Previous online 3D dense reconstruction methods struggle to achieve the balance between memory storage and surface quality, largely due to the usage of stagnant underlying geometry representation, such as TSDF (truncated signed distance functions) or surfels, without any knowledge of the scene priors. In this paper, we present DI-Fusion (Deep Implicit Fusion), based on a novel 3D representation, i.e. Probabilistic Local Implicit Voxels (PLIVoxs), for online 3D reconstruction with a commodity RGB-D camera. Our PLIVox encodes scene priors considering both the local geometry and uncertainty parameterized by a deep neural network. With such deep priors, we are able to perform online implicit 3D reconstruction achieving state-of-the-art camera trajectory estimation accuracy and mapping quality, while achieving better storage efficiency compared with previous online 3D reconstruction approaches. Our implementation is available at https://www.github.com/huangjh-pub/di-fusion.
Online semantic 3D segmentation in company with real-time RGB-D reconstruction poses special challenges such as how to perform 3D convolution directly over the progressively fused 3D geometric data, and how to smartly fuse information from frame to frame. We propose a novel fusion-aware 3D point convolution which operates directly on the geometric surface being reconstructed and exploits effectively the inter-frame correlation for high quality 3D feature learning. This is enabled by a dedicated dynamic data structure which organizes the online acquired point cloud with global-local trees. Glob…
Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；Delft University of Technology（代尔夫特理工大学）；The University of Manchester（曼彻斯特大学）
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 (HR…
KU Leuven（鲁汶大学）；Google Research（谷歌研究院）；ETH Zürich（苏黎世联邦理工学院）；University of Amsterdam（阿姆斯特丹大学）；Lund University（隆德大学）
Many hand-held or mixed reality devices are used with a single sensor for 3D reconstruction, although they often comprise multiple sensors. Multi-sensor depth fusion is able to substantially improve the robustness and accuracy of 3D reconstruction methods, but existing techniques are not robust enough to handle sensors which operate with diverse value ranges as well as noise and outlier statistics. To this end, we introduce SenFuNet, a depth fusion approach that learns sensor-specific noise and outlier statistics and combines the data streams of depth frames from different sensors in an online…
University of Oxford（牛津大学）；Tsinghua-Berkeley Shenzhen Institute, Tsinghua University（清华大学清华-伯克利深圳学院）
Dense 3D reconstruction from a stream of depth images is the key to many mixed reality and robotic applications. Although methods based on Truncated Signed Distance Function (TSDF) Fusion have advanced the field over the years, the TSDF volume representation is confronted with striking a balance between the robustness to noisy measurements and maintaining the level of detail. We present Bi-level Neural Volume Fusion (BNV-Fusion), which leverages recent advances in neural implicit representations and neural rendering for dense 3D reconstruction. In order to incrementally integrate new depth map…
The University of Adelaide（阿德莱德大学）；InnoPeak Technology, Inc.（InnoPeak科技公司）；Monash University（莫纳什大学）；Australian National University（澳大利亚国立大学）
A high-quality 3D reconstruction of a scene from a collection of 2D images can be achieved through offline/online mapping methods. In this paper, we explore active mapping from the perspective of implicit representations, which have recently produced compelling results in a variety of applications. One of the most popular implicit representations - Neural Radiance Field (NeRF), first demonstrated photorealistic rendering results using multi-layer perceptrons, with promising offline 3D reconstruction as a by-product of the radiance field. More recently, researchers also applied this implicit re…
We propose POse-guided SElective Fusion (POSEFusion), a single-view human volumetric capture method that leverages tracking-based methods and tracking-free inference to achieve high-fidelity and dynamic 3D reconstruction. By contributing a novel reconstruction framework which contains pose-guided keyframe selection and robust implicit surface fusion, our method fully utilizes the advantages of both tracking-based methods and tracking-free inference methods, and finally enables the high-fidelity reconstruction of dynamic surface details even in the invisible regions. We formulate the keyframe s…
BNRist（北京信息科学与技术国家研究中心）；Tsinghua University（清华大学）；Beijing Normal University（北京师范大学）；City University of Hong Kong（香港城市大学）；Tencent PCG（腾讯平台与内容事业群）
