CVPR 2020 论文列表

The recent progress in neural architecture search (NAS) has allowed scaling the automated design of neural architectures to real-world domains, such as object detection and semantic segmentation. However, one prerequisite for the application of NAS are large amounts of labeled data and compute resources. This renders its application challenging in few-shot learning scenarios, where many related tasks need to be learned, each with limited amounts of data and compute time. Thus, few-shot learning is typically done with a fixed neural architecture. To improve upon this, we propose MetaNAS, the first method which fully integrates NAS with gradient-based meta-learning. MetaNAS optimizes a meta-architecture along with the meta-weights during meta-training. During meta-testing, architectures can be adapted to a novel task with a few steps of the task optimizer, that is: task adaptation becomes computationally cheap and requires only little data per task. Moreover, MetaNAS is agnostic in that it can be used with arbitrary model-agnostic meta-learning algorithms and arbitrary gradient-based NAS methods. Empirical results on standard few-shot classification benchmarks show that MetaNAS with a combination of DARTS and REPTILE yields state-of-the-art results.

Feature warping is a core technique in optical flow estimation; however, the ambiguity caused by occluded areas during warping is a major problem that remains unsolved. In this paper, we propose an asymmetric occlusion-aware feature matching module, which can learn a rough occlusion mask that filters useless (occluded) areas immediately after feature warping without any explicit supervision. The proposed module can be easily integrated into end-to-end network architectures and enjoys performance gains while introducing negligible computational cost. The learned occlusion mask can be further fed into a subsequent network cascade with dual feature pyramids with which we achieve state-of-the-art performance. At the time of submission, our method, called MaskFlownet, surpasses all published optical flow methods on the MPI Sintel, KITTI 2012 and 2015 benchmarks. Code is available at https://github.com/microsoft/MaskFlownet.

Lifelong place recognition is an essential and challenging task in computer vision with vast applications in robust localization and efficient large-scale 3D reconstruction. Progress is currently hindered by a lack of large, diverse, publicly available datasets. We contribute with Mapillary Street-Level Sequences (SLS), a large dataset for urban and suburban place recognition from image sequences. It contains more than 1.6 million images curated from the Mapillary collaborative mapping platform. The dataset is orders of magnitude larger than current data sources, and is designed to reflect the diversities of true lifelong learning. It features images from 30 major cities across six continents, hundreds of distinct cameras, and substantially different viewpoints and capture times, spanning all seasons over a nine year period. All images are geo-located with GPS and compass, and feature high-level attributes such as road type. We propose a set of benchmark tasks designed to push state-of-the-art performance and provide baseline studies. We show that current state-of-the-art methods still have a long way to go, and that the lack of diversity in existing datasets have prevented generalization to new environments. The dataset and benchmarks are available for academic research.

Conventional cell tracking methods detect multiple cells in each frame (detection) and then associate the detection results in successive time-frames (association). Most cell tracking methods perform the association task independently from the detection task. However, there is no guarantee of preserving coherence between these tasks, and lack of coherence may adversely affect tracking performance. In this paper, we propose the Motion and Position Map (MPM) that jointly represents both detection and association for not only migration but also cell division. It guarantees coherence such that if a cell is detected, the corresponding motion flow can always be obtained. It is a simple but powerful method for multi-object tracking in dense environments. We compared the proposed method with current tracking methods under various conditions in real biological images and found that it outperformed the state-of-the-art (+5.2% improvement compared to the second-best).

Existing Temporal Activity Localization (TAL) methods largely adopt strong supervision for model training, which requires (1) vast amounts of untrimmed videos per each activity category and (2) accurate segment-level boundary annotations (start time and end time) for every instance. This poses a critical restriction to the current methods in practical scenarios where not only segment-level annotations are expensive to obtain, but many activity categories are also rare and unobserved during training. Therefore, Can we learn a TAL model under weak supervision that can localize unseen activity classes? To address this scenario, we define a novel example-based TAL problem called Minimum Effort Temporal Activity Localization (METAL): Given only a few examples, the goal is to find the occurrences of semantically-related segments in an untrimmed video sequence while model training is only supervised by the video-level annotation. Towards this objective, we propose a novel Similarity Pyramid Network (SPN) that adopts the few-shot learning technique of Relation Network and directly encodes hierarchical multi-scale correlations, which we learn by optimizing two complimentary loss functions in an end-to-end manner. We evaluate the SPN on the THUMOS'14 and ActivityNet datasets, of which we rearrange the videos to fit the METAL setup. Results show that our SPN achieves performance superior or competitive to state-of-the-art approaches with stronger supervision.

