Pengcheng Shi

Qinghao Ye, Haiyang Xu, Guohai Xu et al.

Large language models (LLMs) have demonstrated impressive zero-shot abilities on a variety of open-ended tasks, while recent research has also explored the use of LLMs for multi-modal generation. In this study, we introduce mPLUG-Owl, a novel training paradigm that equips LLMs with multi-modal abilities through modularized learning of foundation LLM, a visual knowledge module, and a visual abstractor module. This approach can support multiple modalities and facilitate diverse unimodal and multimodal abilities through modality collaboration. The training paradigm of mPLUG-Owl involves a two-stage method for aligning image and text, which learns visual knowledge with the assistance of LLM while maintaining and even improving the generation abilities of LLM. In the first stage, the visual knowledge module and abstractor module are trained with a frozen LLM module to align the image and text. In the second stage, language-only and multi-modal supervised datasets are used to jointly fine-tune a low-rank adaption (LoRA) module on LLM and the abstractor module by freezing the visual knowledge module. We carefully build a visually-related instruction evaluation set OwlEval. Experimental results show that our model outperforms existing multi-modal models, demonstrating mPLUG-Owl's impressive instruction and visual understanding ability, multi-turn conversation ability, and knowledge reasoning ability. Besides, we observe some unexpected and exciting abilities such as multi-image correlation and scene text understanding, which makes it possible to leverage it for harder real scenarios, such as vision-only document comprehension. Our code, pre-trained model, instruction-tuned models, and evaluation set are available at https://github.com/X-PLUG/mPLUG-Owl. The online demo is available at https://www.modelscope.cn/studios/damo/mPLUG-Owl.

Jiayuan Li, Pengcheng Shi, Qingwu Hu et al.

Multimodal image matching is an important prerequisite for multisource image information fusion. Compared with the traditional matching problem, multimodal feature matching is more challenging due to the severe nonlinear radiation distortion (NRD). Radiation-variation insensitive feature transform (RIFT)~\cite{li2019rift} has shown very good robustness to NRD and become a baseline method in multimodal feature matching. However, the high computational cost for rotation invariance largely limits its usage in practice. In this paper, we propose an improved RIFT method, called RIFT2. We develop a new rotation invariance technique based on dominant index value, which avoids the construction process of convolution sequence ring. Hence, it can speed up the running time and reduce the memory consumption of the original RIFT by almost 3 times in theory. Extensive experiments show that RIFT2 achieves similar matching performance to RIFT while being much faster and having less memory consumption. The source code will be made publicly available in \url{https://github.com/LJY-RS/RIFT2-multimodal-matching-rotation}

Pengcheng Shi, Jiesi Hu, Yanwu Yang et al.

Vascular segmentation in medical imaging plays a crucial role in analysing morphological and functional assessments. Traditional methods, like the centerline Dice (clDice) loss, ensure topology preservation but falter in capturing geometric details, especially under translation and deformation. The combination of clDice with traditional Dice loss can lead to diameter imbalance, favoring larger vessels. Addressing these challenges, we introduce the centerline boundary Dice (cbDice) loss function, which harmonizes topological integrity and geometric nuances, ensuring consistent segmentation across various vessel sizes. cbDice enriches the clDice approach by including boundary-aware aspects, thereby improving geometric detail recognition. It matches the performance of the boundary difference over union (B-DoU) loss through a mask-distance-based approach, enhancing traslation sensitivity. Crucially, cbDice incorporates radius information from vascular skeletons, enabling uniform adaptation to vascular diameter changes and maintaining balance in branch growth and fracture impacts. Furthermore, we conducted a theoretical analysis of clDice variants (cl-X-Dice). We validated cbDice's efficacy on three diverse vascular segmentation datasets, encompassing both 2D and 3D, and binary and multi-class segmentation. Particularly, the method integrated with cbDice demonstrated outstanding performance on the MICCAI 2023 TopCoW Challenge dataset. Our code is made publicly available at: https://github.com/PengchengShi1220/cbDice.

Junyang Wang, Yiyang Zhou, Guohai Xu et al.

Large Vision-Language Models (LVLMs) have recently achieved remarkable success. However, LVLMs are still plagued by the hallucination problem, which limits the practicality in many scenarios. Hallucination refers to the information of LVLMs' responses that does not exist in the visual input, which poses potential risks of substantial consequences. There has been limited work studying hallucination evaluation in LVLMs. In this paper, we propose Hallucination Evaluation based on Large Language Models (HaELM), an LLM-based hallucination evaluation framework. HaELM achieves an approximate 95% performance comparable to ChatGPT and has additional advantages including low cost, reproducibility, privacy preservation and local deployment. Leveraging the HaELM, we evaluate the hallucination in current LVLMs. Furthermore, we analyze the factors contributing to hallucination in LVLMs and offer helpful suggestions to mitigate the hallucination problem. Our training data and human annotation hallucination data will be made public soon.

