76 accepted papers
Magnetic microrobots hold great promise for biomedical applications. However, achieving flexible magnetic field adjustment with a magnetic actuation system (MAS) to actuate diverse microrobots remains a significant challenge. In this work, we propose an Electromagnetic-Permanent Magnet Actuation (EP…
Deep hypergraph clustering has shown strong potential in learning node representations by modeling high-order relationships. However, most existing methods rely on fixed propagation mechanisms that implicitly assume homophily, where connected nodes tend to be similar. This assumption often fails in …
Fair incomplete multi-view clustering (FIMVC) confronts a critical yet unresolved challenge, as existing methods often fail to address the intertwined issues of data missingness and algorithmic bias simultaneously. In this paper, we propose a novel FIMVC method named Adversarial Fair Incomplete Mult
Multi-view clustering achieves outstanding performance but relies on the assumption of complete multi-view samples. However, certain views may be partially unavailable due to failures during acquisition or storage, resulting in distribution shifts across views. Although some incomplete multi-view cl…
Marginal Fisher Analysis (MFA) is a classical dimensionality reduction (DR) method that leverages dual graphs to capture intra-class compactness and inter-class separability. However, MFA’s reliance on high-quality labels limits its practical application. For another, existing unsupervised DR method
Self-supervised pre-training has driven rapid progress in foundation models for language, 2D images, and video, yet remains largely unexplored for learning 3D-aware representations from multi-view images. In this paper, we present E-RayZer, a self-supervised 3D vision model that learns geometrically
Reliable 3D reconstruction from in-the-wild image collections is often hindered by noisy images--irrelevant inputs with little or no view overlap with others. While traditional Structure-from-Motion pipelines handle such cases through geometric verification and outlier rejection, feed-forward 3D rec
Federated Multi-View Clustering has gained increasing attention for its ability to discover complementary clustering structures of distributed multi-view data while preserving data privacy. However, real-world clients often only have access to partial views, and the view incompleteness poses great c
The emergence of Large Vision-Language Models (LVLMs) has significantly advanced video understanding capabilities. However, existing benchmarks focus predominantly on coarse-grained tasks such as action segmentation, classification, captioning, and retrieval. Furthermore, these benchmarks often rely
Eye gaze-based control interfaces provide a non-invasive means of enhancing human-robot collaboration for activities of daily living and can reduce the cognitive burden on operators performing complex tasks. Eye gaze has traditionally been used for "gaze triggering," where fixating on an object acti…
Control of soft robots is considered one of the key elements in achieving their intelligence. However, it faces challenging problems such as nonlinear dynamics, highly deformable structures, and operation in unpredictable situations. Numerous methods have been proposed to overcome these challenges, …
Remote sensing images are becoming increasingly widespread in military, earth resource exploration. Because of the limitation of a single sensor, we can obtain high spatial resolution grayscale panchromatic (PAN) images and low spatial resolution color multispectral (MS) images. Therefore, an import
Mitigating noisy correspondence in cross-modal matching poses a serious challenge due to the problem of error accumulation. Existing methods primarily attribute this accumulation to errors caused by noisy sample pairs. However, a novel source of error from clean sample pairs (also termed anchor pair
Hypergraph Clustering has gained significant attention due to its capability of capturing high order structural information. Among different approaches, contrastive learning-based methods leverage self-supervised learning and data augmentation, exhibiting impressive performance. However, most of the
The success of existing deep multi-view graph clustering methods is based on the assumption that node attributes are fully available across all views. However, in practical scenarios, node attributes are frequently missing due to factors such as data privacy concerns or failures in data collection d…
Finding semantic correspondences between images is a challenging problem in computer vision, particularly under significant viewpoint changes. Previous methods rely on semantic features from pre-trained 2D models like Stable Diffusion and DINOv2, which often struggle to extract viewpoint-invariant f…
We present a unified framework capable of solving a broad range of 3D tasks. Our approach features a stateful recurrent model that continuously updates its state representation with each new observation. Given a stream of images, this evolving state can be used to generate metric-scale pointmaps (pe…
Multi-view clustering aims to identify consistent and complementary information across multiple views to partition data into clusters, emerging as a popular unsupervised method for multi-view data analysis. However, existing methods often design view-specific encoders to extract distinct features fr…
Multi-view clustering is effective in unsupervised multi-view data analysis and has received considerable attention. However, most existing methods excessively emphasize certain attributes, resulting in unfair clustering outcomes, i.e., certain sensitive attributes dominate the clustering results. M…