We propose MAGSAC++ and Progressive NAPSAC sampler, P-NAPSAC in short. In MAGSAC++, we replace the model quality and polishing functions of the original method by an iteratively re-weighted least-squares fitting with weights determined via marginalizing over the noise scale. MAGSAC++ is fast -- often an order of magnitude faster -- and more geometrically accurate than MAGSAC. P-NAPSAC merges the advantages of local and global sampling by drawing samples from gradually growing neighborhoods. Exploiting that nearby points are more likely to originate from the same geometric model, P-NAPSAC finds local structures earlier than global samplers. We show that the progressive spatial sampling in P-NAPSAC can be integrated with PROSAC sampling, which is applied to the first, location-defining, point. The methods are tested on homography and fundamental matrix fitting on six publicly available datasets. MAGSAC combined with P-NAPSAC sampler is superior to state-of-the-art robust estimators in terms of speed, accuracy and failure rate.

The goal of this project is to learn a 3D shape representation that enables accurate surface reconstruction, compact storage, efficient computation, consistency for similar shapes, generalization across diverse shape categories, and inference from depth camera observations. Towards this end, we introduce Local Deep Implicit Functions (LDIF), a 3D shape representation that decomposes space into a structured set of learned implicit functions. We provide networks that infer the space decomposition and local deep implicit functions from a 3D mesh or posed depth image. During experiments, we find that it provides 10.3 points higher surface reconstruction accuracy (F-Score) than the state-of-the-art (OccNet), while requiring fewer than 1% of the network parameters. Experiments on posed depth image completion and generalization to unseen classes show 15.8 and 17.8 point improvements over the state-of-the-art, while producing a structured 3D representation for each input with consistency across diverse shape collections.

Normalization layers have been shown to improve convergence in deep neural networks, and even add useful inductive biases. In many vision applications the local spatial context of the features is important, but most common normalization schemes including Group Normalization (GN), Instance Normalization (IN), and Layer Normalization (LN) normalize over the entire spatial dimension of a feature. This can wash out important signals and degrade performance. For example, in applications that use satellite imagery, input images can be arbitrarily large; consequently, it is nonsensical to normalize over the entire area. Positional Normalization (PN), on the other hand, only normalizes over a single spatial position at a time. A natural compromise is to normalize features by local context, while also taking into account group level information. In this pa- per, we propose Local Context Normalization (LCN): a normalization layer where every feature is normalized based on a window around it and the filters in its group. We propose an algorithmic solution to make LCN efficient for arbitrary window sizes, even if every point in the image has a unique window. LCN outperforms its Batch Normalization (BN), GN, IN, and LN counterparts for object detection, semantic segmentation, and instance segmentation applications in several benchmark datasets, while keeping performance in- dependent of the batch size and facilitating transfer learning.

We tackle the problem of producing realistic simulations of LiDAR point clouds, the sensor of preference for most self-driving vehicles. We argue that, by leveraging real data, we can simulate the complex world more realistically compared to employing virtual worlds built from CAD/procedural models. Towards this goal, we first build a large catalog of 3D static maps and 3D dynamic objects by driving around several cities with our self-driving fleet. We can then generate scenarios by selecting a scene from our catalog and "virtually" placing the self-driving vehicle (SDV) and a set of dynamic objects from the catalog in plausible locations in the scene. To produce realistic simulations, we develop a novel simulator that captures both the power of physics-based and learning-based simulation. We first utilize raycasting over the 3D scene and then use a deep neural network to produce deviations from the physics-based simulation, producing realistic LiDAR point clouds. We showcase LiDARsim's usefulness for perception algorithms-testing on long-tail events and end-to-end closed-loop evaluation on safety-critical scenarios.

