Jun Wang

Jun Wang, Ying Cui, Dongyan Guo et al.

Point cloud completion referring to completing 3D shapes from partial 3D point clouds is a fundamental problem for 3D point cloud analysis tasks. Benefiting from the development of deep neural networks, researches on point cloud completion have made great progress in recent years. However, the explicit local region partition like kNNs involved in existing methods makes them sensitive to the density distribution of point clouds. Moreover, it serves limited receptive fields that prevent capturing features from long-range context information. To solve the problems, we leverage the cross-attention and self-attention mechanisms to design novel neural network for processing point cloud in a per-point manner to eliminate kNNs. Two essential blocks Geometric Details Perception (GDP) and Self-Feature Augment (SFA) are proposed to establish the short-range and long-range structural relationships directly among points in a simple yet effective way via attention mechanism. Then based on GDP and SFA, we construct a new framework with popular encoder-decoder architecture for point cloud completion. The proposed framework, namely PointAttN, is simple, neat and effective, which can precisely capture the structural information of 3D shapes and predict complete point clouds with highly detailed geometries. Experimental results demonstrate that our PointAttN outperforms state-of-the-art methods by a large margin on popular benchmarks like Completion3D and PCN. Code is available at: https://github.com/ohhhyeahhh/PointAttN

Mingqiang Wei, Zeyong Wei, Haoran Zhou et al.

Convolution on 3D point clouds is widely researched yet far from perfect in geometric deep learning. The traditional wisdom of convolution characterises feature correspondences indistinguishably among 3D points, arising an intrinsic limitation of poor distinctive feature learning. In this paper, we propose Adaptive Graph Convolution (AGConv) for wide applications of point cloud analysis. AGConv generates adaptive kernels for points according to their dynamically learned features. Compared with the solution of using fixed/isotropic kernels, AGConv improves the flexibility of point cloud convolutions, effectively and precisely capturing the diverse relations between points from different semantic parts. Unlike the popular attentional weight schemes, AGConv implements the adaptiveness inside the convolution operation instead of simply assigning different weights to the neighboring points. Extensive evaluations clearly show that our method outperforms state-of-the-arts of point cloud classification and segmentation on various benchmark datasets.Meanwhile, AGConv can flexibly serve more point cloud analysis approaches to boost their performance. To validate its flexibility and effectiveness, we explore AGConv-based paradigms of completion, denoising, upsampling, registration and circle extraction, which are comparable or even superior to their competitors. Our code is available at https://github.com/hrzhou2/AdaptConv-master.

Haoran Zhou, Honghua Chen, Yingkui Zhang et al.

Point normal, as an intrinsic geometric property of 3D objects, not only serves conventional geometric tasks such as surface consolidation and reconstruction, but also facilitates cutting-edge learning-based techniques for shape analysis and generation. In this paper, we propose a normal refinement network, called Refine-Net, to predict accurate normals for noisy point clouds. Traditional normal estimation wisdom heavily depends on priors such as surface shapes or noise distributions, while learning-based solutions settle for single types of hand-crafted features. Differently, our network is designed to refine the initial normal of each point by extracting additional information from multiple feature representations. To this end, several feature modules are developed and incorporated into Refine-Net by a novel connection module. Besides the overall network architecture of Refine-Net, we propose a new multi-scale fitting patch selection scheme for the initial normal estimation, by absorbing geometry domain knowledge. Also, Refine-Net is a generic normal estimation framework: 1) point normals obtained from other methods can be further refined, and 2) any feature module related to the surface geometric structures can be potentially integrated into the framework. Qualitative and quantitative evaluations demonstrate the clear superiority of Refine-Net over the state-of-the-arts on both synthetic and real-scanned datasets. Our code is available at https://github.com/hrzhou2/refinenet.

Zhilei Chen, Honghua Chen, Lina Gong et al.

High-confidence overlap prediction and accurate correspondences are critical for cutting-edge models to align paired point clouds in a partial-to-partial manner. However, there inherently exists uncertainty between the overlapping and non-overlapping regions, which has always been neglected and significantly affects the registration performance. Beyond the current wisdom, we propose a novel uncertainty-aware overlap prediction network, dubbed UTOPIC, to tackle the ambiguous overlap prediction problem; to our knowledge, this is the first to explicitly introduce overlap uncertainty to point cloud registration. Moreover, we induce the feature extractor to implicitly perceive the shape knowledge through a completion decoder, and present a geometric relation embedding for Transformer to obtain transformation-invariant geometry-aware feature representations. With the merits of more reliable overlap scores and more precise dense correspondences, UTOPIC can achieve stable and accurate registration results, even for the inputs with limited overlapping areas. Extensive quantitative and qualitative experiments on synthetic and real benchmarks demonstrate the superiority of our approach over state-of-the-art methods.