Current deep multi-modal graph clustering methods primarily rely on Graph Neural Network (GNN) to fully exploit attribute features and graph structures, including message propagation and low-dimensional feature embedding. However, these methods lack further exploration of graph structural informatio…
We introduce a model named DreamLight for universal image relighting in this work, which can seamlessly composite subjects into a new background while maintaining aesthetic uniformity in terms of lighting and color tone. The background can be specified by natural images (image-based relighting) or g…
Contrastive multi-view clustering has demonstrated remarkable potential in complex data analysis, yet existing approaches face two critical challenges: difficulty in constructing high-quality positive and negative pairs and high computational overhead due to static optimization strategies. To addres
Linear Discriminant Analysis (LDA) is a classical supervised dimensionality reduction algorithm. However, LDA focuses more on global structure and overly depends on reliable data labels. For data with outliers and nonlinear structures, LDA cannot effectively capture the true structure of the data. M
Incomplete multi-view clustering (IMVC) extracts consistent and complementary information from multi-source/modality data with missing views, aiming to partition the data into different clusters. It can effectively address the problem of unsupervised multi-source data analysis in complex environment
Federated Multi-View Clustering (FedMVC) aims to uncover consistent clustering structures from distributed multi-view data for clustering while preserving data privacy. However, existing FedMVC methods under vertical settings either ignore the ubiquitous incomplete view issue or require uploading da
Swarming microrobots offer great promise for targeted delivery in biofluidic environments. However, current approaches insufficiently utilize the operator’s perceptual awareness and interactive decision-making capabilities. This work proposes a real-time navigation and control strategy with haptic f
Existing hypergraph clustering methods typically assume that node attributes are fully available. However, in real-world scenarios, missing node attributes are common for the sake of privacy or due to data noise. While some approaches attempt to handle missing attributes in traditional graphs, they…
Multi-view clustering integrates the consistency and complementarity of different views to achieve unsupervised data grouping. Existing multi-view clustering methods primarily confront two challenges: i) they generally perform feature extraction in the feature domain, which is sensitive to noise and…
Collective microrobots enable controlled batch delivery, showing promising application in the biomedical field. However, significant challenges remain in achieving long-distance delivery of collective microrobots in dynamic environments. This study proposes a magnetic actuation strategy for deliveri
We present a system that allows for accurate, fast, and robust estimation of camera parameters and depth maps from casual monocular videos of dynamic scenes. Most conventional structure from motion and monocular SLAM techniques assume input videos that feature predominantly static scenes with large…
Microrobotic swarms have shown promising features due to their collective and flexible behaviours, while achieving precise swarm control and autonomous navigation in complex environments remains a challenge. Here, we propose a Transformer-based reinforcement learning strategy that integrates Proxima
Multi-view clustering (MVC) methods have garnered considerable attention within centralized data frameworks. However, real-world multi-view data are often collected and stored by different organizations, complicating the practical deployment of MVC and motivating the emergence of federated multi-vie…
Moving object segmentation is a crucial task for achieving a high-level understanding of visual scenes and has numerous downstream applications. Humans can effortlessly segment moving objects in videos. Previous work has largely relied on optical flow to provide motion cues; however, this approach o…
Magnetic microrobots are showing great potential in micromanipulation due to the capability of motion control under external fields. However, achieving selective control of magnetic microrobots in three-dimensional (3D) space using global magnetic fields still presents a challenge. In this work, we
Monocular dynamic reconstruction is a challenging and long-standing vision problem due to the highly ill-posed nature of the task. Existing approaches depend on templates, are effective only in quasi-static scenes, or fail to model 3D motion explicitly. We introduce a method for reconstructing gener…
Dynamic 3D reconstruction and point tracking in videos are typically treated as separate tasks, despite their deep connection. We propose St4RTrack, a feed-forward frame- work that simultaneously reconstructs and tracks dynamic video content in a world coordinate frame from RGB in- puts. This is ach…
Multi-view clustering (MVC) has emerged as an important unsupervised multi-view learning method that leverages consistent and complementary information to enhance clustering performance. Recently, tensorized MVC, which processes multi-view data as a tensor to capture their cross-view information, ha
Multi-view graph clustering methods have been widely concerned due to the ability of dealing with arbitrarily shaped datasets. However, many methods with higher time and space complexity make them challenging to deal with large-scale datasets. Besides, many fuzzy clustering methods needs additional…