Numerous methods have been proposed for probabilistic generative modelling of 3D objects. However, none of these is able to produce textured objects, which renders them of limited use for practical tasks. In this work, we present the first generative model of textured 3D meshes. Training such a model would traditionally require a large dataset of textured meshes, but unfortunately, existing datasets of meshes lack detailed textures. We instead propose a new training methodology that allows learning from collections of 2D images without any 3D information. To do so, we train our model to explain a distribution of images by modelling each image as a 3D foreground object placed in front of a 2D background. Thus, it learns to generate meshes that when rendered, produce images similar to those in its training set. A well-known problem when generating meshes with deep networks is the emergence of self-intersections, which are problematic for many use-cases. As a second contribution we therefore introduce a new generation process for 3D meshes that guarantees no self-intersections arise, based on the physical intuition that faces should push one another out of the way as they move. We conduct extensive experiments on our approach, reporting quantitative and qualitative results on both synthetic data and natural images. These show our method successfully learns to generate plausible and diverse textured 3D samples for five challenging object classes.

An event camera detects per-pixel intensity difference and produces asynchronous event stream with low latency, high dynamic range, and low power consumption. As a trade-off, the event camera has low spatial resolution. We propose an end-to-end network to reconstruct high resolution, high dynamic range (HDR) images directly from the event stream. We evaluate our algorithm on both simulated and real-world sequences and verify that it captures fine details of a scene and outperforms the combination of the state-of-the-art event to image algorithms with the state-of-the-art super resolution schemes in many quantitative measures by large margins. We further extend our method by using the active sensor pixel (APS) frames or reconstructing images iteratively.

We present a fully automatic method to generate detailed and accurate artistic shadows from pairs of line drawing sketches and lighting directions. We also contribute a new dataset of one thousand examples of pairs of line drawings and shadows that are tagged with lighting directions. Remarkably, the generated shadows quickly communicate the underlying 3D structure of the sketched scene. Consequently, the shadows generated by our approach can be used directly or as an excellent starting point for artists. We demonstrate that the deep learning network we propose takes a hand-drawn sketch, builds a 3D model in latent space, and renders the resulting shadows. The generated shadows respect the hand-drawn lines and underlying 3D space and contain sophisticated and accurate details, such as self-shadowing effects. Moreover, the generated shadows contain artistic effects, such as rim lighting or halos appearing from backlighting, that would be achievable with traditional 3D rendering methods.

In contrast to the literature where local patterns in 3D point clouds are captured by customized convolutional operators, in this paper we study the problem of how to effectively and efficiently project such point clouds into a 2D image space so that traditional 2D convolutional neural networks (CNNs) such as U-Net can be applied for segmentation. To this end, we are motivated by graph drawing and reformulate it as an integer programming problem to learn the topology-preserving graph-to-grid mapping for each individual point cloud. To accelerate the computation in practice, we further propose a novel hierarchical approximate algorithm. With the help of the Delaunay triangulation for graph construction from point clouds and a multi-scale U-Net for segmentation, we manage to demonstrate the state-of-the-art performance on ShapeNet and PartNet, respectively, with significant improvement over the literature. Code is available at https://github.com/Zhang-VISLab.

One of the widespread solutions for non-rigid tracking has a nested-loop structure: with Gauss-Newton to minimize a tracking objective in the outer loop, and Preconditioned Conjugate Gradient (PCG) to solve a sparse linear system in the inner loop. In this paper, we employ learnable optimizations to improve tracking robustness and speed up solver convergence. First, we upgrade the tracking objective by integrating an alignment data term on deep features which are learned end-to-end through CNN. The new tracking objective can capture the global deformation which helps Gauss-Newton to jump over local minimum, leading to robust tracking on large non-rigid motions. Second, we bridge the gap between the preconditioning technique and learning method by introducing a ConditionNet which is trained to generate a preconditioner such that PCG can converge within a small number of steps. Experimental results indicate that the proposed learning method converges faster than the original PCG by a large margin.