Yangheng Zhao, Jun Wang, Xiaolong Li et al.

3D point cloud semantic segmentation is one of the fundamental tasks for 3D scene understanding and has been widely used in the metaverse applications. Many recent 3D semantic segmentation methods learn a single prototype (classifier weights) for each semantic class, and classify 3D points according to their nearest prototype. However, learning only one prototype for each class limits the model's ability to describe the high variance patterns within a class. Instead of learning a single prototype for each class, in this paper, we propose to use an adaptive number of prototypes to dynamically describe the different point patterns within a semantic class. With the powerful capability of vision transformer, we design a Number-Adaptive Prototype Learning (NAPL) model for point cloud semantic segmentation. To train our NAPL model, we propose a simple yet effective prototype dropout training strategy, which enables our model to adaptively produce prototypes for each class. The experimental results on SemanticKITTI dataset demonstrate that our method achieves 2.3% mIoU improvement over the baseline model based on the point-wise classification paradigm.

Fei Hu, Honghua Chen, Xuequan Lu et al.

How will you repair a physical object with large missings? You may first recover its global yet coarse shape and stepwise increase its local details. We are motivated to imitate the above physical repair procedure to address the point cloud completion task. We propose a novel stepwise point cloud completion network (SPCNet) for various 3D models with large missings. SPCNet has a hierarchical bottom-to-up network architecture. It fulfills shape completion in an iterative manner, which 1) first infers the global feature of the coarse result; 2) then infers the local feature with the aid of global feature; and 3) finally infers the detailed result with the help of local feature and coarse result. Beyond the wisdom of simulating the physical repair, we newly design a cycle loss %based training strategy to enhance the generalization and robustness of SPCNet. Extensive experiments clearly show the superiority of our SPCNet over the state-of-the-art methods on 3D point clouds with large missings.

Honghua Chen, Mingqiang Wei, Jun Wang

Mesh denoising is a fundamental problem in digital geometry processing. It seeks to remove surface noise, while preserving surface intrinsic signals as accurately as possible. While the traditional wisdom has been built upon specialized priors to smooth surfaces, learning-based approaches are making their debut with great success in generalization and automation. In this work, we provide a comprehensive review of the advances in mesh denoising, containing both traditional geometric approaches and recent learning-based methods. First, to familiarize readers with the denoising tasks, we summarize four common issues in mesh denoising. We then provide two categorizations of the existing denoising methods. Furthermore, three important categories, including optimization-, filter-, and data-driven-based techniques, are introduced and analyzed in detail, respectively. Both qualitative and quantitative comparisons are illustrated, to demonstrate the effectiveness of the state-of-the-art denoising methods. Finally, potential directions of future work are pointed out to solve the common problems of these approaches. A mesh denoising benchmark is also built in this work, and future researchers will easily and conveniently evaluate their methods with the state-of-the-art approaches.

Xiaorui Wang, Jun Wang, Xin Tang et al.

Filter pruning is widely adopted to compress and accelerate the Convolutional Neural Networks (CNNs), but most previous works ignore the relationship between filters and channels in different layers. Processing each layer independently fails to utilize the collaborative relationship across layers. In this paper, we intuitively propose a novel pruning method by explicitly leveraging the Filters Similarity in Consecutive Layers (FSCL). FSCL compresses models by pruning filters whose corresponding features are more worthless in the model. The extensive experiments demonstrate the effectiveness of FSCL, and it yields remarkable improvement over state-of-the-art on accuracy, FLOPs and parameter reduction on several benchmark models and datasets.

Yiguo He, Junjie Zhu, Yiying Li et al.

The application of Vision-language foundation models (VLFMs) to remote sensing (RS) imagery has garnered significant attention due to their superior capability in various downstream tasks. A key challenge lies in the scarcity of high-quality, large-scale, image-text paired training data. Recently, several works introduced extensive image-text datasets for RS and trained their VLFMs. However, due to the rudimentary methods used for generating captions, the quality of datasets is suboptimal, requiring larger volumes of training data, while only yielding modest performance improvements. In this paper, we propose a two-stage method named MpGI(Multi-Perspective Generation and Integration) for generating high-quality text captions for RS images. Firstly, we generate distinct and detailed descriptions from different perspectives using Rule-MLLM(Multimodal Large Language Model) Relay Generation and MLLMs generation methods. Next, we utilize Large Language Models (LLMs) to integrate these diverse descriptions into comprehensive captions, capturing details from multiple perspectives. Finally, we have created the HQRS-IT-210K dataset, including about 210,000 RS images and 1.3 million captions. We fine-tuned two VLFMs using our dataset: CLIP, a discriminative model, and CoCa, an image-to-text generative model. This process resulted in our proposed HQRS-CLIP and RS-CoCa models. Experimental results demonstrate that HQRS-CLIP surpassed the previous SOTA RS CLIP model in various downstream tasks while using only 4.2\% of the training data. RS-CoCa outperforms other advanced approaches across benchmark datasets and can generate captions for RS images that rival or even exceed manual annotations. Dataset, pre-trained models, and codes will be released at https://github.com/YiguoHe/HQRS-210K-and-HQRS-CLIP.

