AdaPoinTr: Diverse Point Cloud Completion with Adaptive Geometry-Aware Transformers
Beijing National Research Center for Information Science and Technology (BNRist)（北京信息科学与技术国家研究中心）；State Key Lab of Intelligent Technologies and Systems（智能技术与系统国家重点实验室）；Tsinghua University（清华大学）
Xumin Yu, Yongming Rao, Ziyi Wang, Jiwen Lu, Jie Zhou
In this paper, we present a new method that reformulates point cloud completion as a set-to-set translation problem and design a new model, called PoinTr, which adopts a Transformer encoder-decoder architecture for point cloud completion. By representing the point cloud as a set of unordered groups of points with position embeddings, we convert the input data to a sequence of point proxies and employ the Transformers for generation. To facilitate Transformers to better leverage the inductive bias about 3D geometric structures of point clouds, we further devise a geometry-aware block that models the local geometric relationships explicitly. The migration of Transformers enables our model to better learn structural knowledge and preserve detailed information for point cloud completion. Taking a step towards more complicated and diverse situations, we further propose AdaPoinTr by developing an adaptive query generation mechanism and designing a novel denoising task during completing a point cloud. Coupling these two techniques enables us to train the model efficiently and effectively: we reduce training time (by 15x or more) and improve completion performance (over 20%). We also show our method can be extended to the scene-level point cloud completion scenario by designing a new geometry-enhanced semantic scene completion framework. Extensive experiments on the existing and newly-proposed datasets demonstrate the effectiveness of our method, which attains 6.53 CD on PCN, 0.81 CD on ShapeNet-55 and 0.392 MMD on real-world KITTI, surpassing other work by a large margin and establishing new state-of-the-arts on various benchmarks. Most notably, AdaPoinTr can achieve such promising performance with higher throughputs and fewer FLOPs compared with the previous best methods in practice. The code and datasets are available at https://github.com/yuxumin/PoinTr
Point clouds captured in real-world applications are often incomplete due to the limited sensor resolution, single viewpoint, and occlusion. Therefore, recovering the complete point clouds from partial ones becomes an indispensable task in many practical applications. In this paper, we present a new method that reformulates point cloud completion as a set-to-set translation problem and design a new model, called PoinTr that adopts a transformer encoder-decoder architecture for point cloud completion. By representing the point cloud as a set of unordered groups of points with position embedding…
Point cloud completion has become increasingly popular among generation tasks of 3D point clouds, as it is a challenging yet indispensable problem to recover the complete shape of a 3D object from its partial observation. In this paper, we propose a novel SeedFormer to improve the ability of detail preservation and recovery in point cloud completion. Unlike previous methods based on a global feature vector, we introduce a new shape representation, namely Patch Seeds, which not only captures general structures from partial inputs but also preserves regional information of local patterns. Then, …
Shenzhen University（深圳大学）；University College London（伦敦大学学院）；Adobe Research（奥多比研究院）；Hebrew University of Jerusalem（耶路撒冷希伯来大学）；Tel Aviv University（特拉维夫大学）
We present ShapeFormer, a transformer-based network that produces a distribution of object completions, conditioned on incomplete, and possibly noisy, point clouds. The resultant distribution can then be sampled to generate likely completions, each exhibiting plausible shape details while being faithful to the input. To facilitate the use of transformers for 3D, we introduce a compact 3D representation, vector quantized deep implicit function, that utilizes spatial sparsity to represent a close approximation of a 3D shape by a short sequence of discrete variables. Experiments demonstrate that …
Tsinghua University（清华大学）；Wayne State University（韦恩州立大学）；Kuaishou Technology（快手科技）