High-fidelity 3D scene reconstruction from monocular videos continues to be challenging, especially for complete and fine-grained geometry reconstruction. The previous 3D reconstruction approaches with neural implicit representations have shown a promising ability for complete scene reconstruction, while their results are often over-smooth and lack enough geometric details. This paper introduces a novel neural implicit scene representation with volume rendering for high-fidelity online 3D scene reconstruction from monocular videos. For fine-grained reconstruction, our key insight is to incorpo…
GSFusion: Online RGB-D Mapping Where Gaussian Splatting Meets TSDF Fusion
Smart Robotics Lab, Technical University of Munich（慕尼黑工业大学智能机器人实验室）；Munich Institute of Robotics and Machine Intelligence (MIRMI)（慕尼黑机器人与机器智能研究所）；Smart Robotics Lab, Imperial College London（伦敦帝国理工学院智能机器人实验室）
RemixFusion: Residual-based Mixed Representation for Large-scale Online RGB-D Reconstruction
National Key Laboratory of Parallel and Distributed Computing（平行与分布式计算国家重点实验室）；National University of Defense Technology（国防科技大学）；Peking University（北京大学）；Xiangjiang Laboratory（湘江实验室）
Zhejiang University（浙江大学）；University of Bristol（布里斯托大学）；SenseTime（商汤科技）
In this work, we present a dense tracking and mapping system named Vox-Fusion, which seamlessly fuses neural implicit representations with traditional volumetric fusion methods. Our approach is inspired by the recently developed implicit mapping and positioning system and further extends the idea so that it can be freely applied to practical scenarios. Specifically, we leverage a voxel-based neural implicit surface representation to encode and optimize the scene inside each voxel. Furthermore, we adopt an octree-based structure to divide the scene and support dynamic expansion, enabling our sy…
Johns Hopkins University（约翰斯·霍普金斯大学）；Reality Labs, Meta Inc.（Meta公司现实实验室）
Temporally consistent depth estimation is crucial for online applications such as augmented reality. While stereo depth estimation has received substantial attention as a promising way to generate 3D information, there is relatively little work focused on maintaining temporal stability. Indeed, based on our analysis, current techniques still suffer from poor temporal consistency. Stabilizing depth temporally in dynamic scenes is challenging due to concurrent object and camera motion. In an online setting, this process is further aggravated because only past frames are available. We present a f…
We present the first single-view 3D reconstruction network aimed at recovering geometric details from an input image which encompass both topological shape structures and surface features. Our key idea is to train the network to learn a detail disentangled reconstruction consisting of two functions, one implicit field representing the coarse 3D shape and the other capturing the details. Given an input image, our network, coined D$^2$IM-Net, encodes it into global and local features which are respectively fed into two decoders. The base decoder uses the global features to reconstruct a coarse i…
University of Electronic Science and Technology of China（电子科技大学）
Infrared and visible images, as multi-modal image pairs, show significant differences in the expression of the same scene. The image fusion task is faced with two problems: one is to maintain the unique features between different modalities, and the other is to maintain features at various levels like local and global features. This paper discusses the limitations of deep learning models in image fusion and the corresponding optimization strategies. Based on artificially designed structures and constraints, we divide models into explicit models, and implicit models that adaptively learn high-l…
The Institute of Industrial Science, The University of Tokyo（东京大学生产技术研究所）；The National Institute of Advanced Industrial Science and Technology (AIST)（日本产业技术综合研究所）
GAMMA: Graspability-Aware Mobile MAnipulation Policy Learning based on Online Grasping Pose Fusion
CFCS, School of Computer Science, Peking University（北京大学计算机学院CFCS）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）；Galbot Tongji University（同济大学Galbot）
We present a novel online depth map fusion approach that learns depth map aggregation in a latent feature space. While previous fusion methods use an explicit scene representation like signed distance functions (SDFs), we propose a learned feature representation for the fusion. The key idea is a separation between the scene representation used for the fusion and the output scene representation, via an additional translator network. Our neural network architecture consists of two main parts: a depth and feature fusion sub-network, which is followed by a translator sub-network to produce the fin…
Implicit Neural Feature Fusion Function for Multispectral and Hyperspectral Image Fusion
