Depth completion aims to predict dense depth maps with sparse depth measurements from a depth sensor. Currently, Convolutional Neural Network (CNN) based models are the most popular methods applied to depth completion tasks. However, despite the excellent high-end performance, they suffer from a limited representation area. To overcome the drawbacks of CNNs, a more effective and powerful method has been presented: the Transformer, which is an adaptive self-attention setting sequence-to-sequence model. While the standard Transformer quadratically increases the computational cost from the key-query dot-product of input resolution which improperly employs depth completion tasks. In this work, we propose a different window-based Transformer architecture for depth completion tasks named Sparse-to-Dense Transformer (SDformer). The network consists of an input module for the depth map and RGB image features extraction and concatenation, a U-shaped encoder-decoder Transformer for extracting deep features, and a refinement module. Specifically, we first concatenate the depth map features with the RGB image features through the input model. Then, instead of calculating self-attention with the whole feature maps, we apply different window sizes to extract the long-range depth dependencies. Finally, we refine the predicted features from the input module and the U-shaped encoder-decoder Transformer module to get the enriching depth features and employ a convolution layer to obtain the dense depth map. In practice, the SDformer obtains state-of-the-art results against the CNN-based depth completion models with lower computing loads and parameters on the NYU Depth V2 and KITTI DC datasets.
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, …
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）
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…
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…
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 …
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）
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 …
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…
CVSformer: Cross-View Synthesis Transformer for Semantic Scene Completion
Tianjin University（天津大学）；Shenzhen University（深圳大学）；A*STAR（新加坡科技研究局）；The Hong Kong Polytechnic University（香港理工大学）；South China University of Technology（华南理工大学）；Alibaba Damo Academy（阿里巴巴达摩院）
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）
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 model…
Bridging global context interactions correctly is important for high-fidelity image completion with large masks. Previous methods attempting this via deep or large receptive field (RF) convolutions cannot escape from the dominance of nearby interactions, which may be inferior. In this paper, we propose to treat image completion as a directionless sequence-to-sequence prediction task, and deploy a transformer to directly capture long-range dependence in the encoder. Crucially, we employ a restrictive CNN with small and non-overlapping RF for weighted token representation, which allows the trans…
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）
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…
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…
Transformer based Pluralistic Image Completion with Reduced Information Loss
School of Computer Science and Technology, Beijing Institute of Technology（北京理工大学计算机科学与技术学院）；School of Information Science and Technology, University of Science and Technology of China（中国科学技术大学信息科学技术学院）；Microsoft Cloud AI（微软云人工智能部门）；Wormpex AI Research LLC（Wormpex人工智能研究有限责任公司）
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…
Columbia University（哥伦比亚大学）；Google（谷歌）；U.S. Army Research Laboratory（美国陆军研究实验室）
We propose the Multiple View Performer (MVP) - a new architecture for 3D shape completion from a series of temporally sequential views. MVP accomplishes this task by using linear-attention Transformers called Performers. Our model allows the current observation of the scene to attend to the previous ones for more accurate infilling. The history of past observations is compressed via the compact associative memory approximating modern continuous Hopfield memory, but crucially of size independent from the history length. We compare our model with several baselines for shape completion over time,…
We address the problem of generating a 360-degree image from a single image with a narrow field of view by estimating its surroundings. Previous methods suffered from overfitting to the training resolution and deterministic generation. This paper proposes a completion method using a transformer for scene modeling and novel methods to improve the properties of a 360-degree image on the output image. Specifically, we use CompletionNets with a transformer to perform diverse completions and AdjustmentNet to match color, stitching, and resolution with an input image, enabling inference at any resol…
Technical University of Denmark（丹麦技术大学）；Ecole des Ponts（巴黎路桥学院）；Meta
Most pipelines for Augmented and Virtual Reality estimate the ego-motion of the camera by creating a map of sparse 3D landmarks. In this paper, we tackle the problem of depth completion, that is, densifying this sparse 3D map using RGB images as guidance. This remains a challenging problem due to the low density, non-uniform and outlier-prone 3D landmarks produced by SfM and SLAM pipelines. We introduce a transformer block, SparseFormer, that fuses 3D landmarks with deep visual features to produce dense depth. The SparseFormer has a global receptive field, making the module especially effectiv…
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）
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）
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…
FMI for Biomedical Research（FMI生物医学研究所）；Fondazione Human Technopole（人类技术基金会）
Transformer architectures show spectacular performance on NLP tasks and have recently also been used for tasks such as image completion or image classification. Here we propose to use a sequential image representation, where each prefix of the complete sequence describes the whole image at reduced resolution. Using such Fourier Domain Encodings (FDEs), an auto-regressive image completion task is equivalent to predicting a higher resolution output given a low-resolution input. Additionally, we show that an encoder-decoder setup can be used to query arbitrary Fourier coefficients given a set of …
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…
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）
Australian National University（澳大利亚国立大学）；SenseTime（商汤科技）
Weakly Supervised Semantic Segmentation (WSSS) is challenging, particularly when image-level labels are used to supervise pixel level prediction. To bridge their gap, a Class Activation Map (CAM) is usually generated to provide pixel level pseudo labels. CAMs in Convolutional Neural Networks suffer from partial activation ie, only the most discriminative regions are activated. Transformer based methods, on the other hand, are highly effective at exploring global context with long range dependency modeling, potentially alleviating the "partial activation" issue. In this paper, we propose the fi…
University of California, Irvine（加州大学欧文分校）；Georgia Institute of Technology（佐治亚理工学院）
We tackle the problem of automatically reconstructing a complete 3D model of a scene from a single RGB image. This challenging task requires inferring the shape of both visible and occluded surfaces. Our approach utilizes viewer-centered, multi-layer representation of scene geometry adapted from recent methods for single object shape completion. To improve the accuracy of view-centered representations for complex scenes, we introduce a novel "Epipolar Feature Transformer" that transfers convolutional network features from an input view to other virtual camera viewpoints, and thus better covers…
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）
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…
Training state-of-the-art models for human pose estimation in videos requires datasets with annotations that are really hard and expensive to obtain. Although transformers have been recently utilized for body pose sequence modeling, related methods rely on pseudo-ground truth to augment the currently limited training data available for learning such models. In this paper, we introduce PoseBERT, a transformer module that is fully trained on 3D Motion Capture (MoCap) data via masked modeling. It is simple, generic and versatile, as it can be plugged on top of any image-based model to transform i…