Point cloud completion concerns to predict missing part for incomplete 3D shapes. A common strategy is to generate complete shape according to incomplete input. However, unordered nature of point clouds will degrade generation of high-quality 3D shapes, as detailed topology and structure of unordered points are hard to be captured during the generative process using an extracted latent code. We address this problem by formulating completion as point cloud deformation process. Specifically, we design a novel neural network, named PMP-Net++, to mimic behavior of an earth mover. It moves each poi…
Point cloud completion task aims to predict the missing part of incomplete point clouds and generate complete point clouds with details. In this paper, we propose a novel point cloud completion network, namely CompleteDT. Specifically, features are learned from point clouds with different resolutions, which is sampled from the incomplete input, and are converted to a series of \textit{spots} based on the geometrical structure. Then, the Dense Relation Augment Module (DRA) based on the transformer is proposed to learn features within \textit{spots} and consider the correlation among these \text…
Tsinghua University（清华大学）；Kuaishou Technology（快手科技）；Wayne State University（韦恩州立大学）
Point cloud completion aims to predict a complete shape in high accuracy from its partial observation. However, previous methods usually suffered from discrete nature of point cloud and unstructured prediction of points in local regions, which makes it hard to reveal fine local geometric details on the complete shape. To resolve this issue, we propose SnowflakeNet with Snowflake Point Deconvolution (SPD) to generate the complete point clouds. The SnowflakeNet models the generation of complete point clouds as the snowflake-like growth of points in 3D space, where the child points are progressiv…
Nanjing University of Aeronautics and Astronautics（南京航空航天大学）
Problems such as equipment defects or limited viewpoints will lead the captured point clouds to be incomplete. Therefore, recovering the complete point clouds from the partial ones plays an vital role in many practical tasks, and one of the keys lies in the prediction of the missing part. In this paper, we propose a novel point cloud completion approach namely ProxyFormer that divides point clouds into existing (input) and missing (to be predicted) parts and each part communicates information through its proxies. Specifically, we fuse information into point proxy via feature and position extra…
Tsinghua University（清华大学）；Tencent PCG（腾讯平台与内容事业群）；Kuaishou Technology（快手科技）；Wayne State University（韦恩州立大学）
Most existing point cloud completion methods suffer from the discrete nature of point clouds and the unstructured prediction of points in local regions, which makes it difficult to reveal fine local geometric details. To resolve this issue, we propose SnowflakeNet with snowflake point deconvolution (SPD) to generate complete point clouds. SPD models the generation of point clouds as the snowflake-like growth of points, where child points are generated progressively by splitting their parent points after each SPD. Our insight into the detailed geometry is to introduce a skip-transformer in the …
DAPoinTr: Domain Adaptive Point Transformer for Point Cloud Completion
Deakin University（迪肯大学）；Shanghai Jiao Tong University（上海交通大学）；East China Normal University（华东师范大学）；Zhejiang University（浙江大学）；The University of Western Australia（西澳大学）
NYU（纽约大学）；NVIDIA（英伟达）；ASU（亚利桑那州立大学）；University of Toronto（多伦多大学）；Vector Institute（向量研究所）；Caltech（加州理工学院）
Humans can easily imagine the complete 3D geometry of occluded objects and scenes. This appealing ability is vital for recognition and understanding. To enable such capability in AI systems, we propose VoxFormer, a Transformer-based semantic scene completion framework that can output complete 3D volumetric semantics from only 2D images. Our framework adopts a two-stage design where we start from a sparse set of visible and occupied voxel queries from depth estimation, followed by a densification stage that generates dense 3D voxels from the sparse ones. A key idea of this design is that the vi…
High-Resolution Cranial Defect Reconstruction by Iterative, Low-Resolution, Point Cloud Completion Transformers
AGH University of Science and Technology（AGH科技大学）；University of Applied Sciences Western Switzerland (HES-SO Valais)（瑞士西部应用科学大学（瓦莱州高等学院））；Information Systems Institute（信息系统研究所）
Korea University（高丽大学）；Sony AI（索尼人工智能）；Sejong University（世宗大学）
