Learning 3D representations by fusing point cloud and multi-view data has been proven to be fairly effective. While prior works typically focus on exploiting global features of the two modalities, in this paper we argue that more discriminative featu
res can be derived by modeling where to fuse. To investigate this, we propose a novel Correspondence-Aware Point-view Fusion Net (CAPNet). The core element of CAP-Net is a module named Correspondence-Aware Fusion (CAF) which integrates the local features of the two modalities based on their correspondence scores. We further propose to filter out correspondence scores with low values to obtain salient local correspondences, which reduces redundancy for the fusion process. In our CAP-Net, we utilize the CAF modules to fuse the multi-scale features of the two modalities both bidirectionally and hierarchically in order to obtain more informative features. Comprehensive evaluations on popular 3D shape benchmarks covering 3D object classification and retrieval show the superiority of the proposed framework.
This paper presents a neural network built upon Transformers, namely PlaneTR, to simultaneously detect and reconstruct planes from a single image. Different from previous methods, PlaneTR jointly leverages the context information and the geometric st
ructures in a sequence-to-sequence way to holistically detect plane instances in one forward pass. Specifically, we represent the geometric structures as line segments and conduct the network with three main components: (i) context and line segments encoders, (ii) a structure-guided plane decoder, (iii) a pixel-wise plane embedding decoder. Given an image and its detected line segments, PlaneTR generates the context and line segment sequences via two specially designed encoders and then feeds them into a Transformers-based decoder to directly predict a sequence of plane instances by simultaneously considering the context and global structure cues. Finally, the pixel-wise embeddings are computed to assign each pixel to one predicted plane instance which is nearest to it in embedding space. Comprehensive experiments demonstrate that PlaneTR achieves a state-of-the-art performance on the ScanNet and NYUv2 datasets.
Human vision is able to capture the part-whole hierarchical information from the entire scene. This paper presents the Visual Parser (ViP) that explicitly constructs such a hierarchy with transformers. ViP divides visual representations into two leve
ls, the part level and the whole level. Information of each part represents a combination of several independent vectors within the whole. To model the representations of the two levels, we first encode the information from the whole into part vectors through an attention mechanism, then decode the global information within the part vectors back into the whole representation. By iteratively parsing the two levels with the proposed encoder-decoder interaction, the model can gradually refine the features on both levels. Experimental results demonstrate that ViP can achieve very competitive performance on three major tasks e.g. classification, detection and instance segmentation. In particular, it can surpass the previous state-of-the-art CNN backbones by a large margin on object detection. The tiny model of the ViP family with $7.2times$ fewer parameters and $10.9times$ fewer FLOPS can perform comparably with the largest model ResNeXt-101-64$times$4d of ResNe(X)t family. Visualization results also demonstrate that the learnt parts are highly informative of the predicting class, making ViP more explainable than previous fundamental architectures. Code is available at https://github.com/kevin-ssy/ViP.
Leveraging the advances of natural language processing, most recent scene text recognizers adopt an encoder-decoder architecture where text images are first converted to representative features and then a sequence of characters via `direct decoding.
However, scene text images suffer from rich noises of different sources such as complex background and geometric distortions which often confuse the decoder and lead to incorrect alignment of visual features at noisy decoding time steps. This paper presents I2C2W, a novel scene text recognizer that is accurate and tolerant to various noises in scenes. I2C2W consists of an image-to-character module (I2C) and a character-to-word module (C2W) which are complementary and can be trained end-to-end. I2C detects characters and predicts their relative positions in a word. It strives to detect all possible characters including incorrect and redundant ones based on different alignments of visual features without the restriction of time steps. Taking the detected characters as input, C2W learns from character semantics and their positions to filter out incorrect and redundant detection and produce the final word recognition. Extensive experiments over seven public datasets show that I2C2W achieves superior recognition performances and outperforms the state-of-the-art by large margins on challenging irregular scene text datasets.
Current developments in temporal event or action localization usually target actions captured by a single camera. However, extensive events or actions in the wild may be captured as a sequence of shots by multiple cameras at different positions. In t
his paper, we propose a new and challenging task called multi-shot temporal event localization, and accordingly, collect a large scale dataset called MUlti-Shot EventS (MUSES). MUSES has 31,477 event instances for a total of 716 video hours. The core nature of MUSES is the frequent shot cuts, for an average of 19 shots per instance and 176 shots per video, which induces large intrainstance variations. Our comprehensive evaluations show that the state-of-the-art method in temporal action localization only achieves an mAP of 13.1% at IoU=0.5. As a minor contribution, we present a simple baseline approach for handling the intra-instance variations, which reports an mAP of 18.9% on MUSES and 56.9% on THUMOS14 at IoU=0.5. To facilitate research in this direction, we release the dataset and the project code at https://songbai.site/muses/ .
