spatial relationships between ground truth and predicted parts. The experimental evaluation on the Pascal-Part dataset shows that we achieve state-of-the-art results on this task."

Generative adversarial networks (GANs) have achieved impressive results today, but not all generated images are perfect. A number of quantitative criteria have recently emerged for generative model, but none of them are designed for a single generated image. In this paper, we propose a new research topic, Generated Image Quality Assessment (GIQA), which quantitatively evaluates the quality of each generated image. We introduce three GIQA algorithms from two perspectives: learning-based and data-based. We evaluate a number of images generated by various recent GAN models on different datasets and demonstrate that they are consistent with human assessments. Furthermore, GIQA is available to many applications, like separately evaluate the realism and diversity of generative models, and enable online hard negative mining (OHEM) in the training of GANs to improve the results."

Recently, context reasoning using image regions beyond local convolution has shown great potential for scene parsing. In this work, we explore how to incorperate the linguistic knowledge to promote context reasoning over image regions by proposing a Graph Interaction unit (GI unit) and a Semantic Context Loss (SC-loss). The GI unit is capable of enhancing feature representations of convolution networks over high-level semantics and learning the semantic coherency adaptively to each sample. Specifically, the dataset-based linguistic knowledge is first incorporated in the GI unit to promote context reasoning over the visual graph, then the evolved representations of the visual graph are mapped to each local representation to enhance the discriminated capability for scene parsing. GI unit is further improved by the SC-loss to enhance the semantic representations over the exemplar-based semantic graph. We perform full ablation studies to demonstrate the effectiveness of each component in our approach. Particularly, the proposed GINet outperforms the state-of-the-art approaches on the popular benchmarks, including Pascal-Context and COCO Stuff."

We discuss a general formulation for the Continual Learning (CL) problem for classification---a learning task where a stream provides samples to a learner and the goal of the learner, depending on the samples it receives, is to continually upgrade its knowledge about the old classes and learn new ones. Our formulation takes inspiration from the open-set recognition problem where test scenarios do not necessarily belong to the training distribution. We also discuss various quirks and assumptions encoded in recently proposed approaches for CL. We argue that some oversimplify the problem to an extent that leaves it with very little practical importance, and makes it extremely easy to perform well on. To validate this, we propose GDumb that (1) greedily stores samples in memory as they come and; (2) at test time, trains a model from scratch using samples only in the memory. We show that even though GDumb is not specifically designed for CL problems, it obtains state-of-the-art accuracies (often with large margins) in almost all the experiments when compared to a multitude of recently proposed algorithms. Surprisingly, it outperforms approaches in CL formulations for which they were specifically designed. This, we believe, raises concerns regarding our progress in CL for classification. Overall, we hope our formulation, characterizations and discussions will help in designing realistically useful CL algorithms, and GDumb will serve as a strong contender for the same."

We propose a self-supervised Gaussian ATtention network for image Clustering (GATCluster). Rather than extracting intermediate features first and then performing traditional clustering algorithms, GATCluster directly outputs semantic cluster labels without further post-processing. We give a Label Feature Theorem to guarantee that the learned features are one-hot encoded vectors and the trivial solutions are avoided. Based on this theorem, we design four self-learning tasks with the constraints of transformation invariance, separability maximization, entropy analysis, and attention mapping. Specifically, the transformation invariance and separability maximization tasks learn the relations between samples. The entropy analysis task aims to avoid trivial solutions. To capture the object-oriented semantics, we design a self-supervised attention mechanism that includes a Gaussian attention module and a soft-attention loss. Moreover, we design a two-step learning algorithm that is memory-efficient for clustering large-size images. Extensive experiments demonstrate the superiority of our proposed method in comparison with the state-of-the-art image clustering benchmarks."

Although current image generation methods have reached impressive quality levels, they are still unable to produce plausible yet diverse images of handwritten words. On the contrary, when writing by hand, a great variability is observed across different writers, and even when analyzing words scribbled by the same individual, involuntary variations are conspicuous. In this work, we take a step closer to producing realistic and varied artificially rendered handwritten words. We propose a novel method that is able to produce credible handwritten word images by conditioning the generative process with both calligraphic style features and textual content. Our generator is guided by three complementary learning objectives: to produce realistic images, to imitate a certain handwriting style and to convey a specific textual content. Our model is unconstrained to any predefined vocabulary, being able to render whatever input word. Given a sample writer, it is also able to mimic its calligraphic features in a few-shot setup. We significantly advance over prior art and demonstrate with qualitative, quantitative and human-based evaluations the realistic aspect of our synthetically produced images."