K-Means clustering is a classical and effective unsupervised learning method attributed to its simplicity and efficiency. However, it faces notable challenges, including sensitivity to random initial centroid selection, a limited ability to discover the intrinsic manifold structures within nonlinear…
"Recent advancements in diffusion-based generative image editing have sparked a profound revolution, reshaping the landscape of image outpainting and inpainting tasks. Despite these strides, the field grapples with inherent challenges, including: i) inferior quality; ii) poor consistency; iii) insuf…
Multi-view clustering is a popular unsupervised multi-view learning method. Real-world multi-view data are often distributed across multiple entities, presenting a challenge for performing multi-view clustering. Federated learning provides a solution by enabling multiple entities to collaboratively…
Recently, anchor graph-based multi-view clustering has been proven to be highly efficient for large-scale data processing. However, most existing anchor graph-based clustering methods necessitate post-processing to obtain clustering labels and are unable to effectively utilize the information within…
Multi-view clustering is an effective method to process massive unlabeled multi-view data. Since data of different views may be collected and held by different parties, it becomes impractical to train a multi-view clustering model in a centralized way, for the sake of privacy. However, federated mul…
Introducing collective control strategies to microrobots provides a promising tool for enhancing the capability of individual microrobots and promoting the manipulation performance. However, controlling numerous micro-agents brings challenges to the precise control and deployment. Herein, an on-dema
Partial multi-view clustering is a challenging and practical research problem for data analysis in real-world applications, due to the potential data missing issue in different views. However, most existing methods have not fully explored the correlation information among various incomplete views. I…
Principal component analysis (PCA) is a popular unsupervised dimensionality reduction method to extract the principal components of data. However, there are two problems with the existing PCA: (1) Traditional PCA methods treat each sample equally and ignore sample differences. (2) They fail to extra…
Humans can learn to manipulate new objects by simply watching others; providing robots with the ability to learn from such demonstrations would enable a natural interface specifying new behaviors. This work develops Robot See Robot Do (RSRD), a method for imitating articulated object manipulation fr…
Recovering dense and long-range pixel motion in videos is a challenging problem. Part of the difficulty arises from the 3D-to-2D projection process leading to occlusions and discontinuities in the 2D motion domain. While 2D motion can be intricate we posit that the underlying 3D motion can often be…
Graph-based multimedia data clustering has attracted much attention due to the impressive clustering performance for arbitrarily shaped multimedia data. However, existing graph-based clustering methods need post-processing to get labels for multimedia data with high computational complexity. Moreove…
Although K-Means clustering has been widely studied due to its simplicity, these methods still have the following fatal drawbacks. Firstly, they need to initialize the cluster centers, which causes unstable clustering performance. Secondly, they have poor performance on non-Gaussian datasets. Inspir…
We consider the visual disambiguation task of determining whether a pair of visually similar images depict the same or distinct 3D surfaces (e.g., the same or opposite sides of a symmetric building). Illusory image matches, where two images observe distinct but visually similar 3D surfaces, can be c…
Finding correspondences between images is a fundamental problem in computer vision. In this paper, we show that correspondence emerges in image diffusion models without any explicit supervision. We propose a simple strategy to extract this implicit knowledge out of diffusion networks as image featur…
In this work, we aim to reconstruct a time-varying 3D model, capable of rendering photo-realistic renderings with independent control of viewpoint, illumination, and time, from Internet photos of large-scale landmarks. The core challenges are twofold. First, different types of temporal changes, such…
Multi-view clustering (MVC) based on non-negative matrix factorization (NMF) and its variants have attracted much attention due to their advantages in clustering interpretability. However, existing NMF-based multi-view clustering methods perform NMF on each view respectively and ignore the impact of…
We present a new test-time optimization method for estimating dense and long-range motion from a video sequence. Prior optical flow or particle video tracking algorithms typically operate within limited temporal windows, struggling to track through occlusions and maintain global consistency of estim…
We introduce 3D Moments, a new computational photography effect. As input we take a pair of near-duplicate photos, i.e., photos of moving subjects from similar viewpoints, common in people's photo collections. As output, we produce a video that smoothly interpolates the scene motion from the first p…
"We present a method for learning to generate unbounded flythrough videos of natural scenes starting from a single view. This capability is learned from a collection of single photographs, without requiring camera poses or even multiple views of each scene. To achieve this, we propose a novel self-s…