We propose a computational approach for recipe ideation, a downstream task that helps users select and gather ingredients for creating dishes. To perform this task, we developed RecipeMind, a food affinity score prediction model that quantifies the suitability of adding an ingredient to set of other ingredients. We constructed a large-scale dataset containing ingredient co-occurrence based scores to train and evaluate RecipeMind on food affinity score prediction. Deployed in recipe ideation, RecipeMind helps the user expand an initial set of ingredients by suggesting additional ingredients. Ex…
GeoFormer: Learning Point Cloud Completion with Tri-Plane Integrated Transformer
ShanghaiTech University（上海科技大学）；Xiaohongshu Inc.（小红书公司）；Shanghai Jiao Tong University（上海交通大学）；The University of Hong Kong（香港大学）；HKU Shanghai Advanced Computing and Intelligent Technology Research Institute（港沪高级计算与智能技术研究院）
In many vision and robotics applications, it is common that the captured objects are represented by very few points. Most of the existing completion methods are designed for partial point clouds with many points, and they perform poorly or even fail completely in the case of few points. However, due to the lack of detail information, completing objects from few points faces a huge challenge. Inspired by the successful applications of GAN and Transformers in the image-based vision task, we introduce GAN and Transformer techniques to address the above problem. Firstly, the end-to-end encoder-dec…
Technische Universität München（慕尼黑工业大学）；Google Inc.（谷歌公司）
We propose a novel approach aimed at object and semantic scene completion from a partial scan represented as a 3D point cloud. Our architecture relies on three novel layers that are used successively within an encoder-decoder structure and specifically developed for the task at hand. The first one carries out feature extraction by matching the point features to a set of pre-trained local descriptors. Then, to avoid losing individual descriptors as part of standard operations such as max-pooling, we propose an alternative neighbor-pooling operation that relies on adopting the feature vectors wi…
PointSSC: A Cooperative Vehicle-Infrastructure Point Cloud Benchmark for Semantic Scene Completion
Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University（复旦大学脑智能科学与技术研究院）；Mogo Auto Intelligence and Telematics Information Technology Company Ltd.（摩智智行智能与远程信息技术有限公司）
3DMambaComplete: Exploring Structured State Space Model for Point Cloud Completion
Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University（复旦大学计算机学院数据科学实验室）；Department of Information Engineering, The Chinese University of Hong Kong（香港中文大学信息工程系）
MGPC: Multimodal Network for Generalizable Point Cloud Completion With Modality Dropout and Progressive Decoding
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation of Chinese Academy of Sciences（中国科学院自动化研究所 multimodal 人工智能系统国家重点实验室）；Chemical Defense Institute, Academy of Military Sciences（军事科学院化学防御研究院）；Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation of Chinese Academy of Sciences（中国科学院自动化研究所 复杂系统认知与决策智能重点实验室）
Hikvision Research Institute（海康威视研究院）；Sichuan University（四川大学）；Zhejiang University（浙江大学）
The rapid development of point cloud learning has driven point cloud completion into a new era. However, the information flows of most existing completion methods are solely feedforward, and high-level information is rarely reused to improve low-level feature learning. To this end, we propose a novel Feedback Network (FBNet) for point cloud completion, in which present features are efficiently refined by rerouting subsequent fine-grained ones. Firstly, partial inputs are fed to a Hierarchical Graph-based Network (HGNet) to generate coarse shapes. Then, we cascade several Feedback-Aware Complet…
Designing a synthetic crown is a time-consuming, inconsistent, and labor-intensive process. In this work, we present a fully automatic method that not only learns human design dental crowns, but also improves the consistency, functionality, and esthetic of the crowns. Following success in point cloud completion using the transformer-based network, we tackle the problem of the crown generation as a point-cloud completion around a prepared tooth. To this end, we use a geometry-aware transformer to generate dental crowns. Our main contribution is to add a margin line information to the network, a…
MAGE: View-guided Point Cloud Completion with Efficient Modality Alignment and Adaptive Geometry Enhancement
MAIS, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所MAIS研究室）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；GIPSA-lab, Univ. Grenoble Alpes, CNRS, Grenoble INP（格勒诺布尔大学GIPSA实验室，法国国家科学研究中心，格勒诺布尔国立综合理工学院）
