3D assets have rapidly expanded in quantity and diversity due to the growing popularity of virtual reality and gaming. As a result, text-to-shape retrieval has become essential in facilitating intuitive search within large repositories. However, existing methods require canonical poses and support few object categories, limiting their real-world applicability where objects can belong to diverse classes and appear in random orientations. To address this challenge, we propose RI-Mamba, the first rotation-invariant state-space model for point clouds. RI-Mamba defines global and local reference frames to disentangle pose from geometry and uses Hilbert sorting to construct token sequences with meaningful geometric structure while maintaining rotation invariance. We further introduce a novel strategy to compute orientational embeddings and reintegrate them via feature-wise linear modulation, effectively recovering spatial context and enhancing model expressiveness. Our strategy is inherently compatible with state-space models and operates in linear time. To scale up retrieval, we adopt cross-modal contrastive learning with automated triplet generation, allowing training on diverse datasets without manual annotation. Extensive experiments demonstrate RI-Mamba's superior representational capacity and robustness, achieving state-of-the-art performance on the OmniObject3D benchmark across more than 200 object categories under arbitrary orientations. Our code will be made available at https://github.com/ndkhanh360/RI-Mamba.git.
MambaHash: Visual State Space Deep Hashing Model for Large-Scale Image Retrieval
School of Computer Science, Inner Mongolia University, Provincial Key Laboratory of Mongolian Information Processing Technology, National and Local Joint Engineering Research Center of Mongolian Information Processing（内蒙古大学计算机学院、蒙古信息处理技术省级重点实验室、蒙古信息处理国家与地方联合工程研究中心）
MamFusion: Multi-Mamba with Temporal Fusion for Partially Relevant Video Retrieval
Hangzhou City University（杭州城市大学）；University of Wisconsin–Madison（威斯康星大学麦迪逊分校）；Hangzhou Normal University（杭州师范大学）；Zhejiang Provincial Engineering Research Center for Real-Time SmartTech in Urban Security Governance（浙江省实时智能安防技术工程研究中心）
GeoMamba: A Geometry-driven MambaVision Framework and Dataset for Fine-grained Optical-SAR Object Retrieval
School of Artificial Intelligence, Wuhan University（武汉大学人工智能学院）；School of Artificial Intelligence and Information Engineering, Zhejiang University of Science & Technology（浙江科技大学人工智能与信息工程学院）；Hangzhou Institute of Technology, Xidian University（西安电子科技大学杭州研究院）；State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University（武汉大学测绘遥感信息工程国家重点实验室）
Renmin University of China（中国人民大学）；Nanjing University of Science and Technology（南京理工大学）；Tsinghua University（清华大学）
Point cloud-based large scale place recognition is an important but challenging task for many applications such as Simultaneous Localization and Mapping (SLAM). Taking the task as a point cloud retrieval problem, previous methods have made delightful achievements. However, how to deal with catastrophic collapse caused by rotation problems is still under-explored. In this paper, to tackle the issue, we propose a novel Point Cloud-based Rotation-aware Large Scale Place Recognition Network (RPR-Net). In particular, to solve the problem, we propose to learn rotation-invariant features in three ste…
The University of Hong Kong（香港大学）；Brown University（布朗大学）；Microsoft Research Asia（微软亚洲研究院）；Centre for Garment Production Limited, Hong Kong（香港成衣生产中心有限公司）；SUSTech（南方科技大学）；Texas A&M University（德克萨斯农工大学）
Scalable 6D pose estimation for rigid objects from RGB images aims at handling multiple objects and generalizing to novel objects. Building on a well-known auto-encoding framework to cope with object symmetry and the lack of labeled training data, we achieve scalability by disentangling the latent representation of auto-encoder into shape and pose sub-spaces. The latent shape space models the similarity of different objects through contrastive metric learning, and the latent pose code is compared with canonical rotations for rotation retrieval. Because different object symmetries induce incons…
School of Computer Science, University of Sydney（悉尼大学计算机科学学院）