Yiguo He, Xinjun Cheng, Junjie Zhu et al.

Vision Language Models (VLMs) have achieved remarkable breakthroughs in the field of remote sensing in recent years. Synthetic Aperture Radar (SAR) imagery, with its all-weather capability, is essential in remote sensing, yet the lack of large-scale, high-quality SAR image-text datasets hinders its semantic understanding. In this paper, we construct SAR-TEXT, a large-scale and high-quality dataset consisting of over 130,000 SAR image-text pairs. To construct the SAR-TEXT dataset, we design the SAR-Narrator framework, which generates textual descriptions for SAR images through a multi-stage strategy. To verify the effectiveness of the SAR-TEXT dataset, we conduct experiments on three typical vision-language tasks: image-text retrieval, image captioning, and visual question answering (VQA). Specifically, we construct three representative models on SAR-TEXT: SAR-RS-CLIP, SAR-RS-CoCa, and SAR-GPT. SAR-RS-CLIP achieves notable improvements in retrieval performance, boosting average recall by 12.97% and 10.0% on the OSdataset_512 and HRSID test sets, respectively. In the captioning task, SAR-RS-CoCa achieves significant improvements over the original CoCa models in terms of BLEU-4, SPICE, and CIDEr scores. In the VQA task, SAR-GPT outperforms baseline and single-stage models on multiple SAR-VQA datasets, demonstrating stronger semantic understanding and reasoning ability, as further confirmed by qualitative results. It is worth noting that, as a flexible captioning tool, SAR-Narrator can be readily adopted by the community to construct larger-scale SAR image-text datasets. All code, pretrained models, and the SAR-Text dataset are publicly available at: https://github.com/YiguoHe/SAR-TEXT.

Yuexing Ding, Jun Wang, Hongbing Lyu

In the field of medical image segmentation, challenges such as indistinct lesion features, ambiguous boundaries,and multi-scale characteristics have long revailed. This paper proposes an improved method named Intensity-Spatial Dual Masked AutoEncoder (ISD-MAE). Based on the tissue-contrast semi-masked autoencoder, a Masked AutoEncoder (MAE) branch is introduced to perform intensity masking and spatial masking operations on chest CT images for multi-scale feature learning and segmentation tasks. The model utilizes a dual-branch structure and contrastive learning to enhance the ability to learn tissue features and boundary details. Experiments are conducted on multiple 2D and 3D datasets. The results show that ISD-MAE significantly outperforms other methods in 2D pneumonia and mediastinal tumor segmentation tasks. For example, the Dice score reaches 90.10% on the COVID19 LESION dataset, and the performance is relatively stable. However, there is still room for improvement on 3D datasets. In response to this, improvement directions are proposed, including optimizing the loss function, using enhanced 3D convolution blocks, and processing datasets from multiple perspectives.Our code is available at:https://github.com/prowontheus/ISD-MAE.

Tianrui Guan, Jun Wang, Shiyi Lan et al.

We present a novel architecture for 3D object detection, M3DeTR, which combines different point cloud representations (raw, voxels, bird-eye view) with different feature scales based on multi-scale feature pyramids. M3DeTR is the first approach that unifies multiple point cloud representations, feature scales, as well as models mutual relationships between point clouds simultaneously using transformers. We perform extensive ablation experiments that highlight the benefits of fusing representation and scale, and modeling the relationships. Our method achieves state-of-the-art performance on the KITTI 3D object detection dataset and Waymo Open Dataset. Results show that M3DeTR improves the baseline significantly by 1.48% mAP for all classes on Waymo Open Dataset. In particular, our approach ranks 1st on the well-known KITTI 3D Detection Benchmark for both car and cyclist classes, and ranks 1st on Waymo Open Dataset with single frame point cloud input. Our code is available at: https://github.com/rayguan97/M3DETR.

