Learning robust feature matching between the template and search area is crucial for 3D Siamese tracking. The core of Siamese feature matching is how to assign high feature similarity on the corresponding points between the template and search area for precise object localization. In this paper, we propose a novel point cloud registration-driven Siamese tracking framework, with the intuition that spatially aligned corresponding points (via 3D registration) tend to achieve consistent feature representations. Specifically, our method consists of two modules, including a tracking-specific nonlocal registration module and a registration-aided Sinkhorn template-feature aggregation module. The registration module targets at the precise spatial alignment between the template and search area. The tracking-specific spatial distance constraint is proposed to refine the cross-attention weights in the nonlocal module for discriminative feature learning. Then, we use the weighted SVD to compute the rigid transformation between the template and search area, and align them to achieve the desired spatially aligned corresponding points. For the feature aggregation model, we formulate the feature matching between the transformed template and search area as an optimal transport problem and utilize the Sinkhorn optimization to search for the outlier-robust matching solution. Also, a registration-aided spatial distance map is built to improve the matching robustness in indistinguishable regions (e.g., smooth surface). Finally, guided by the obtained feature matching map, we aggregate the target information from the template into the search area to construct the target-specific feature, which is then fed into a CenterPoint-like detection head for object localization. Extensive experiments on KITTI, NuScenes and Waymo datasets verify the effectiveness of our proposed method.
相關內容
Realistic reconstruction of two hands interacting with objects is a new and challenging problem that is essential for building personalized Virtual and Augmented Reality environments. Graph Convolutional networks (GCNs) allow for the preservation of the topologies of hands poses and shapes by modeling them as a graph. In this work, we propose the THOR-Net which combines the power of GCNs, Transformer, and self-supervision to realistically reconstruct two hands and an object from a single RGB image. Our network comprises two stages; namely the features extraction stage and the reconstruction stage. In the features extraction stage, a Keypoint RCNN is used to extract 2D poses, features maps, heatmaps, and bounding boxes from a monocular RGB image. Thereafter, this 2D information is modeled as two graphs and passed to the two branches of the reconstruction stage. The shape reconstruction branch estimates meshes of two hands and an object using our novel coarse-to-fine GraFormer shape network. The 3D poses of the hands and objects are reconstructed by the other branch using a GraFormer network. Finally, a self-supervised photometric loss is used to directly regress the realistic textured of each vertex in the hands' meshes. Our approach achieves State-of-the-art results in Hand shape estimation on the HO-3D dataset (10.0mm) exceeding ArtiBoost (10.8mm). It also surpasses other methods in hand pose estimation on the challenging two hands and object (H2O) dataset by 5mm on the left-hand pose and 1 mm on the right-hand pose.
Remarkable performance from Transformer networks in Natural Language Processing promote the development of these models in dealing with computer vision tasks such as image recognition and segmentation. In this paper, we introduce a novel framework, called Multi-level Multi-scale Point Transformer (MLMSPT) that works directly on the irregular point clouds for representation learning. Specifically, a point pyramid transformer is investigated to model features with diverse resolutions or scales we defined, followed by a multi-level transformer module to aggregate contextual information from different levels of each scale and enhance their interactions. While a multi-scale transformer module is designed to capture the dependencies among representations across different scales. Extensive evaluation on public benchmark datasets demonstrate the effectiveness and the competitive performance of our methods on 3D shape classification, segmentation tasks.
Unsupervised object discovery (UOD) has recently shown encouraging progress with the adoption of pre-trained Transformer features. However, current methods based on Transformers mainly focus on designing the localization head (e.g., seed selection-expansion and normalized cut) and overlook the importance of improving Transformer features. In this work, we handle UOD task from the perspective of feature enhancement and propose FOReground guidance and MUlti-LAyer feature fusion for unsupervised object discovery, dubbed FORMULA. Firstly, we present a foreground guidance strategy with an off-the-shelf UOD detector to highlight the foreground regions on the feature maps and then refine object locations in an iterative fashion. Moreover, to solve the scale variation issues in object detection, we design a multi-layer feature fusion module that aggregates features responding to objects at different scales. The experiments on VOC07, VOC12, and COCO 20k show that the proposed FORMULA achieves new state-of-the-art results on unsupervised object discovery. The code will be released at //github.com/VDIGPKU/FORMULA.
Actions are about how we interact with the environment, including other people, objects, and ourselves. In this paper, we propose a novel multi-modal Holistic Interaction Transformer Network (HIT) that leverages the largely ignored, but critical hand and pose information essential to most human actions. The proposed "HIT" network is a comprehensive bi-modal framework that comprises an RGB stream and a pose stream. Each of them separately models person, object, and hand interactions. Within each sub-network, an Intra-Modality Aggregation module (IMA) is introduced that selectively merges individual interaction units. The resulting features from each modality are then glued using an Attentive Fusion Mechanism (AFM). Finally, we extract cues from the temporal context to better classify the occurring actions using cached memory. Our method significantly outperforms previous approaches on the J-HMDB, UCF101-24, and MultiSports datasets. We also achieve competitive results on AVA. The code will be available at //github.com/joslefaure/HIT.