University of Electronic Science and Technology of China（电子科技大学）；Institute of Methodologies for Environmental Analysis (CNR-IMAA)（环境分析研究所（CNR-IMAA））；National Biodiversity Future Center（国家生物多样性未来中心）
Infrared and Visible Image Fusion Based on Implicit Neural Representations
College of Computer Science, Beijing Information Science and Technology University（北京信息科技大学计算机学院）；School of Mathematical Sciences, Capital Normal University（首都师范大学数学学院）
Beijing University of Posts and Telecommunications（北京邮电大学）；Beijing Key Laboratory of Space-ground Interconnection and Convergence（北京天地互联与融合重点实验室）
Online knowledge distillation conducts knowledge transfer among all student models to alleviate the reliance on pre-trained models. However, existing online methods rely heavily on the prediction distributions and neglect the further exploration of the representational knowledge. In this paper, we propose a novel Multi-scale Feature Extraction and Fusion method (MFEF) for online knowledge distillation, which comprises three key components: Multi-scale Feature Extraction, Dual-attention and Feature Fusion, towards generating more informative feature maps for distillation. The multiscale feature…
We present DeepSurfels, a novel hybrid scene representation for geometry and appearance information. DeepSurfels combines explicit and neural building blocks to jointly encode geometry and appearance information. In contrast to established representations, DeepSurfels better represents high-frequency textures, is well-suited for online updates of appearance information, and can be easily combined with machine learning methods. We further present an end-to-end trainable online appearance fusion pipeline that fuses information from RGB images into the proposed scene representation and is trained…
An increasing number of laser powder bed fusion machines use off-axis infrared cameras to improve online monitoring and data-driven control capabilities. However, there is still a severe lack of algorithmic solutions to properly process the infrared images from these cameras that has led to several key limitations: a lack of online monitoring capabilities for the laser tracks, insufficient pre-processing of the infrared images for data-driven methods, and large memory requirements for storing the infrared images. To address these limitations, we study over 30 segmentation algorithms that segme…
O2V-Mapping: Online Open-Vocabulary Mapping with Neural Implicit Representation
Academy for Engineering & Technology（工程与技术学院）；Fudan University（复旦大学）；State Key Laboratory of Intelligent Vehicle Safety Technology（智能车辆安全技术国家重点实验室）；School of Future Technology（未来技术学院）；Harbin Institute of Technology（哈尔滨工业大学）；Department of Computer Science and Engineering（计算机科学与工程系）；Shanghai Jiao Tong University（上海交通大学）
Bilkent University（比尔肯特大学）；Texas A&M University at Qatar（德州农工大学卡塔尔分校）
In this paper, an Entropy functional based online Adaptive Decision Fusion (EADF) framework is developed for image analysis and computer vision applications. In this framework, it is assumed that the compound algorithm consists of several sub-algorithms each of which yielding its own decision as a real number centered around zero, representing the confidence level of that particular sub-algorithm. Decision values are linearly combined with weights which are updated online according to an active fusion method based on performing entropic projections onto convex sets describing sub-algorithms. I…
Recently, transformer-based image segmentation methods have achieved notable success against previous solutions. While for video domains, how to effectively model temporal context with the attention of object instances across frames remains an open problem. In this paper, we propose an online video instance segmentation framework with a novel instance-aware temporal fusion method. We first leverages the representation, i.e., a latent code in the global context (instance code) and CNN feature maps to represent instance- and pixel-level features. Based on this representation, we introduce a crop…
We propose a learning framework named Feature Fusion Learning (FFL) that efficiently trains a powerful classifier through a fusion module which combines the feature maps generated from parallel neural networks. Specifically, we train a number of parallel neural networks as sub-networks, then we combine the feature maps from each sub-network using a fusion module to create a more meaningful feature map. The fused feature map is passed into the fused classifier for overall classification. Unlike existing feature fusion methods, in our framework, an ensemble of sub-network classifiers transfers i…
DiffSemanticFusion: Semantic Raster BEV Fusion for Autonomous Driving via Online HD Map Diffusion
