2024-05-14 更新
ODIN: A Single Model for 2D and 3D Segmentation
Authors:Ayush Jain, Pushkal Katara, Nikolaos Gkanatsios, Adam W. Harley, Gabriel Sarch, Kriti Aggarwal, Vishrav Chaudhary, Katerina Fragkiadaki
State-of-the-art models on contemporary 3D segmentation benchmarks like ScanNet consume and label dataset-provided 3D point clouds, obtained through post processing of sensed multiview RGB-D images. They are typically trained in-domain, forego large-scale 2D pre-training and outperform alternatives that featurize the posed RGB-D multiview images instead. The gap in performance between methods that consume posed images versus post-processed 3D point clouds has fueled the belief that 2D and 3D perception require distinct model architectures. In this paper, we challenge this view and propose ODIN (Omni-Dimensional INstance segmentation), a model that can segment and label both 2D RGB images and 3D point clouds, using a transformer architecture that alternates between 2D within-view and 3D cross-view information fusion. Our model differentiates 2D and 3D feature operations through the positional encodings of the tokens involved, which capture pixel coordinates for 2D patch tokens and 3D coordinates for 3D feature tokens. ODIN achieves state-of-the-art performance on ScanNet200, Matterport3D and AI2THOR 3D instance segmentation benchmarks, and competitive performance on ScanNet, S3DIS and COCO. It outperforms all previous works by a wide margin when the sensed 3D point cloud is used in place of the point cloud sampled from 3D mesh. When used as the 3D perception engine in an instructable embodied agent architecture, it sets a new state-of-the-art on the TEACh action-from-dialogue benchmark. Our code and checkpoints can be found at the project website (https://odin-seg.github.io).
PDF Camera Ready (CVPR 2024, Highlight)
点此查看论文截图
A Hybrid Generative and Discriminative PointNet on Unordered Point Sets
Authors:Yang Ye, Shihao Ji
As point cloud provides a natural and flexible representation usable in myriad applications (e.g., robotics and self-driving cars), the ability to synthesize point clouds for analysis becomes crucial. Recently, Xie et al. propose a generative model for unordered point sets in the form of an energy-based model (EBM). Despite the model achieving an impressive performance for point cloud generation, one separate model needs to be trained for each category to capture the complex point set distributions. Besides, their method is unable to classify point clouds directly and requires additional fine-tuning for classification. One interesting question is: Can we train a single network for a hybrid generative and discriminative model of point clouds? A similar question has recently been answered in the affirmative for images, introducing the framework of Joint Energy-based Model (JEM), which achieves high performance in image classification and generation simultaneously. This paper proposes GDPNet, the first hybrid Generative and Discriminative PointNet that extends JEM for point cloud classification and generation. Our GDPNet retains strong discriminative power of modern PointNet classifiers, while generating point cloud samples rivaling state-of-the-art generative approaches.
PDF
点此查看论文截图
Fast LiDAR Upsampling using Conditional Diffusion Models
Authors:Sander Elias Magnussen Helgesen, Kazuto Nakashima, Jim Tørresen, Ryo Kurazume
The search for refining 3D LiDAR data has attracted growing interest motivated by recent techniques such as supervised learning or generative model-based methods. Existing approaches have shown the possibilities for using diffusion models to generate refined LiDAR data with high fidelity, although the performance and speed of such methods have been limited. These limitations make it difficult to execute in real-time, causing the approaches to struggle in real-world tasks such as autonomous navigation and human-robot interaction. In this work, we introduce a novel approach based on conditional diffusion models for fast and high-quality sparse-to-dense upsampling of 3D scene point clouds through an image representation. Our method employs denoising diffusion probabilistic models trained with conditional inpainting masks, which have been shown to give high performance on image completion tasks. We introduce a series of experiments, including multiple datasets, sampling steps, and conditional masks, to determine the ideal configuration, striking a balance between performance and inference speed. This paper illustrates that our method outperforms the baselines in sampling speed and quality on upsampling tasks using the KITTI-360 dataset. Furthermore, we illustrate the generalization ability of our approach by simultaneously training on real-world and synthetic datasets, introducing variance in quality and environments.
