ECCV 2020 论文列表

Most 3D reconstruction methods may only recover scene properties up to a global scale ambiguity. We present a novel approach to single view metrology that can recover the absolute scale of a scene represented by 3D heights of objects or camera height above the ground as well as camera parameters of orientation and field of view, using just a monocular image acquired in unconstrained condition. Our method relies on data-driven priors learned by a deep network specifically designed to imbibe weakly supervised constraints from the interplay of the unknown camera with 3D entities such as object heights, through estimation of bounding box projections. We leverage categorical priors for objects such as humans or cars that commonly occur in natural images, as references for scale estimation. We demonstrate state-of-the-art qualitative and quantitative results on several datasets as well as applications including virtual object insertion. Furthermore, the perceptual quality of our outputs is validated by a user study."

We revisit the one-shot Neural Architecture Search (NAS) paradigm and analyze its advantages over existing NAS approaches. Existing one-shot method, however, is hard to train and not yet effective on large scale datasets like ImageNet. This work propose a Single Path One-Shot model to address the challenge in the training. Our central idea is to construct a simplified supernet, where all architectures are single paths so that weight co-adaption problem is alleviated. Training is performed by uniform path sampling. All architectures (and their weights) are trained fully and equally. Comprehensive experiments verify that our approach is flexible and effective. It is easy to train and fast to search. It effortlessly supports complex search spaces (e.g., building blocks, channel, mixed-precision quantization) and different search constraints (e.g., FLOPs, latency). It is thus convenient to use for various needs. It achieves start-of-the-art performance on the large dataset ImageNet."

Informative features play a crucial role in the single image super-resolution task. Channel attention has been demonstrated to be effective for preserving information-rich features in each layer. However, channel attention treats each convolution layer as a separate process, which is kind of missing the correlation among different layers. To address this problem, we propose a new holistic attention network (HAN), which consists of a layer attention module (LAM) and a channel-spatial attention module (CSAM), to model the holistic interdependencies among layers, channels, and positions. Specifically, the proposed LAM adaptively emphasizes hierarchical features by considering correlations among layers. Meanwhile, CSAM learns the confidence at all the positions of each channel to selectively capture more informative features. Extensive experiments demonstrate that the proposed HAN performs favorably against the state-of-the-art single image super-resolution approaches."

Deep learning based Multiple Object Tracking (MOT) currently relies on off-the-shelf detectors for tracking-by-detection. This results in deep models that are detector biased and evaluations that are detector influenced. To resolve this issue, we introduce Deep Motion Modeling Network (DMM-Net) that can estimate multiple objects' motion parameters to perform joint detection and association in an end-to-end manner. DMM-Net models object features over multiple frames and simultaneously infers object classes, visibility and their motion parameters. These outputs are readily used to update the tracklets for efficient MOT. DMM-Net achieves PR-MOTA score of 12.80 @ 120+ fps for the popular UA-DETRAC challenge - which is better performance and orders of magnitude faster. We also contribute a synthetic large-scale public dataset Omni-MOT for vehicle tracking that provides precise ground-truth annotations to eliminate the detector influence in MOT evaluation. This 14M+ frames dataset is extendable with our public script. We demonstrate the suitability of Omni-MOT for deep learning with DMM-Net, and also make the source code of our network public."

This paper uses a graphic engine to simulate a large amount of training data with free annotations. Between synthetic and real data, there is a two-level domain gap, i.e., content level and appearance level. While the latter has been widely studied, we focus on reducing the content gap in attributes like illumination and viewpoint. To reduce the problem complexity, we choose a smaller and more controllable application, vehicle re-identification (re-ID). We introduce a large-scale synthetic dataset VehicleX. Created in Unity, it contains 1,362 vehicles of various 3D models with fully editable attributes. We propose an attribute descent approach to let VehicleX approximate the attributes in real-world datasets. Specifically, we manipulate each attribute in VehicleX, aiming to minimize the discrepancy between VehicleX and real data in terms of the Fr ́echet Inception Distance (FID). This attribute descent algorithm allows content domain adaptation (DA) orthogonal to existing appearance DA methods. We mix the optimized VehicleX data with real-world vehicle re-ID datasets, and observe consistent improvement. With the augmented datasets, we report competitive accuracy. We make the dataset, engine and our codes available at https://github.com/yorkeyao/VehicleX/."