This paper addresses the challenge of reconstructing 3D indoor scenes from multi-view images. Many previous works have shown impressive reconstruction results on textured objects, but they still have difficulty in handling low-textured planar regions, which are common in indoor scenes. An approach t…
We present a new neural representation, called Neural Ray (NeuRay), for the novel view synthesis task. Recent works construct radiance fields from image features of input views to render novel view images, which enables the generalization to new scenes. However, due to occlusions, a 3D point may be…
Remotely actuated small-scale robots have shown promising capabilities in targeted delivery, micromanipulation, and biosensing. However, challenges remain in imaging and control of a robot in a large workspace, especially when conducting targeted navigation in hard-to-reach and tortuous regions of a
This paper addresses the challenge of reconstructing an animatable human model from a multi-view video. Some recent works have proposed to decompose a non-rigidly deforming scene into a canonical neural radiance field and a set of deformation fields that map observation-space points to the canonical…
We present a method that synthesizes novel views of complex scenes by interpolating a sparse set of nearby views. The core of our method is a network architecture that includes a multilayer perceptron and a ray transformer that estimates radiance and volume density at continuous 5D locations (3D spa…
Endovascular surgery has become a popular minimally invasive approach to diagnose and treat various vascular diseases. However, manipulating conventional passive guidewires and catheters still has technical challenges, such as long duration and undesired trauma. In addition, radiation exposure induc
This paper addresses the challenge of novel view synthesis for a human performer from a very sparse set of camera views. Some recent works have shown that learning implicit neural representations of 3D scenes achieves remarkable view synthesis quality given dense input views. However, the representa…
After years of development, various swarms of robots have been proposed for many complicated tasks, such as forming patterns, cooperative locomotion, and adapting to different environments. However, controlling microrobotic swarms is still a challenging task owing to the lacking of integrated device…
We present an end-to-end inverse rendering pipeline that includes a fully differentiable renderer, and can reconstruct geometry, materials, and illumination from scratch from a set of images. Our rendering framework represents specular BRDFs and environmental illumination using mixtures of spherical…
We propose ultrasound Doppler imaging and magnetic navigation of collective cell microrobots in whole blood. Cell microrobots are cultured using stem cells and iron microparticles, they have spheroidal structures and can be actuated under external magnetic fields. A collective of cell microrobots ca…
Predicting where people can walk in a scene is important for many tasks, including autonomous driving systems and human behavior analysis. Yet learning a computational model for this purpose is challenging due to semantic ambiguity and a lack of labeled data: current datasets only have labels on whe…
Recent research on learned visual descriptors has shown promising improvements in correspondence estimation, a key component of many 3D vision tasks. However, existing descriptor learning frameworks typically require ground-truth correspondences between feature points for training, which are challen…
Graph neural networks (GNNs) have made considerable achievements in processing graph-structured data. However, existing methods can not allocate learnable weights to different nodes in the neighborhood and lack of robustness on account of neglecting both node attributes and graph reconstruction. Mor…
We propose thrombolysis using a magnetic nanoparticle microswarm with tissue plasminogen activator (tPA) under ultrasound imaging. The microswarm is generated in blood using an oscillating magnetic field and can be navigated with locomotion along both the long and short axis. By modulating the input…
Microrobots capable of performing targeted delivery are promising for biomedical applications. Due to the restriction of their small size and volume, however, the real-time <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">in vivo</i> imaging strategy
Dynamic self-assembly is treated as a promising approach for generating a robotic swarm to perform coordinated tasks, and the assembled pattern can be tuned by regulating the energy input. However, location of a dynamically assembled pattern is hard to be determined, especially under global fields,…
Microrobots are considered as promising tools for biomedical applications. However, the imaging of them becomes challenges in order to be further applied on in vivo environments. Here we report the magnetic navigation of a paramagnetic nanoparticle-based swarm using ultrasound images. The swarm can…
This work proposes a multi-image matching method to estimate semantic correspondences across multiple images. In contrast to the previous methods that optimize all pairwise correspondences, the proposed method identifies and matches only a sparse set of reliable features in the image collection. In…
In this letter, we report a miniature swimming robot that consists of a nonmagnetic V-shaped head, an I-shaped tail attached with a magnet and a flexible link for interconnection of the rigid head and tail. The use of a flexible link enables the robot to exhibit two different vibration modes by tuni