Reconstructing 3D layouts from multiple $360^{\circ}$ panoramas has received increasing attention recently as estimating a complete layout of a large-scale and complex room from a single panorama is very difficult. The state-of-the-art method, called PSMNet, introduces the first learning-based framework that jointly estimates the room layout and registration given a pair of panoramas. However, PSMNet relies on an approximate (i.e., "noisy") registration as input. Obtaining this input requires a solution for wide baseline registration which is a challenging problem. In this work, we present a complete multi-view panoramic layout estimation framework that jointly learns panorama registration and layout estimation given a pair of panoramas without relying on a pose prior. The major improvement over PSMNet comes from a novel Geometry-aware Panorama Registration Network or GPR-Net that effectively tackles the wide baseline registration problem by exploiting the layout geometry and computing fine-grained correspondences on the layout boundaries, instead of the global pixel-space. Our architecture consists of two parts. First, given two panoramas, we adopt a vision transformer to learn a set of 1D horizon features sampled on the panorama. These 1D horizon features encode the depths of individual layout boundary samples and the correspondence and covisibility maps between layout boundaries. We then exploit a non-linear registration module to convert these 1D horizon features into a set of corresponding 2D boundary points on the layout. Finally, we estimate the final relative camera pose via RANSAC and obtain the complete layout simply by taking the union of registered layouts. Experimental results indicate that our method achieves state-of-the-art performance in both panorama registration and layout estimation on a large-scale indoor panorama dataset ZInD.
Correlation acts as a critical role in the tracking field, especially in recent popular Siamese-based trackers. The correlation operation is a simple fusion manner to consider the similarity between the template and the search region. However, the correlation operation itself is a local linear matching process, leading to lose semantic information and fall into local optimum easily, which may be the bottleneck of designing high-accuracy tracking algorithms. Is there any better feature fusion method than correlation? To address this issue, inspired by Transformer, this work presents a novel attention-based feature fusion network, which effectively combines the template and search region features solely using attention. Specifically, the proposed method includes an ego-context augment module based on self-attention and a cross-feature augment module based on cross-attention. Finally, we present a Transformer tracking (named TransT) method based on the Siamese-like feature extraction backbone, the designed attention-based fusion mechanism, and the classification and regression head. Experiments show that our TransT achieves very promising results on six challenging datasets, especially on large-scale LaSOT, TrackingNet, and GOT-10k benchmarks. Our tracker runs at approximatively 50 fps on GPU. Code and models are available at //github.com/chenxin-dlut/TransT.
Modern neural network training relies heavily on data augmentation for improved generalization. After the initial success of label-preserving augmentations, there has been a recent surge of interest in label-perturbing approaches, which combine features and labels across training samples to smooth the learned decision surface. In this paper, we propose a new augmentation method that leverages the first and second moments extracted and re-injected by feature normalization. We replace the moments of the learned features of one training image by those of another, and also interpolate the target labels. As our approach is fast, operates entirely in feature space, and mixes different signals than prior methods, one can effectively combine it with existing augmentation methods. We demonstrate its efficacy across benchmark data sets in computer vision, speech, and natural language processing, where it consistently improves the generalization performance of highly competitive baseline networks.
We investigate the problem of automatically determining what type of shoe left an impression found at a crime scene. This recognition problem is made difficult by the variability in types of crime scene evidence (ranging from traces of dust or oil on hard surfaces to impressions made in soil) and the lack of comprehensive databases of shoe outsole tread patterns. We find that mid-level features extracted by pre-trained convolutional neural nets are surprisingly effective descriptors for this specialized domains. However, the choice of similarity measure for matching exemplars to a query image is essential to good performance. For matching multi-channel deep features, we propose the use of multi-channel normalized cross-correlation and analyze its effectiveness. Our proposed metric significantly improves performance in matching crime scene shoeprints to laboratory test impressions. We also show its effectiveness in other cross-domain image retrieval problems: matching facade images to segmentation labels and aerial photos to map images. Finally, we introduce a discriminatively trained variant and fine-tune our system through our proposed metric, obtaining state-of-the-art performance.
This paper introduces an online model for object detection in videos designed to run in real-time on low-powered mobile and embedded devices. Our approach combines fast single-image object detection with convolutional long short term memory (LSTM) layers to create an interweaved recurrent-convolutional architecture. Additionally, we propose an efficient Bottleneck-LSTM layer that significantly reduces computational cost compared to regular LSTMs. Our network achieves temporal awareness by using Bottleneck-LSTMs to refine and propagate feature maps across frames. This approach is substantially faster than existing detection methods in video, outperforming the fastest single-frame models in model size and computational cost while attaining accuracy comparable to much more expensive single-frame models on the Imagenet VID 2015 dataset. Our model reaches a real-time inference speed of up to 15 FPS on a mobile CPU.
Recently, deep learning has achieved very promising results in visual object tracking. Deep neural networks in existing tracking methods require a lot of training data to learn a large number of parameters. However, training data is not sufficient for visual object tracking as annotations of a target object are only available in the first frame of a test sequence. In this paper, we propose to learn hierarchical features for visual object tracking by using tree structure based Recursive Neural Networks (RNN), which have fewer parameters than other deep neural networks, e.g. Convolutional Neural Networks (CNN). First, we learn RNN parameters to discriminate between the target object and background in the first frame of a test sequence. Tree structure over local patches of an exemplar region is randomly generated by using a bottom-up greedy search strategy. Given the learned RNN parameters, we create two dictionaries regarding target regions and corresponding local patches based on the learned hierarchical features from both top and leaf nodes of multiple random trees. In each of the subsequent frames, we conduct sparse dictionary coding on all candidates to select the best candidate as the new target location. In addition, we online update two dictionaries to handle appearance changes of target objects. Experimental results demonstrate that our feature learning algorithm can significantly improve tracking performance on benchmark datasets.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191