Semantic segmentation (SS) is an important perception manner for self-driving cars and robotics, which classifies each pixel into a pre-determined class. The widely-used cross entropy (CE) loss-based deep networks has achieved significant progress w.
r.t. the mean Intersection-over Union (mIoU). However, the cross entropy loss can not take the different importance of each class in an self-driving system into account. For example, pedestrians in the image should be much more important than the surrounding buildings when make a decisions in the driving, so their segmentation results are expected to be as accurate as possible. In this paper, we propose to incorporate the importance-aware inter-class correlation in a Wasserstein training framework by configuring its ground distance matrix. The ground distance matrix can be pre-defined following a priori in a specific task, and the previous importance-ignored methods can be the particular cases. From an optimization perspective, we also extend our ground metric to a linear, convex or concave increasing function $w.r.t.$ pre-defined ground distance. We evaluate our method on CamVid and Cityscapes datasets with different backbones (SegNet, ENet, FCN and Deeplab) in a plug and play fashion. In our extenssive experiments, Wasserstein loss demonstrates superior segmentation performance on the predefined critical classes for safe-driving.
This paper presents a fast and parsimonious parsing method to accurately and robustly detect a vectorized wireframe in an input image with a single forward pass. The proposed method is end-to-end trainable, consisting of three components: (i) line se
gment and junction proposal generation, (ii) line segment and junction matching, and (iii) line segment and junction verification. For computing line segment proposals, a novel exact dual representation is proposed which exploits a parsimonious geometric reparameterization for line segments and forms a holistic 4-dimensional attraction field map for an input image. Junctions can be treated as the basins in the attraction field. The proposed method is thus called Holistically-Attracted Wireframe Parser (HAWP). In experiments, the proposed method is tested on two benchmarks, the Wireframe dataset, and the YorkUrban dataset. On both benchmarks, it obtains state-of-the-art performance in terms of accuracy and efficiency. For example, on the Wireframe dataset, compared to the previous state-of-the-art method L-CNN, it improves the challenging mean structural average precision (msAP) by a large margin ($2.8%$ absolute improvements) and achieves 29.5 FPS on single GPU ($89%$ relative improvement). A systematic ablation study is performed to further justify the proposed method.
This paper presents regional attraction of line segment maps, and hereby poses the problem of line segment detection (LSD) as a problem of region coloring. Given a line segment map, the proposed regional attraction first establishes the relationship
between line segments and regions in the image lattice. Based on this, the line segment map is equivalently transformed to an attraction field map (AFM), which can be remapped to a set of line segments without loss of information. Accordingly, we develop an end-to-end framework to learn attraction field maps for raw input images, followed by a squeeze module to detect line segments. Apart from existing works, the proposed detector properly handles the local ambiguity and does not rely on the accurate identification of edge pixels. Comprehensive experiments on the Wireframe dataset and the YorkUrban dataset demonstrate the superiority of our method. In particular, we achieve an F-measure of 0.831 on the Wireframe dataset, advancing the state-of-the-art performance by 10.3 percent.
The formation of interfacial moire patterns from angular and/or lattice mismatch has become a powerful approach to engineer a range of quantum phenomena in van der Waals heterostructures. For long-lived and valley-polarized interlayer excitons in tra
nsition-metal dichalcogenide (TMDC) heterobilayers, signatures of quantum confinement by the moire landscape have been reported in recent experimental studies. Such moire confinement has offered the exciting possibility to tailor new excitonic systems, such as ordered arrays of zero-dimensional (0D) quantum emitters and their coupling into topological superlattices. A remarkable nature of the moire potential is its dramatic response to strain, where a small uniaxial strain can tune the array of quantum-dot-like 0D traps into parallel stripes of one-dimensional (1D) quantum wires. Here, we present direct evidence for the 1D moire potentials from real space imaging and the corresponding 1D moire excitons from photoluminescence (PL) emission in MoSe2/WSe2 heterobilayers. Whereas the 0D moire excitons display quantum emitter-like sharp PL peaks with circular polarization, the PL emission from 1D moire excitons has linear polarization and two orders of magnitude higher intensity. The results presented here establish strain engineering as a powerful new method to tailor moire potentials as well as their optical and electronic responses on demand.
In object detection, keypoint-based approaches often suffer a large number of incorrect object bounding boxes, arguably due to the lack of an additional look into the cropped regions. This paper presents an efficient solution which explores the visua
l patterns within each cropped region with minimal costs. We build our framework upon a representative one-stage keypoint-based detector named CornerNet. Our approach, named CenterNet, detects each object as a triplet, rather than a pair, of keypoints, which improves both precision and recall. Accordingly, we design two customized modules named cascade corner pooling and center pooling, which play the roles of enriching information collected by both top-left and bottom-right corners and providing more recognizable information at the central regions, respectively. On the MS-COCO dataset, CenterNet achieves an AP of 47.0%, which outperforms all existing one-stage detectors by at least 4.9%. Meanwhile, with a faster inference speed, CenterNet demonstrates quite comparable performance to the top-ranked two-stage detectors. Code is available at https://github.com/Duankaiwen/CenterNet.