Yuang Liu, Wei Zhang, Jun Wang

Model quantization is a promising approach to compress deep neural networks and accelerate inference, making it possible to be deployed on mobile and edge devices. To retain the high performance of full-precision models, most existing quantization methods focus on fine-tuning quantized model by assuming training datasets are accessible. However, this assumption sometimes is not satisfied in real situations due to data privacy and security issues, thereby making these quantization methods not applicable. To achieve zero-short model quantization without accessing training data, a tiny number of quantization methods adopt either post-training quantization or batch normalization statistics-guided data generation for fine-tuning. However, both of them inevitably suffer from low performance, since the former is a little too empirical and lacks training support for ultra-low precision quantization, while the latter could not fully restore the peculiarities of original data and is often low efficient for diverse data generation. To address the above issues, we propose a zero-shot adversarial quantization (ZAQ) framework, facilitating effective discrepancy estimation and knowledge transfer from a full-precision model to its quantized model. This is achieved by a novel two-level discrepancy modeling to drive a generator to synthesize informative and diverse data examples to optimize the quantized model in an adversarial learning fashion. We conduct extensive experiments on three fundamental vision tasks, demonstrating the superiority of ZAQ over the strong zero-shot baselines and validating the effectiveness of its main components. Code is available at <https://git.io/Jqc0y>.

Qian Xie, Yu-Kun Lai, Jing Wu et al.

In this paper, we address the 3D object detection task by capturing multi-level contextual information with the self-attention mechanism and multi-scale feature fusion. Most existing 3D object detection methods recognize objects individually, without giving any consideration on contextual information between these objects. Comparatively, we propose Multi-Level Context VoteNet (MLCVNet) to recognize 3D objects correlatively, building on the state-of-the-art VoteNet. We introduce three context modules into the voting and classifying stages of VoteNet to encode contextual information at different levels. Specifically, a Patch-to-Patch Context (PPC) module is employed to capture contextual information between the point patches, before voting for their corresponding object centroid points. Subsequently, an Object-to-Object Context (OOC) module is incorporated before the proposal and classification stage, to capture the contextual information between object candidates. Finally, a Global Scene Context (GSC) module is designed to learn the global scene context. We demonstrate these by capturing contextual information at patch, object and scene levels. Our method is an effective way to promote detection accuracy, achieving new state-of-the-art detection performance on challenging 3D object detection datasets, i.e., SUN RGBD and ScanNet. We also release our code at https://github.com/NUAAXQ/MLCVNet.

Qiyu Hou, Jun Wang, Meixuan Qiao et al.

To overcome the limitations and challenges of current automatic table data annotation methods and random table data synthesis approaches, we propose a novel method for synthesizing annotation data specifically designed for table recognition. This method utilizes the structure and content of existing complex tables, facilitating the efficient creation of tables that closely replicate the authentic styles found in the target domain. By leveraging the actual structure and content of tables from Chinese financial announcements, we have developed the first extensive table annotation dataset in this domain. We used this dataset to train several recent deep learning-based end-to-end table recognition models. Additionally, we have established the inaugural benchmark for real-world complex tables in the Chinese financial announcement domain, using it to assess the performance of models trained on our synthetic data, thereby effectively validating our method's practicality and effectiveness. Furthermore, we applied our synthesis method to augment the FinTabNet dataset, extracted from English financial announcements, by increasing the proportion of tables with multiple spanning cells to introduce greater complexity. Our experiments show that models trained on this augmented dataset achieve comprehensive improvements in performance, especially in the recognition of tables with multiple spanning cells.

Huadong Tang, Youpeng Zhao, Yan Huang et al.

It is widely agreed that open-vocabulary-based approaches outperform classical closed-set training solutions for recognizing unseen objects in images for semantic segmentation. Existing open-vocabulary approaches leverage vision-language models, such as CLIP, to align visual features with rich semantic features acquired through pre-training on large-scale vision-language datasets. However, the text prompts employed in these methods are short phrases based on fixed templates, failing to capture comprehensive object attributes. Moreover, while the CLIP model excels at exploiting image-level features, it is less effective at pixel-level representation, which is crucial for semantic segmentation tasks. In this work, we propose to alleviate the above-mentioned issues by leveraging multiple large-scale models to enhance the alignment between fine-grained visual features and enriched linguistic features. Specifically, our method employs large language models (LLMs) to generate enriched language prompts with diverse visual attributes for each category, including color, shape/size, and texture/material. Additionally, for enhanced visual feature extraction, the SAM model is adopted as a supplement to the CLIP visual encoder through a proposed learnable weighted fusion strategy. Built upon these techniques, our method, termed LMSeg, achieves state-of-the-art performance across all major open-vocabulary segmentation benchmarks. The code will be made available soon.

Jian Hu, Zixu Cheng, Shaogang Gong et al.