Recent increase in the availability of warped images projected onto a manifold (e.g., omnidirectional spherical images), coupled with the success of higher-order assignment methods, has sparked an interest in the search for improved higher-order matching algorithms on warped images due to projection. Although currently, several existing methods “flatten"" such 3D images to use planar graph / hypergraph matching methods, they still suffer from severe distortions and other undesired artifacts, which result in inaccurate matching. Alternatively, current planar methods cannot be trivially extended to effectively match points on images warped onto manifolds. Hence, matching on these warped images persists as a formidable challenge. In this paper, we pose the assignment problem as finding a bijective map between two graph induced simplicial complexes, which are higher-order analogues of graphs. We propose a constrained quadratic assignment problem (QAP) that matches each p-skeleton of the simplicial complexes, iterating from the highest to the lowest dimension. The accuracy and robustness of our approach are illustrated on both synthetic and real-world spherical / warped (projected) images with known ground-truth correspondences. We significantly outperform existing state-of-the-art spherical matching methods on a diverse set of datasets."

With a proliferation of generic domain-adaptation approaches, we report a simple yet effective technique for learning difficult per-pixel 2.5D and 3D regression representations of articulated people. We obtained strong sim-to-real domain generalization for the 2.5D DensePose estimation task and the 3D human surface normal estimation task. On the multi-person DensePose MSCOCO benchmark, our approach outperforms the state-of-the-art methods which are trained on real densely labelled images. This is an important result since obtaining human manifold's intrinsic uv coordinates on real images is time consuming and prone to labeling noise. Additionally, we present our model's 3D surface normal predictions on the MSCOCO dataset that lacks any real 3D surface normal labels. The key to our approach is to mitigate the ""Inter-domain Covariate Shift"" with a carefully selected training batch from a mixture of domain samples, a deep batch-normalized residual network, and a modified multi-task learning objective. Our approach is complementary to existing domain-adaptation techniques and can be applied to other dense per-pixel pose estimation problems. "

This paper studies the problem of predicting future trajectories of people in unseen cameras of novel scenarios and views. We approach this problem through the real-data-free setting in which the model is trained only on 3D simulation data and applied out-of-the-box to a wide variety of real cameras. We propose a novel approach to learn robust representation through augmenting the simulation training data such that the representation can better generalize to unseen real-world test data. The key idea is to mix the feature of the hardest camera view with the adversarial feature of the original view. We refer to our method as $ extit{SimAug}$. We show that $ extit{SimAug}$ achieves promising results on three real-world benchmarks using zero real training data, and state-of-the-art performance in the Stanford Drone and the VIRAT/ActEV dataset when using in-domain training data. Code and models are released at https://next.cs.cmu.edu/simaug"

Fully-automatic execution is the ultimate goal for many Computer Vision applications. However, this objective is not always realistic in tasks associated with high failure costs, such as medical applications. For these tasks, semi-automatic methods allowing minimal effort from users to guide computer algorithms are often preferred due to desirable accuracy and performance. Inspired by the practicality and applicability of the semi-automatic approach, this paper proposes a novel deep neural network architecture, namely SideInfNet that effectively integrates features learnt from images with side information extracted from user annotations. To evaluate our method, we applied the proposed network to three semantic segmentation tasks and conducted extensive experiments on benchmark datasets. Experimental results and comparison with prior work have verified the superiority of our model, suggesting the generality and effectiveness of the model in semi-automatic semantic segmentation. "

When training a neural network for a desired task, one may prefer to adapt a pre-trained network rather than starting from randomly initialized weights. Adaptation can be useful in cases when training data is scarce, when a single learner needs to perform multiple tasks, or when one wishes to encode priors in the network. The most commonly employed approaches for network adaptation are fine-tuning and using the pre-trained network as a fixed feature extractor, among others.