We introduce GANHopper, an unsupervised image-to-image translation network that transforms images gradually between two domains, through multiple hops. Instead of executing translation directly, we steer the translation by requiring the network to produce in-between images that resemble weighted hybrids between images from the input domains. Our network is trained on unpaired images from the two domains only, without any in-between images. All hops are produced using a single generator along each direction. In addition to the standard cycle-consistency and adversarial losses, we introduce a new hybrid discriminator, which is trained to classify the intermediate images produced by the generator as weighted hybrids, with weights based on a predetermined hop count. We also add a smoothness term to constrain the magnitude of each hop, further regularizing the translation. Compared to previous methods, GANHopper excels at image translations involving domain-specific image features and geometric variations while also preserving non-domain-specific features such as general color schemes"

The generation of realistic apparel model has become increasingly popular as a result of the rapid pace of change in fashion trends and the growing need for garment models in various applications such as virtual try-on. For such application requirements, it is important to have a general cloth model that can represent a diverse set of garments. Previous studies often make certain assumptions about the garment, such as the topology or suited body shape. We propose a unified method using the generative network. Our model is applicable to different garment topologies with different sewing patterns and fabric materials. We also develop a novel image representation of garment models, and a reliable mapping algorithm between the general garment model and the image representation that can regularize the data representation of the cloth. Using this special intermediate image representation, the generated garment model can be easily retargeted to another body, enabling garment customization. In addition, a large garment appearance dataset is provided for use in garment reconstruction, garment capturing, and other applications. We demonstrate that our generative model has high reconstruction accuracy and can provide rich variations of virtual garments."

Generative adversarial networks (GANs) have gained increasing popularity in various computer vision applications, and recently start to be deployed to resource-constrained mobile devices. Similar to other deep models, state-of-the-art GANs also suffer from high parameter complexities. That has recently motivated the exploration of compressing GANs (usually generators). Compared to the vast literature and prevailing success in compressing deep classifiers, the study of GAN compression remains in its infancy, so far leveraging individual compression techniques instead of more sophisticated combinations. We observe that due to the notorious instability of training GANs, heuristically stacking different compression techniques will result in unsatisfactory results. To this end, we propose the first end-to-end optimization framework combining multiple compression means for GAN compression, dubbed GAN Slimming (GS). GS seamlessly integrates three mainstream compression techniques: model distillation, channel pruning and quantization, together with the GAN minimax objective, into one unified optimization form, that can be efficiently optimized from end to end. Without bells and whistles, GS largely outperforms existing options in compressing image-to-image translation GANs. Specifically, we apply GS to compress CartoonGAN, a state-of-the-art style transfer network, by up to $47 imes$ times, with minimal visual quality degradation. Codes and pre-trained models can be found at https://github.com/TAMU-VITA/GAN-Slimming."

In this paper, we propose a computationally tractable and theoretically supported non-linear low-dimensional generative model to represent real-world data in the presence of noise and sparse outliers. The non-linear low-dimensional manifold discovery of data is done through describing a joint distribution over observations, and their low-dimensional representations (i.e. manifold coordinates). Our model, called generative low-dimensional background model (G-LBM) admits variational operations on the distribution of the manifold coordinates and simultaneously generates a low-rank structure of the latent manifold given the data. Therefore, our probabilistic model contains the intuition of the non-probabilistic low-dimensional manifold learning. G-LBM selects the intrinsic dimensionality of the underling manifold of the observations, and its probabilistic nature models the noise in the observation data. G-LBM has direct application in the background scenes model estimation from video sequences and we have evaluated its performance on SBMnet-2016 and BMC2012 datasets, where it achieved a performance higher or comparable to other state-of-the-art methods while being agnostic to the background scenes in videos. Besides, in challenges such as camera jitter and background motion, G-LBM is able to robustly estimate the background by effectively modeling the uncertainties in video observations in these scenarios."