Shaocheng Yan, Pengcheng Shi, Jiayuan Li

Recent advances in point cloud registration mostly leverage geometric information. Although these methods have yielded promising results, they still struggle with problems of low overlap, thus limiting their practical usage. In this paper, we propose ML-SemReg, a plug-and-play point cloud registration framework that fully exploits semantic information. Our key insight is that mismatches can be categorized into two types, i.e., inter- and intra-class, after rendering semantic clues, and can be well addressed by utilizing multi-level semantic consistency. We first propose a Group Matching module to address inter-class mismatching, outputting multiple matching groups that inherently satisfy Local Semantic Consistency. For each group, a Mask Matching module based on Scene Semantic Consistency is then introduced to suppress intra-class mismatching. Benefit from those two modules, ML-SemReg generates correspondences with a high inlier ratio. Extensive experiments demonstrate excellent performance and robustness of ML-SemReg, e.g., in hard-cases of the KITTI dataset, the Registration Recall of MAC increases by almost 34 percentage points when our ML-SemReg is equipped. Code is available at \url{https://github.com/Laka-3DV/ML-SemReg}

Pengcheng Shi, Jie Zhang, Haozhe Cheng et al.

Point cloud registration is a fundamental problem in many domains. Practically, the overlap between point clouds to be registered may be relatively small. Most unsupervised methods lack effective initial evaluation of overlap, leading to suboptimal registration accuracy. To address this issue, we propose an unsupervised network Overlap Bias Matching Network (OBMNet) for partial point cloud registration. Specifically, we propose a plug-and-play Overlap Bias Matching Module (OBMM) comprising two integral components, overlap sampling module and bias prediction module. These two components are utilized to capture the distribution of overlapping regions and predict bias coefficients of point cloud common structures, respectively. Then, we integrate OBMM with the neighbor map matching module to robustly identify correspondences by precisely merging matching scores of points within the neighborhood, which addresses the ambiguities in single-point features. OBMNet can maintain efficacy even in pair-wise registration scenarios with low overlap ratios. Experimental results on extensive datasets demonstrate that our approach's performance achieves a significant improvement compared to the state-of-the-art registration approach.

Jie Zhang, Pengcheng Shi, Zaiwang Gu et al.

The neural rendering of humans is a topic of great research significance. However, previous works mostly focus on achieving photorealistic details, neglecting the exploration of human parsing. Additionally, classical semantic work are all limited in their ability to efficiently represent fine results in complex motions. Human parsing is inherently related to radiance reconstruction, as similar appearance and geometry often correspond to similar semantic part. Furthermore, previous works often design a motion field that maps from the observation space to the canonical space, while it tends to exhibit either underfitting or overfitting, resulting in limited generalization. In this paper, we present Semantic-Human, a novel method that achieves both photorealistic details and viewpoint-consistent human parsing for the neural rendering of humans. Specifically, we extend neural radiance fields (NeRF) to jointly encode semantics, appearance and geometry to achieve accurate 2D semantic labels using noisy pseudo-label supervision. Leveraging the inherent consistency and smoothness properties of NeRF, Semantic-Human achieves consistent human parsing in both continuous and novel views. We also introduce constraints derived from the SMPL surface for the motion field and regularization for the recovered volumetric geometry. We have evaluated the model using the ZJU-MoCap dataset, and the obtained highly competitive results demonstrate the effectiveness of our proposed Semantic-Human. We also showcase various compelling applications, including label denoising, label synthesis and image editing, and empirically validate its advantageous properties.

David Millard, Cecilia Alm, Rashid Ali et al.

Federated reinforcement learning typically aggregates value functions or policies by parameter averaging, which emphasizes expected return and can obscure statistical multimodality and tail behavior that matter in safety-critical settings. We formalize federated distributional reinforcement learning (FedDistRL), where clients parametrize quantile value function critics and federate these networks only. We also propose TR-FedDistRL, which builds a per client, risk-aware Wasserstein barycenter over a temporal buffer. This local barycenter provides a reference region to constrain the parameter averaged critic, ensuring necessary distributional information is not averaged out during the federation process. The distributional trust region is implemented as a shrink-squash step around this reference. Under fixed-policy evaluation, the feasibility map is nonexpansive and the update is contractive in a probe-set Wasserstein metric under evaluation. Experiments on a bandit, multi-agent gridworld, and continuous highway environment show reduced mean-smearing, improved safety proxies (catastrophe/accident rate), and lower critic/policy drift versus mean-oriented and non-federated baselines.

Yifan Xie, Jihua Zhu, Shiqi Li et al.