3D automatic annotation has received increased attention since manually annotating 3D point clouds is laborious. However, existing methods are usually complicated, e.g., pipelined training for 3D foreground/background segmentation, cylindrical object proposals, and point completion. Furthermore, they often overlook the inter-object feature relation that is particularly informative to hard samples for 3D annotation. To this end, we propose a simple yet effective end-to-end Context-Aware Transformer (CAT) as an automated 3D-box labeler to generate precise 3D box annotations from 2D boxes, traine…
Large Depth Completion Model from Sparse Observations
Zhejiang University（浙江大学）；Tongyi Lab, Alibaba Group（阿里云实验室）；Fudan University（复旦大学）；Ningbo Innovation Center, Zhejiang University（宁波创新中心，浙江大学）；NingboTech University（宁波科技学院）；Jinhua Institute of Zhejiang University（金华大学浙大研究院）
Technical University of Munich (TUM)（慕尼黑工业大学）；Xiamen University（厦门大学）
As a dynamic and essential component in the road environment of urban scenarios, vehicles are the most popular investigation targets. To monitor their behavior and extract their geometric characteristics, an accurate and instant measurement of vehicles plays a vital role in traffic and transportation fields. Point clouds acquired from the mobile laser scanning (MLS) system deliver 3D information of road scenes with unprecedented detail. They have proven to be an adequate data source in the fields of intelligent transportation and autonomous driving, especially for extracting vehicles. However,…
Three-dimentional reconstruction of complex, dynamic population canopy architecture for crops with a novel point cloud completion model: A case study in Brassica napus rapeseed
Heriot-Watt University（赫瑞-瓦特大学）；Amazon Alexa AI（亚马逊 Alexa AI）；University of Southern California（南加州大学）
Language-guided robots performing home and office tasks must navigate in and interact with the world. Grounding language instructions against visual observations and actions to take in an environment is an open challenge. We present Embodied BERT (EmBERT), a transformer-based model which can attend to high-dimensional, multi-modal inputs across long temporal horizons for language-conditioned task completion. Additionally, we bridge the gap between successful object-centric navigation models used for non-interactive agents and the language-guided visual task completion benchmark, ALFRED, by int…
City University of Hong Kong（香港城市大学）；Microsoft Cloud + AI（微软云与人工智能部门）
Image completion has made tremendous progress with convolutional neural networks (CNNs), because of their powerful texture modeling capacity. However, due to some inherent properties (e.g., local inductive prior, spatial-invariant kernels), CNNs do not perform well in understanding global structures or naturally support pluralistic completion. Recently, transformers demonstrate their power in modeling the long-term relationship and generating diverse results, but their computation complexity is quadratic to input length, thus hampering the application in processing high-resolution images. This…
NetEase Fuxi AI Lab（网易伏羲人工智能实验室）；University of Michigan（密歇根大学）；NetEase（网易）
Motion completion is a challenging and long-discussed problem, which is of great significance in film and game applications. For different motion completion scenarios (in-betweening, in-filling, and blending), most previous methods deal with the completion problems with case-by-case designs. In this work, we propose a simple but effective method to solve multiple motion completion problems under a unified framework and achieves a new state of the art accuracy under multiple evaluation settings. Inspired by the recent great success of attention-based models, we consider the completion as a sequ…
TransBridge: Boost 3D Object Detection by Scene-Level Completion with Transformer Decoder
School of Computer Science, Beijing Institute of Technology（北京理工大学计算机科学学院）；Robotics and Autonomous Driving Lab (RAL), Baidu Research（百度研究机器人与自动驾驶实验室）；State Key Laboratory of Internet of Things for Smart City, Department of Computer and Information Science, University of Macau（澳门大学智能城市物联网国家重点实验室，计算机与信息科学系）
TDCNet: Transparent Objects Depth Completion with CNN-Transformer Dual-Branch Parallel Network
Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences（中国科学院长春光学精密机械与物理研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Harbin Institute of Technology（哈尔滨工业大学）；College of Physics, Northeast Normal University（东北师范大学物理学院）