Video Temporal Grounding (TG) aims to temporally locate video segments matching a natural language description (a query) in a long video. While Vision-Language Models (VLMs) are effective at holistic semantic matching, they often struggle with fine-grained temporal localisation. Recently, Group Relative Policy Optimisation (GRPO) reformulates the inference process as a reinforcement learning task, enabling fine-grained grounding and achieving strong in-domain performance. However, GRPO relies on labelled data, making it unsuitable in unlabelled domains. Moreover, because videos are large and expensive to store and process, performing full-scale adaptation introduces prohibitive latency and computational overhead, making it impractical for real-time deployment. To overcome both problems, we introduce a Data-Efficient Unlabelled Cross-domain Temporal Grounding method, from which a model is first trained on a labelled source domain, then adapted to a target domain using only a small number of unlabelled videos from the target domain. This approach eliminates the need for target annotation and keeps both computational and storage overhead low enough to run in real time. Specifically, we introduce. Uncertainty-quantified Rollout Policy Adaptation (URPA) for cross-domain knowledge transfer in learning video temporal grounding without target labels. URPA generates multiple candidate predictions using GRPO rollouts, averages them to form a pseudo label, and estimates confidence from the variance across these rollouts. This confidence then weights the training rewards, guiding the model to focus on reliable supervision. Experiments on three datasets across six cross-domain settings show that URPA generalises well using only a few unlabelled target videos. Codes will be released once published.

Shangding Gu, Donghao Ying, Ming Jin et al. · berkeley

We introduce Model Feedback Learning (MFL), a novel test-time optimization framework for optimizing inputs to pre-trained AI models or deployed hardware systems without requiring any retraining of the models or modifications to the hardware. In contrast to existing methods that rely on adjusting model parameters, MFL leverages a lightweight reverse model to iteratively search for optimal inputs, enabling efficient adaptation to new objectives under deployment constraints. This framework is particularly advantageous in real-world settings, such as semiconductor manufacturing recipe generation, where modifying deployed systems is often infeasible or cost-prohibitive. We validate MFL on semiconductor plasma etching tasks, where it achieves target recipe generation in just five iterations, significantly outperforming both Bayesian optimization and human experts. Beyond semiconductor applications, MFL also demonstrates strong performance in chemical processes (e.g., chemical vapor deposition) and electronic systems (e.g., wire bonding), highlighting its broad applicability. Additionally, MFL incorporates stability-aware optimization, enhancing robustness to process variations and surpassing conventional supervised learning and random search methods in high-dimensional control settings. By enabling few-shot adaptation, MFL provides a scalable and efficient paradigm for deploying intelligent control in real-world environments.

Yabin Xu, Liangliang Nan, Laishui Zhou et al.

Reconstruction of high-fidelity 3D objects or scenes is a fundamental research problem. Recent advances in RGB-D fusion have demonstrated the potential of producing 3D models from consumer-level RGB-D cameras. However, due to the discrete nature and limited resolution of their surface representations (e.g., point- or voxel-based), existing approaches suffer from the accumulation of errors in camera tracking and distortion in the reconstruction, which leads to an unsatisfactory 3D reconstruction. In this paper, we present a method using on-the-fly implicits of Hermite Radial Basis Functions (HRBFs) as a continuous surface representation for camera tracking in an existing RGB-D fusion framework. Furthermore, curvature estimation and confidence evaluation are coherently derived from the inherent surface properties of the on-the-fly HRBF implicits, which devote to a data fusion with better quality. We argue that our continuous but on-the-fly surface representation can effectively mitigate the impact of noise with its robustness and constrain the reconstruction with inherent surface smoothness when being compared with discrete representations. Experimental results on various real-world and synthetic datasets demonstrate that our HRBF-fusion outperforms the state-of-the-art approaches in terms of tracking robustness and reconstruction accuracy.

Yunxiang Li, Guodong Zeng, Yifan Zhang et al.

Accurate evaluation of the treatment result on X-ray images is a significant and challenging step in root canal therapy since the incorrect interpretation of the therapy results will hamper timely follow-up which is crucial to the patients' treatment outcome. Nowadays, the evaluation is performed in a manual manner, which is time-consuming, subjective, and error-prone. In this paper, we aim to automate this process by leveraging the advances in computer vision and artificial intelligence, to provide an objective and accurate method for root canal therapy result assessment. A novel anatomy-guided multi-branch Transformer (AGMB-Transformer) network is proposed, which first extracts a set of anatomy features and then uses them to guide a multi-branch Transformer network for evaluation. Specifically, we design a polynomial curve fitting segmentation strategy with the help of landmark detection to extract the anatomy features. Moreover, a branch fusion module and a multi-branch structure including our progressive Transformer and Group Multi-Head Self-Attention (GMHSA) are designed to focus on both global and local features for an accurate diagnosis. To facilitate the research, we have collected a large-scale root canal therapy evaluation dataset with 245 root canal therapy X-ray images, and the experiment results show that our AGMB-Transformer can improve the diagnosis accuracy from 57.96% to 90.20% compared with the baseline network. The proposed AGMB-Transformer can achieve a highly accurate evaluation of root canal therapy. To our best knowledge, our work is the first to perform automatic root canal therapy evaluation and has important clinical value to reduce the workload of endodontists.