The majority of point cloud registration methods currently rely on extracting features from points. However, these methods are limited by their dependence on information obtained from a single modality of points, which can result in deficiencies such as inadequate perception of global features and a lack of texture information. Actually, humans can employ visual information learned from 2D images to comprehend the 3D world. Based on this fact, we present a novel Cross-Modal Information-Guided Network (CMIGNet), which obtains global shape perception through cross-modal information to achieve precise and robust point cloud registration. Specifically, we first incorporate the projected images from the point clouds and fuse the cross-modal features using the attention mechanism. Furthermore, we employ two contrastive learning strategies, namely overlapping contrastive learning and cross-modal contrastive learning. The former focuses on features in overlapping regions, while the latter emphasizes the correspondences between 2D and 3D features. Finally, we propose a mask prediction module to identify keypoints in the point clouds. Extensive experiments on several benchmark datasets demonstrate that our network achieves superior registration performance.

Pengcheng Shi, Shaocheng Yan, Yilin Xiao et al.

Correspondence-based point cloud registration (PCR) plays a key role in robotics and computer vision. However, challenges like sensor noises, object occlusions, and descriptor limitations inevitably result in numerous outliers. RANSAC family is the most popular outlier removal solution. However, the requisite iterations escalate exponentially with the outlier ratio, rendering it far inferior to existing methods (SC2PCR [1], MAC [2], etc.) in terms of accuracy or speed. Thus, we propose a two-stage consensus filtering (TCF) that elevates RANSAC to state-of-the-art (SOTA) speed and accuracy. Firstly, one-point RANSAC obtains a consensus set based on length consistency. Subsequently, two-point RANSAC refines the set via angle consistency. Then, three-point RANSAC computes a coarse pose and removes outliers based on transformed correspondence's distances. Drawing on optimizations from one-point and two-point RANSAC, three-point RANSAC requires only a few iterations. Eventually, an iterative reweighted least squares (IRLS) is applied to yield the optimal pose. Experiments on the large-scale KITTI and ETH datasets demonstrate our method achieves up to three-orders-of-magnitude speedup compared to MAC while maintaining registration accuracy and recall. Our code is available at https://github.com/ShiPC-AI/TCF.

Yu Chen, Pengcheng Shi

Real-world point clouds usually suffer from incompleteness and display different poses. While current point cloud completion methods excel in reproducing complete point clouds with consistent poses as seen in the training set, their performance tends to be unsatisfactory when handling point clouds with diverse poses. We propose a network named Rotation-Invariant Completion Network (RICNet), which consists of two parts: a Dual Pipeline Completion Network (DPCNet) and an enhancing module. Firstly, DPCNet generates a coarse complete point cloud. The feature extraction module of DPCNet can extract consistent features, no matter if the input point cloud has undergone rotation or translation. Subsequently, the enhancing module refines the fine-grained details of the final generated point cloud. RICNet achieves better rotation invariance in feature extraction and incorporates structural relationships in man-made objects. To assess the performance of RICNet and existing methods on point clouds with various poses, we applied random transformations to the point clouds in the MVP dataset and conducted experiments on them. Our experiments demonstrate that RICNet exhibits superior completion performance compared to existing methods.

Pengcheng Shi, Xutao Guo, Yanwu Yang et al.

Convolutional neural networks (CNN) and Transformer variants have emerged as the leading medical image segmentation backbones. Nonetheless, due to their limitations in either preserving global image context or efficiently processing irregular shapes in visual objects, these backbones struggle to effectively integrate information from diverse anatomical regions and reduce inter-individual variability, particularly for the vasculature. Motivated by the successful breakthroughs of graph neural networks (GNN) in capturing topological properties and non-Euclidean relationships across various fields, we propose NexToU, a novel hybrid architecture for medical image segmentation. NexToU comprises improved Pool GNN and Swin GNN modules from Vision GNN (ViG) for learning both global and local topological representations while minimizing computational costs. To address the containment and exclusion relationships among various anatomical structures, we reformulate the topological interaction (TI) module based on the nature of binary trees, rapidly encoding the topological constraints into NexToU. Extensive experiments conducted on three datasets (including distinct imaging dimensions, disease types, and imaging modalities) demonstrate that our method consistently outperforms other state-of-the-art (SOTA) architectures. All the code is publicly available at https://github.com/PengchengShi1220/NexToU.

Pengcheng Shi, Haozhe Cheng, Xu Han et al.

Point cloud completion estimates complete shapes from incomplete point clouds to obtain higher-quality point cloud data. Most existing methods only consider global object features, ignoring spatial and semantic information of adjacent points. They cannot distinguish structural information well between different object parts, and the robustness of models is poor. To tackle these challenges, we propose an information interaction-based generative network for point cloud completion ($\mathbf{DualGenerator}$). It contains an adversarial generation path and a variational generation path, which interact with each other and share weights. DualGenerator introduces a local refinement module in generation paths, which captures general structures from partial inputs, and then refines shape details of the point cloud. It promotes completion in the unknown region and makes a distinction between different parts more obvious. Moreover, we design DGStyleGAN to improve the generation quality further. It promotes the robustness of this network combined with fusion analysis of dual-path completion results. Qualitative and quantitative evaluations demonstrate that our method is superior on MVP and Completion3D datasets. The performance will not degrade significantly after adding noise interference or sparse sampling.