Bosch Corporate Research, Bosch (China) Investment Ltd.（博世企业研究院、博世（中国）投资有限公司）；School of Communication and Information Engineering, Shanghai University（上海大学通信与信息工程学院）；Shanghai Jiaotong University（上海交通大学）；AIR, Tsinghua University（清华大学人工智能研究院）；Robert Bosch GmbH（罗伯特·博世集团）
MIT Computer Science and Artificial Intelligence Laboratory（麻省理工学院计算机科学与人工智能实验室）
In this paper, we present a multi-modal online person verification system using both speech and visual signals. Inspired by neuroscientific findings on the association of voice and face, we propose an attention-based end-to-end neural network that learns multi-sensory associations for the task of person verification. The attention mechanism in our proposed network learns to conditionally select a salient modality between speech and facial representations that provides a balance between complementary inputs. By virtue of this capability, the network is robust to missing or corrupted data from e…
Microsoft Research Asia（微软亚洲研究院）；Carnegie Mellon University（卡内基梅隆大学）；Huazhong University of Science and Technology（华中科技大学）
Video instance segmentation (VIS) aims at classifying, segmenting and tracking object instances in video sequences. Recent transformer-based neural networks have demonstrated their powerful capability of modeling spatio-temporal correlations for the VIS task. Relying on video- or clip-level input, they suffer from high latency and computational cost. We propose a robust context fusion network to tackle VIS in an online fashion, which predicts instance segmentation frame-by-frame with a few preceding frames. To acquire the precise and temporal-consistent prediction for each frame efficiently, t…
The Center for Machine Perception, FEE CTU in Prague（捷克布拉格技术大学电气工程学院机器感知中心）；Faculty of Civil Engineering, CTU in Prague（捷克布拉格技术大学土木工程学院）
In this paper, we propose a novel method for visual object tracking called HMMTxD. The method fuses observations from complementary out-of-the box trackers and a detector by utilizing a hidden Markov model whose latent states correspond to a binary vector expressing the failure of individual trackers. The Markov model is trained in an unsupervised way, relying on an online learned detector to provide a source of tracker-independent information for a modified Baum- Welch algorithm that updates the model w.r.t. the partially annotated data. We show the effectiveness of the proposed method on com…
With the digitization of travel industry, it is more and more important to understand users from their online behaviors. However, online travel industry data are more challenging to analyze due to extra sparseness, dispersed user history actions, fast change of user interest and lack of direct or indirect feedbacks. In this work, a new similarity method is proposed to measure the destination similarity in terms of implicit user interest. By comparing the proposed method to several other widely used similarity measures in recommender systems, the proposed method achieves a significant improveme…
ETH Zürich（苏黎世联邦理工学院）；CVL, ETH Zürich（苏黎世联邦理工学院计算机视觉实验室）；PSI, KU Leuven（鲁汶大学）；CVG Group at ETH Zürich（苏黎世联邦理工学院计算机视觉与几何组）；Google Research Zürich（谷歌苏黎世研究院）
This paper presents a real-time online vision framework to jointly recover an indoor scene's 3D structure and semantic label. Given noisy depth maps, a camera trajectory, and 2D semantic labels at train time, the proposed deep neural network based approach learns to fuse the depth over frames with suitable semantic labels in the scene space. Our approach exploits the joint volumetric representation of the depth and semantics in the scene feature space to solve this task. For a compelling online fusion of the semantic labels and geometry in real-time, we introduce an efficient vortex pooling bl…
Hubei University of Technology（湖北工业大学）；Huazhong University of Science and Technology（华中科技大学）；Nanjing University（南京大学）
Affinity graph-based segmentation methods have become a major trend in computer vision. The performance of these methods relies on the constructed affinity graph, with particular emphasis on the neighborhood topology and pairwise affinities among superpixels. Due to the advantages of assimilating different graphs, a multi-scale fusion graph has a better performance than a single graph with single-scale. However, these methods ignore the noise from images which influences the accuracy of pairwise similarities. Multi-scale combinatorial grouping and graph fusion also generate a higher computatio…
NavMapFusion: Diffusion-based Fusion of Navigation Maps for Online Vectorized HD Map Construction
Mercedes-Benz Research & Development North America, USA（梅赛德斯-奔驰北美研究与开发）；University of Stuttgart, Germany（斯图加特大学）；University of California, San Diego, USA（加州大学圣地亚哥分校）；University of Southampton, United Kingdom（南安普顿大学）