PDF
点此查看论文截图
Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Driving
Authors:Lingdong Kong, Xiang Xu, Jiawei Ren, Wenwei Zhang, Liang Pan, Kai Chen, Wei Tsang Ooi, Ziwei Liu
Efficient data utilization is crucial for advancing 3D scene understanding in autonomous driving, where reliance on heavily human-annotated LiDAR point clouds challenges fully supervised methods. Addressing this, our study extends into semi-supervised learning for LiDAR semantic segmentation, leveraging the intrinsic spatial priors of driving scenes and multi-sensor complements to augment the efficacy of unlabeled datasets. We introduce LaserMix++, an evolved framework that integrates laser beam manipulations from disparate LiDAR scans and incorporates LiDAR-camera correspondences to further assist data-efficient learning. Our framework is tailored to enhance 3D scene consistency regularization by incorporating multi-modality, including 1) multi-modal LaserMix operation for fine-grained cross-sensor interactions; 2) camera-to-LiDAR feature distillation that enhances LiDAR feature learning; and 3) language-driven knowledge guidance generating auxiliary supervisions using open-vocabulary models. The versatility of LaserMix++ enables applications across LiDAR representations, establishing it as a universally applicable solution. Our framework is rigorously validated through theoretical analysis and extensive experiments on popular driving perception datasets. Results demonstrate that LaserMix++ markedly outperforms fully supervised alternatives, achieving comparable accuracy with five times fewer annotations and significantly improving the supervised-only baselines. This substantial advancement underscores the potential of semi-supervised approaches in reducing the reliance on extensive labeled data in LiDAR-based 3D scene understanding systems.
PDF Preprint; 17 pages, 6 figures, 8 tables; Code at https://github.com/ldkong1205/LaserMix
点此查看论文截图
Rethinking Efficient and Effective Point-based Networks for Event Camera Classification and Regression: EventMamba
Authors:Hongwei Ren, Yue Zhou, Jiadong Zhu, Haotian Fu, Yulong Huang, Xiaopeng Lin, Yuetong Fang, Fei Ma, Hao Yu, Bojun Cheng
Event cameras, drawing inspiration from biological systems, efficiently detect changes in ambient light with low latency and high dynamic range while consuming minimal power. The most current approach to processing event data often involves converting it into frame-based representations, which is well-established in traditional vision. However, this approach neglects the sparsity of event data, loses fine-grained temporal information during the transformation process, and increases the computational burden, making it ineffective for characterizing event camera properties. In contrast, Point Cloud is a popular representation for 3D processing and is better suited to match the sparse and asynchronous nature of the event camera. Nevertheless, despite the theoretical compatibility of point-based methods with event cameras, the results show a performance gap that is not yet satisfactory compared to frame-based methods. In order to bridge the performance gap, we propose EventMamba, an efficient and effective Point Cloud framework that achieves competitive results even compared to the state-of-the-art (SOTA) frame-based method in both classification and regression tasks. This notable accomplishment is facilitated by our rethinking of the distinction between Event Cloud and Point Cloud, emphasizing effective temporal information extraction through optimized network structures. Specifically, EventMamba leverages temporal aggregation and State Space Model (SSM) based Mamba boasting enhanced temporal information extraction capabilities. Through a hierarchical structure, EventMamba is adept at abstracting local and global spatial features and implicit and explicit temporal features. By adhering to the lightweight design principle, EventMamba delivers impressive results with minimal computational resource utilization, demonstrating its efficiency and effectiveness.