Jun Wang

Weakly Supervised Object Detection (WSOD), aiming to train detectors with only image-level dataset, has arisen increasing attention for researchers. In this project, we focus on two-phase WSOD architecture which integrates a powerful detector with a pure WSOD model. We explore the effectiveness of some representative detectors utilized as the second-phase detector in two-phase WSOD and propose a two-phase WSOD architecture. In addition, we present a strategy to establish the pseudo ground truth (PGT) used to train the second-phase detector. Unlike previous works that regard top one bounding boxes as PGT, we consider more bounding boxes to establish the PGT annotations. This alleviates the insufficient learning problem caused by the low recall of PGT. We also propose some strategies to refine the PGT during the training of the second detector. Our strategies suspend the training in specific epoch, then refine the PGT by the outputs of the second-phase detector. After that, the algorithm continues the training with the same gradients and weights as those before suspending. Elaborate experiments are conduceted on the PASCAL VOC 2007 dataset to verify the effectiveness of our methods. As results demonstrate, our two-phase architecture improves the mAP from 49.17% to 53.21% compared with the single PCL model. Additionally, the best PGT generation strategy obtains a 0.7% mAP increment. Our best refinement strategy boosts the performance by 1.74% mAP. The best results adopting all of our methods achieve 55.231% mAP which is the state-of-the-art performance.

Yunxiang Li, Yifan Zhang, Yaqi Wang et al.

As the most economical and routine auxiliary examination in the diagnosis of root canal treatment, oral X-ray has been widely used by stomatologists. It is still challenging to segment the tooth root with a blurry boundary for the traditional image segmentation method. To this end, we propose a model for high-resolution segmentation based on polynomial curve fitting with landmark detection (HS-PCL). It is based on detecting multiple landmarks evenly distributed on the edge of the tooth root to fit a smooth polynomial curve as the segmentation of the tooth root, thereby solving the problem of fuzzy edge. In our model, a maximum number of the shortest distances algorithm (MNSDA) is proposed to automatically reduce the negative influence of the wrong landmarks which are detected incorrectly and deviate from the tooth root on the fitting result. Our numerical experiments demonstrate that the proposed approach not only reduces Hausdorff95 (HD95) by 33.9% and Average Surface Distance (ASD) by 42.1% compared with the state-of-the-art method, but it also achieves excellent results on the minute quantity of datasets, which greatly improves the feasibility of automatic root canal therapy evaluation by medical image computing.

Qiaoyun Wu, Xiaoxi Gong, Kai Xu et al.

We present a target-driven navigation system to improve mapless visual navigation in indoor scenes. Our method takes a multi-view observation of a robot and a target as inputs at each time step to provide a sequence of actions that move the robot to the target without relying on odometry or GPS at runtime. The system is learned by optimizing a combinational objective encompassing three key designs. First, we propose that an agent conceives the next observation before making an action decision. This is achieved by learning a variational generative module from expert demonstrations. We then propose predicting static collision in advance, as an auxiliary task to improve safety during navigation. Moreover, to alleviate the training data imbalance problem of termination action prediction, we also introduce a target checking module to differentiate from augmenting navigation policy with a termination action. The three proposed designs all contribute to the improved training data efficiency, static collision avoidance, and navigation generalization performance, resulting in a novel target-driven mapless navigation system. Through experiments on a TurtleBot, we provide evidence that our model can be integrated into a robotic system and navigate in the real world. Videos and models can be found in the supplementary material.

Yuanpeng Liu, Jun Zhou, Yuqi Zhang et al.

In this paper, we focus on estimating the 6D pose of objects in point clouds. Although the topic has been widely studied, pose estimation in point clouds remains a challenging problem due to the noise and occlusion. To address the problem, a novel 3DPVNet is presented in this work, which utilizes 3D local patches to vote for the object 6D poses. 3DPVNet is comprised of three modules. In particular, a Patch Unification (\textbf{PU}) module is first introduced to normalize the input patch, and also create a standard local coordinate frame on it to generate a reliable vote. We then devise a Weight-guided Neighboring Feature Fusion (\textbf{WNFF}) module in the network, which fuses the neighboring features to yield a semi-global feature for the center patch. WNFF module mines the neighboring information of a local patch, such that the representation capability to local geometric characteristics is significantly enhanced, making the method robust to a certain level of noise. Moreover, we present a Patch-level Voting (\textbf{PV}) module to regress transformations and generates pose votes. After the aggregation of all votes from patches and a refinement step, the final pose of the object can be obtained. Compared to recent voting-based methods, 3DPVNet is patch-level, and directly carried out on point clouds. Therefore, 3DPVNet achieves less computation than point/pixel-level voting scheme, and has robustness to partial data. Experiments on several datasets demonstrate that 3DPVNet achieves the state-of-the-art performance, and is also robust against noise and occlusions.