Current object detection frameworks mainly rely on bounding box regression to localize objects. Despite the remarkable progress in recent years, the precision of bounding box regression remains unsatisfactory, hence limiting performance in object detection. We observe that precise localization requires careful placement of each side of the bounding box. However, the mainstream approach, which focuses on predicting centers and sizes, is not the most effective way to accomplish this task, especially when there exists displacements with large variance between the anchors and the targets. In this paper, we propose an alternative approach, named as Side-Aware Boundary Localization (SABL), where each side of the bounding box is respectively localized with a dedicated network branch. To tackle the difficulty of precise localization in the presence of displacements with large variance, we further propose a two-step localization scheme, which first predicts a range of movement through bucket prediction and then pinpoints the precise position within the predicted bucket. We test the proposed method on both two-stage and single-stage detection frameworks. Replacing the standard bounding box regression branch with the proposed design leads to significant improvements on Faster R-CNN, RetinaNet, and Cascade R-CNN, by 3.0%, 1.7%, and 0.9%, respectively. Code is available at https://github.com/open-mmlab/mmdetection."

We address the problem of domain adaptation in videos for the task of human action recognition. Inspired by image-based domain adaptation, we can perform video adaptation by aligning the features of frames or clips of source and target videos. However, equally aligning all clips is sub-optimal as not all clips are informative for the task. As the first novelty, we propose an attention mechanism which focuses on more discriminative clips and directly optimizes for video-level (cf. clip-level) alignment. As the backgrounds are often very different between source and target, the source background-corrupted model adapts poorly to target domain videos. To alleviate this, as a second novelty, we propose to use the clip order prediction as an auxiliary task. The clip order prediction loss, when combined with domain adversarial loss, encourages learning of representations which focus on the humans and objects involved in the actions, rather than the uninformative and widely differing (between source and target) backgrounds. We empirically show that both components contribute positively towards adaptation performance. We report state-of-the-art performances on two out of three challenging public benchmarks, two based on the UCF and HMDB datasets, and one on Kinetics to NEC-Drone datasets. We also support the intuitions and the results with qualitative results."

Video inpainting aims to restore missing regions of a video and has many applications such as video editing and object removal. However, existing methods either suffer from inaccurate short-term context aggregation or rarely explore long-term frame information. In this work, we present a novel context aggregation network to effectively exploit both short-term and long-term frame information for video inpainting. In the encoding stage, we propose boundary-aware short-term context aggregation, which aligns and aggregates, from neighbor frames, local regions that are closely related to the boundary context of missing regions into the target frame. Furthermore, we propose dynamic long-term context aggregation to globally refine the feature map generated in the encoding stage using long-term frame features, which are dynamically updated throughout the inpainting process. Experiments show that it outperforms state-of-the-art methods with better inpainting results and fast inpainting speed."

Shonan Rotation Averaging is a fast, simple, and elegant rotation averaging algorithm that is guaranteed to recover globally optimal solutions under mild assumptions on the measurement noise. Our method employs semidefinite relaxation in order to recover provably globally optimal solutions of the rotation averaging problem. In contrast to prior work, we show how to solve large-scale instances of these relaxations using manifold minimization on (only slightly) higher-dimensional rotation manifolds, re-using existing high-performance (but local) structure-from-motion pipelines. Our method thus preserves the speed and scalability of those, while enabling the recovery of globally optimal solutions."