PDF Extension Journal of TTPOINT and PEPNet
点此查看论文截图
Benchmarking Classical and Learning-Based Multibeam Point Cloud Registration
Authors:Li Ling, Jun Zhang, Nils Bore, John Folkesson, Anna Wåhlin
Deep learning has shown promising results for multiple 3D point cloud registration datasets. However, in the underwater domain, most registration of multibeam echo-sounder (MBES) point cloud data are still performed using classical methods in the iterative closest point (ICP) family. In this work, we curate and release DotsonEast Dataset, a semi-synthetic MBES registration dataset constructed from an autonomous underwater vehicle in West Antarctica. Using this dataset, we systematically benchmark the performance of 2 classical and 4 learning-based methods. The experimental results show that the learning-based methods work well for coarse alignment, and are better at recovering rough transforms consistently at high overlap (20-50%). In comparison, GICP (a variant of ICP) performs well for fine alignment and is better across all metrics at extremely low overlap (10%). To the best of our knowledge, this is the first work to benchmark both learning-based and classical registration methods on an AUV-based MBES dataset. To facilitate future research, both the code and data are made available online.
PDF Accepted at ICRA 2024 (IEEE International Conference on Robotics and Automation 2024)
点此查看论文截图
Mesh Denoising Transformer
Authors:Wenbo Zhao, Xianming Liu, Deming Zhai, Junjun Jiang, Xiangyang Ji
Mesh denoising, aimed at removing noise from input meshes while preserving their feature structures, is a practical yet challenging task. Despite the remarkable progress in learning-based mesh denoising methodologies in recent years, their network designs often encounter two principal drawbacks: a dependence on single-modal geometric representations, which fall short in capturing the multifaceted attributes of meshes, and a lack of effective global feature aggregation, hindering their ability to fully understand the mesh’s comprehensive structure. To tackle these issues, we propose SurfaceFormer, a pioneering Transformer-based mesh denoising framework. Our first contribution is the development of a new representation known as Local Surface Descriptor, which is crafted by establishing polar systems on each mesh face, followed by sampling points from adjacent surfaces using geodesics. The normals of these points are organized into 2D patches, mimicking images to capture local geometric intricacies, whereas the poles and vertex coordinates are consolidated into a point cloud to embody spatial information. This advancement surmounts the hurdles posed by the irregular and non-Euclidean characteristics of mesh data, facilitating a smooth integration with Transformer architecture. Next, we propose a dual-stream structure consisting of a Geometric Encoder branch and a Spatial Encoder branch, which jointly encode local geometry details and spatial information to fully explore multimodal information for mesh denoising. A subsequent Denoising Transformer module receives the multimodal information and achieves efficient global feature aggregation through self-attention operators. Our experimental evaluations demonstrate that this novel approach outperforms existing state-of-the-art methods in both objective and subjective assessments, marking a significant leap forward in mesh denoising.
PDF
点此查看论文截图
PRENet: A Plane-Fit Redundancy Encoding Point Cloud Sequence Network for Real-Time 3D Action Recognition
Authors:Shenglin He, Xiaoyang Qu, Jiguang Wan, Guokuan Li, Changsheng Xie, Jianzong Wang
Recognizing human actions from point cloud sequence has attracted tremendous attention from both academia and industry due to its wide applications. However, most previous studies on point cloud action recognition typically require complex networks to extract intra-frame spatial features and inter-frame temporal features, resulting in an excessive number of redundant computations. This leads to high latency, rendering them impractical for real-world applications. To address this problem, we propose a Plane-Fit Redundancy Encoding point cloud sequence network named PRENet. The primary concept of our approach involves the utilization of plane fitting to mitigate spatial redundancy within the sequence, concurrently encoding the temporal redundancy of the entire sequence to minimize redundant computations. Specifically, our network comprises two principal modules: a Plane-Fit Embedding module and a Spatio-Temporal Consistency Encoding module. The Plane-Fit Embedding module capitalizes on the observation that successive point cloud frames exhibit unique geometric features in physical space, allowing for the reuse of spatially encoded data for temporal stream encoding. The Spatio-Temporal Consistency Encoding module amalgamates the temporal structure of the temporally redundant part with its corresponding spatial arrangement, thereby enhancing recognition accuracy. We have done numerous experiments to verify the effectiveness of our network. The experimental results demonstrate that our method achieves almost identical recognition accuracy while being nearly four times faster than other state-of-the-art methods.