Jun Wang, Shiyi Lan, Mingfei Gao et al.

Real-time 3D object detection is crucial for autonomous cars. Achieving promising performance with high efficiency, voxel-based approaches have received considerable attention. However, previous methods model the input space with features extracted from equally divided sub-regions without considering that point cloud is generally non-uniformly distributed over the space. To address this issue, we propose a novel 3D object detection framework with dynamic information modeling. The proposed framework is designed in a coarse-to-fine manner. Coarse predictions are generated in the first stage via a voxel-based region proposal network. We introduce InfoFocus, which improves the coarse detections by adaptively refining features guided by the information of point cloud density. Experiments are conducted on the large-scale nuScenes 3D detection benchmark. Results show that our framework achieves the state-of-the-art performance with 31 FPS and improves our baseline significantly by 9.0% mAP on the nuScenes test set.

Dening Lu, Xuequan Lu, Yangxing Sun et al.

Point cloud filtering, the main bottleneck of which is removing noise (outliers) while preserving geometric features, is a fundamental problem in 3D field. The two-step schemes involving normal estimation and position update have been shown to produce promising results. Nevertheless, the current normal estimation methods including optimization ones and deep learning ones, often either have limited automation or cannot preserve sharp features. In this paper, we propose a novel feature-preserving normal estimation method for point cloud filtering with preserving geometric features. It is a learning method and thus achieves automatic prediction for normals. For training phase, we first generate patch based samples which are then fed to a classification network to classify feature and non-feature points. We finally train the samples of feature and non-feature points separately, to achieve decent results. Regarding testing, given a noisy point cloud, its normals can be automatically estimated. For further point cloud filtering, we iterate the above normal estimation and a current position update algorithm for a few times. Various experiments demonstrate that our method outperforms state-of-the-art normal estimation methods and point cloud filtering techniques, in terms of both quality and quantity.

Jingwei Song, Jun Wang, Liang Zhao et al.

In minimal invasive surgery, it is important to rebuild and visualize the latest deformed shape of soft-tissue surfaces to mitigate tissue damages. This paper proposes an innovative Simultaneous Localization and Mapping (SLAM) algorithm for deformable dense reconstruction of surfaces using a sequence of images from a stereoscope. We introduce a warping field based on the Embedded Deformation (ED) nodes with 3D shapes recovered from consecutive pairs of stereo images. The warping field is estimated by deforming the last updated model to the current live model. Our SLAM system can: (1) Incrementally build a live model by progressively fusing new observations with vivid accurate texture. (2) Estimate the deformed shape of unobserved region with the principle As-Rigid-As-Possible. (3) Show the consecutive shape of models. (4) Estimate the current relative pose between the soft-tissue and the scope. In-vivo experiments with publicly available datasets demonstrate that the 3D models can be incrementally built for different soft-tissues with different deformations from sequences of stereo images obtained by laparoscopes. Results show the potential clinical application of our SLAM system for providing surgeon useful shape and texture information in minimal invasive surgery.

Dongyan Guo, Jun Wang, Ying Cui et al.

By decomposing the visual tracking task into two subproblems as classification for pixel category and regression for object bounding box at this pixel, we propose a novel fully convolutional Siamese network to solve visual tracking end-to-end in a per-pixel manner. The proposed framework SiamCAR consists of two simple subnetworks: one Siamese subnetwork for feature extraction and one classification-regression subnetwork for bounding box prediction. Our framework takes ResNet-50 as backbone. Different from state-of-the-art trackers like Siamese-RPN, SiamRPN++ and SPM, which are based on region proposal, the proposed framework is both proposal and anchor free. Consequently, we are able to avoid the tricky hyper-parameter tuning of anchors and reduce human intervention. The proposed framework is simple, neat and effective. Extensive experiments and comparisons with state-of-the-art trackers are conducted on many challenging benchmarks like GOT-10K, LaSOT, UAV123 and OTB-50. Without bells and whistles, our SiamCAR achieves the leading performance with a considerable real-time speed.

Xingyu Xie, Jianlong Wu, Guangcan Liu et al.

In this paper, we study the problem of matrix recovery, which aims to restore a target matrix of authentic samples from grossly corrupted observations. Most of the existing methods, such as the well-known Robust Principal Component Analysis (RPCA), assume that the target matrix we wish to recover is low-rank. However, the underlying data structure is often non-linear in practice, therefore the low-rankness assumption could be violated. To tackle this issue, we propose a novel method for matrix recovery in this paper, which could well handle the case where the target matrix is low-rank in an implicit feature space but high-rank or even full-rank in its original form. Namely, our method pursues the low-rank structure of the target matrix in an implicit feature space. By making use of the specifics of an accelerated proximal gradient based optimization algorithm, the proposed method could recover the target matrix with non-linear structures from its corrupted version. Comprehensive experiments on both synthetic and real datasets demonstrate the superiority of our method.