We present a learning framework that learns to recover the 3D shape, pose and texture from a single image, trained on an image collection without any ground truth 3D shape, multi-view, camera viewpoints or keypoint supervision. We approach this highly under-constrained problem in a ``analysis by synthesis"" framework where the goal is to predict the likely shape, texture and camera viewpoint that could produce the image with various learned category-specific priors. Our particular contribution in this paper is a representation of the distribution over cameras, which we call ``camera-multiplex"". Instead of picking a point estimate, we maintain a set of camera hypotheses that are optimized during training to best explain the image given the current shape and texture. We call our approach Unsupervised Category-Specific Mesh Reconstruction (U-CMR), and present qualitative and quantitative results on CUB, Pascal 3D and new web-scraped datasets. We obtain state-of-the-art camera prediction results and show that we can learn to predict diverse shapes and textures across objects using an image collection without any keypoint annotations or 3D ground truth. Project page: https://shubham-goel.github.io/ucmr"

We present a novel learning approach to recover the 6D poses and sizes of unseen object instances from an RGB-D image. To handle the intra-class shape variation, we propose a deep network to reconstruct the 3D object model by explicitly modeling the deformation from a pre-learned categorical shape prior. Additionally, our network infers the dense correspondences between the depth observation of the object instance and the reconstructed 3D model to jointly estimate the 6D object pose and size. We design an autoencoder that trains on a collection of object models and compute the mean latent embedding for each category to learn the categorical shape priors. Extensive experiments on both synthetic and real-world datasets demonstrate that our approach significantly outperforms the state of the art. Our code is available at https://github.com/mentian/object-deformnet."

We present a novel resizing module for neural networks: shape adaptor, a drop-in enhancement built on top of traditional resizing layers, such as pooling, bilinear sampling, and strided convolution. Whilst traditional resizing layers have fixed and deterministic reshaping factors, our module allows for a learnable reshaping factor. Our implementation enables shape adaptors to be trained end-to-end without any additional supervision, through which network architectures can be optimised for each individual task, in a fully automated way. We performed experiments across seven image classification datasets, and results show that by simply using a set of our shape adaptors instead of the original resizing layers, performance increases consistently over human-designed networks, across all datasets. Additionally, we show the effectiveness of shape adaptors on two other applications: network compression and transfer learning."

Scene text detection has been significantly advanced over recent years, especially after the emergence of deep neural network. However, due to high diversity of scene texts in scale, orientation, shape and aspect ratio, as well as the inherent limitation of convolutional neural network for geometric transformations, to achieve accurate scene text detection is still an open problem. In this paper, we propose a novel sequential deformation method to effectively model the line-shape of scene text. An auxiliary character counting supervision is further introduced to guide the sequential offset prediction. The whole network can be easily optimized through an end-to-end multi-task manner. Extensive experiments are conducted on public scene text detection datasets including ICDAR 2017 MLT, ICDAR 2015, Total-text and SCUT-CTW1500. The experimental results demonstrate that the proposed method has outperformed previous state-of-the-art methods."

In recent years, Deep Neural Networks (DNN) have empowered Compressed Sensing (CS) substantially and have achieved high reconstruction quality and speed far exceeding traditional CS methods. However, there are still lots of issues to be further explored before it can be practical enough. There are mainly two challenging problems in CS, one is to achieve efficient data sampling, and the other is to reconstruct images with high-quality. To address the two challenges, this paper proposes a novel Runge-Kutta Convolutional Compressed Sensing Network (RK-CCSNet). In the sensing stage, RK-CCSNet applies Sequential Convolutional Module (SCM) to gradually compact measurements through a series of convolution filters. In the reconstruction stage, RK-CCSNet establishes a novel Learned Runge-Kutta Block (LRKB) based on the famous Runge-Kutta methods, reformulating the process of image reconstruction as a discrete dynamical system. Finally, the implementation of RK-CCSNet achieves state-of-the-art performance on influential benchmarks with respect to prestigious baselines, and all the codes are available at https://github.com/rkteddy/RK-CCSNet."