PDF Accepted by the 2024 International Joint Conference on Neural Networks (IJCNN 2024)
点此查看论文截图
RGBD-Glue: General Feature Combination for Robust RGB-D Point Cloud Registration
Authors:Congjia Chen, Xiaoyu Jia, Yanhong Zheng, Yufu Qu
Point cloud registration is a fundamental task for estimating rigid transformations between point clouds. Previous studies have used geometric information for extracting features, matching and estimating transformation. Recently, owing to the advancement of RGB-D sensors, researchers have attempted to utilize visual information to improve registration performance. However, these studies focused on extracting distinctive features by deep feature fusion, which cannot effectively solve the negative effects of each feature’s weakness, and cannot sufficiently leverage the valid information. In this paper, we propose a new feature combination framework, which applies a looser but more effective fusion and can achieve better performance. An explicit filter based on transformation consistency is designed for the combination framework, which can overcome each feature’s weakness. And an adaptive threshold determined by the error distribution is proposed to extract more valid information from the two types of features. Owing to the distinctive design, our proposed framework can estimate more accurate correspondences and is applicable to both hand-crafted and learning-based feature descriptors. Experiments on ScanNet show that our method achieves a state-of-the-art performance and the rotation accuracy of 99.1%.
PDF
点此查看论文截图
SceneFactory: A Workflow-centric and Unified Framework for Incremental Scene Modeling
Authors:Yijun Yuan, Michael Bleier, Andreas Nüchter
We present SceneFactory, a workflow-centric and unified framework for incremental scene modeling, that supports conveniently a wide range of applications, such as (unposed and/or uncalibrated) multi-view depth estimation, LiDAR completion, (dense) RGB-D/RGB-L/Mono//Depth-only reconstruction and SLAM. The workflow-centric design uses multiple blocks as the basis for building different production lines. The supported applications, i.e., productions avoid redundancy in their designs. Thus, the focus is on each block itself for independent expansion. To support all input combinations, our implementation consists of four building blocks in SceneFactory: (1) Mono-SLAM, (2) depth estimation, (3) flexion and (4) scene reconstruction. Furthermore, we propose an unposed & uncalibrated multi-view depth estimation model (U2-MVD) to estimate dense geometry. U2-MVD exploits dense bundle adjustment for solving for poses, intrinsics, and inverse depth. Then a semantic-awared ScaleCov step is introduced to complete the multi-view depth. Relying on U2-MVD, SceneFactory both supports user-friendly 3D creation (with just images) and bridges the applications of Dense RGB-D and Dense Mono. For high quality surface and color reconstruction, we propose due-purpose Multi-resolutional Neural Points (DM-NPs) for the first surface accessible Surface Color Field design, where we introduce Improved Point Rasterization (IPR) for point cloud based surface query. We implement and experiment with SceneFactory to demonstrate its broad practicability and high flexibility. Its quality also competes or exceeds the tightly-coupled state of the art approaches in all tasks. We contribute the code to the community (https://jarrome.github.io/).
PDF
点此查看论文截图
OverlapMamba: Novel Shift State Space Model for LiDAR-based Place Recognition
Authors:Qiuchi Xiang, Jintao Cheng, Jiehao Luo, Jin Wu, Rui Fan, Xieyuanli Chen, Xiaoyu Tang
Place recognition is the foundation for enabling autonomous systems to achieve independent decision-making and safe operations. It is also crucial in tasks such as loop closure detection and global localization within SLAM. Previous methods utilize mundane point cloud representations as input and deep learning-based LiDAR-based Place Recognition (LPR) approaches employing different point cloud image inputs with convolutional neural networks (CNNs) or transformer architectures. However, the recently proposed Mamba deep learning model, combined with state space models (SSMs), holds great potential for long sequence modeling. Therefore, we developed OverlapMamba, a novel network for place recognition, which represents input range views (RVs) as sequences. In a novel way, we employ a stochastic reconstruction approach to build shift state space models, compressing the visual representation. Evaluated on three different public datasets, our method effectively detects loop closures, showing robustness even when traversing previously visited locations from different directions. Relying on raw range view inputs, it outperforms typical LiDAR and multi-view combination methods in time complexity and speed, indicating strong place recognition capabilities and real-time efficiency.
PDF
点此查看论文截图