Jihua Zhu, Siyu Xu, Zutao Jiang et al.

This paper proposes a global approach for the multi-view registration of unordered range scans. As the basis of multi-view registration, pair-wise registration is very pivotal. Therefore, we first select a good descriptor and accelerate its correspondence propagation for the pair-wise registration. Then, we design an effective rule to judge the reliability of pair-wise registration results. Subsequently, we propose a model augmentation method, which can utilize reliable results of pair-wise registration to augment the model shape. Finally, multi-view registration can be accomplished by operating the pair-wise registration and judgment, and model augmentation alternately. Experimental results on public available data sets show, that this approach can automatically achieve the multi-view registration of unordered range scans with good accuracy and effectiveness.

Jingwei Song, Jun Wang, Liang Zhao et al.

Real-time simultaneously localization and dense mapping is very helpful for providing Virtual Reality and Augmented Reality for surgeons or even surgical robots. In this paper, we propose MIS-SLAM: a complete real-time large scale dense deformable SLAM system with stereoscope in Minimal Invasive Surgery based on heterogeneous computing by making full use of CPU and GPU. Idled CPU is used to perform ORB- SLAM for providing robust global pose. Strategies are taken to integrate modules from CPU and GPU. We solved the key problem raised in previous work, that is, fast movement of scope and blurry images make the scope tracking fail. Benefiting from improved localization, MIS-SLAM can achieve large scale scope localizing and dense mapping in real-time. It transforms and deforms current model and incrementally fuses new observation while keeping vivid texture. In-vivo experiments conducted on publicly available datasets presented in the form of videos demonstrate the feasibility and practicality of MIS-SLAM for potential clinical purpose.

Simin Wan, Feng Shu, Jinhui Lu et al.

In this paper, given the beamforming vector of confidential messages and artificial noise (AN) projection matrix and total power constraint, a power allocation (PA) strategy of maximizing secrecy rate (Max-SR) is proposed for secure directional modulation (DM) networks. By the method of Lagrange multiplier, the analytic expression of the proposed PA strategy is derived. To confirm the benefit from the Max-SR-based PA strategy, we take the null-space projection (NSP) beamforming scheme as an example and derive its closed-form expression of optimal PA strategy. From simulation results, we find the following facts: in the medium and high signal-to-noise-ratio (SNR) regions, compared with three typical PA parameters such $β=0.1, 0.5$, and $0.9$, the optimal PA shows a substantial SR performance gain with maximum gain percent up to more than $60\%$. Additionally, as the PA factor increases from 0 to 1, the achievable SR increases accordingly in the low SNR region whereas it first increases and then decreases in the medium and high SNR regions, where the SR can be approximately viewed as a convex function of the PA factor. Finally, as the number of antennas increases, the optimal PA factor becomes large and tends to one in the medium and high SNR region. In other words, the contribution of AN to SR can be trivial in such a situation.

Minmin Xu, Siyu Xu, Jihua Zhu et al.

This paper proposes an effective approach for the scaling registration of $m$-D point sets. Different from the rigid transformation, the scaling registration can not be formulated into the common least square function due to the ill-posed problem caused by the scale factor. Therefore, this paper designs a novel objective function for the scaling registration problem. The appearance of this objective function is a rational fraction, where the numerator item is the least square error and the denominator item is the square of the scale factor. By imposing the emphasis on scale factor, the ill-posed problem can be avoided in the scaling registration. Subsequently, the new objective function can be solved by the proposed scaling iterative closest point (ICP) algorithm, which can obtain the optimal scaling transformation. For the practical applications, the scaling ICP algorithm is further extended to align partially overlapping point sets. Finally, the proposed approach is tested on public data sets and applied to merging grid maps of different resolutions. Experimental results demonstrate its superiority over previous approaches on efficiency and robustness.

Weinan Zhang, Ye Pan, Tianxiong Zhou et al.

Display advertising normally charges advertisers for every single ad impression. Specifically, if an ad in a webpage has been loaded in the browser, an ad impression is counted. However, due to the position and size of the ad slot, lots of ads are actually not viewed but still measured as impressions and charged. These fraud ad impressions indeed undermine the efficacy of display advertising. A perfect ad impression viewability measurement should match what the user has really viewed with a short memory. In this paper, we conduct extensive investigations on display ad impression viewability measurements on dimensions of ad creative displayed pixel percentage and exposure time to find which measurement provides the most accurate ad impression counting. The empirical results show that the most accurate measurement counts one ad impression if more than 75% of the ad creative pixels have been exposed for at least 2 continuous seconds.