Measuring friction coefficients between cloth and an external body is a longstanding issue in mechanical engineering, never yet addressed with a pure vision-based system. The latter offers the prospect of simpler, less invasive friction measurement protocols compared to traditional ones, and can vastly benefit from recent deep learning advances. Such a novel measurement strategy however proves challenging, as no large labelled dataset for cloth contact exists, and creating one would require thousands of physics workbench measurements with broad coverage of cloth-material pairs. Using synthetic data instead is only possible assuming the availability of a soft-body mechanical simulator with true-to-life friction physics accuracy, yet to be verified. We propose a first vision-based measurement network for friction between cloth and a substrate, using a simple and repeatable video acquisition protocol. We train our network on purely synthetic data generated by a state-of-the-art frictional contact simulator, which we carefully calibrate and validate against real experiments under controlled conditions. We show promising results on a large set of contact pairs between real cloth samples and various kinds of substrates, with 93.6% of all measurements predicted within 0.1 range of standard physics bench measurements.

We propose a novel method to use both audio and a low-resolution image to perform extreme face super-resolution (a 16x increase of the input size). When the resolution of the input image is very low (e.g., 8x8 pixels), the loss of information is so dire that important details of the original identity have been lost and audio can aid the recovery of a plausible high-resolution image. In fact, audio carries information about facial attributes, such as gender and age. To combine the aural and visual modalities, we propose a method to first build the latent representations of a face from the lone audio track and then from the lone low-resolution image. We then train a network to fuse these two representations. We show experimentally that audio can assist in recovering attributes such as the gender, the age and the identity, and thus improve the correctness of the high-resolution image reconstruction process. Our procedure does not make use of human annotation and thus can be easily trained with existing video datasets. Moreover, we show that our model builds a factorized representation of images and audio as it allows one to mix low-resolution images and audio from different videos and to generate realistic faces with semantically meaningful combinations.

We address weakly-supervised video actor-action segmentation (VAAS), which extends general video object segmentation (VOS) to additionally consider action labels of the actors. The most successful methods on VOS synthesize a pool of pseudo-annotations (PAs) and then refine them iteratively. However, they face challenges as to how to select from a massive amount of PAs high-quality ones, how to set an appropriate stop condition for weakly-supervised training, and how to initialize PAs pertaining to VAAS. To overcome these challenges, we propose a general Weakly-Supervised framework with a Wise Selection of training samples and model evaluation criterion (WS^2). Instead of blindly trusting quality-inconsistent PAs, WS^2 employs a learning-based selection to select effective PAs and a novel region integrity criterion as a stopping condition for weakly-supervised training. In addition, a 3D-Conv GCAM is devised to adapt to the VAAS task. Extensive experiments show that WS^2 achieves state-of-the-art performance on both weakly-supervised VOS and VAAS tasks and is on par with the best fully-supervised method on VAAS.

Graphs offer a natural way to formulate Multiple Object Tracking (MOT) within the tracking-by-detection paradigm. However, they also introduce a major challenge for learning methods, as defining a model that can operate on such structured domain is not trivial. As a consequence, most learning-based work has been devoted to learning better features for MOT and then using these with well-established optimization frameworks. In this work, we exploit the classical network flow formulation of MOT to define a fully differentiable framework based on Message Passing Networks (MPNs). By operating directly on the graph domain, our method can reason globally over an entire set of detections and predict final solutions. Hence, we show that learning in MOT does not need to be restricted to feature extraction, but it can also be applied to the data association step. We show a significant improvement in both MOTA and IDF1 on three publicly available benchmarks. Our code is available at https://bit.ly/motsolv.

While high resolution images contain semantically more useful information than their lower resolution counterparts, processing them is computationally more expensive, and in some applications, e.g. remote sensing, they can be much more expensive to acquire. For these reasons, it is desirable to develop an automatic method to selectively use high resolution data when necessary while maintaining accuracy and reducing acquisition/run-time cost. In this direction, we propose PatchDrop a reinforcement learning approach to dynamically identify when and where to use/acquire high resolution data conditioned on the paired, cheap, low resolution images. We conduct experiments on CIFAR10, CIFAR100, ImageNet and fMoW datasets where we use significantly less high resolution data while maintaining similar accuracy to models which use full high resolution images.