Recent investigations on rotation invariance for 3D point clouds have been devoted to devising rotation-invariant feature descriptors or learning canonical spaces where objects are semantically aligned. Examinations of learning frameworks for invariance have seldom been looked into. In this work, we review rotation invariance in terms of point cloud registration and propose an effective framework for rotation invariance learning via three sequential stages, namely rotation-invariant shape encoding, aligned feature integration, and deep feature registration. We first encode shape descriptors co…
Chinese University of Hong Kong（香港中文大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Tel Aviv University（特拉维夫大学）
Recently, many deep neural networks were designed to process 3D point clouds, but a common drawback is that rotation invariance is not ensured, leading to poor generalization to arbitrary orientations. In this paper, we introduce a new low-level purely rotation-invariant representation to replace common 3D Cartesian coordinates as the network inputs. Also, we present a network architecture to embed these representations into features, encoding local relations between points and their neighbors, and the global shape structure. To alleviate inevitable global information loss caused by the rotati…
Litemaze；VinAI Research（VinAI 研究院）；VinUniversity（Vin 大学）；Hong Kong University of Science and Technology（香港科技大学）
Recent advances in deep learning for 3D point clouds have shown great promises in scene understanding tasks thanks to the introduction of convolution operators to consume 3D point clouds directly in a neural network. Point cloud data, however, could have arbitrary rotations, especially those acquired from 3D scanning. Recent works show that it is possible to design point cloud convolutions with rotation invariance property, but such methods generally do not perform as well as translation-invariant only convolution. We found that a key reason is that compared to point coordinates, rotation-inva…
Ningbo Research Institute, Zhejiang University（浙江大学宁波研究院）；College of Information Science and Electronic Engineering, Zhejiang University（浙江大学信息与电子工程学院）；NingboTech University（浙大宁波理工学院）；VinAI；Hong Kong University of Science and Technology（香港科技大学）
3D point clouds deep learning is a promising field of research that allows a neural network to learn features of point clouds directly, making it a robust tool for solving 3D scene understanding tasks. While recent works show that point cloud convolutions can be invariant to translation and point permutation, investigations of the rotation invariance property for point cloud convolution has been so far scarce. Some existing methods perform point cloud convolutions with rotation-invariant features, existing methods generally do not perform as well as translation-invariant only counterpart. In t…
Beihang University（北京航空航天大学）；Shanghai Aerospace Control Technology Institute（上海航天控制技术研究所）；Peking Union Medical College Hospital（北京协和医院）；Chinese Academy of Medical Sciences and Peking Union Medical College（中国医学科学院北京协和医学院）
The computer-aided diagnosis (CAD) system can provide a reference basis for the clinical diagnosis of skin diseases. Convolutional neural networks (CNNs) can not only extract visual elements such as colors and shapes but also semantic features. As such they have made great improvements in many tasks of dermoscopy images. The imaging of dermoscopy has no principal orientation, indicating that there are a large number of skin lesion rotations in the datasets. However, CNNs lack rotation invariance, which is bound to affect the robustness of CNNs against rotations. To tackle this issue, we propos…
Remote sensing image retrieval (RSIR) is the process of ranking database images depending on the degree of similarity compared to the query image. As the complexity of RSIR increases due to the diversity in shooting range, angle, and location of remote sensors, there is an increasing demand for methods to address these issues and improve retrieval performance. In this work, we introduce a novel method for retrieving aerial images by merging group convolution with attention mechanism and metric learning, resulting in robustness to rotational variations. For refinement and emphasis on important …
RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing
College of Computer Science and Technology, National University of Defense Technology, China（国防科技大学计算机科学与技术学院）；Tsinghua University, China（清华大学）；Beijing University of Posts and Telecommunications, China（北京邮电大学）；School of Computer Science, Wuhan University, China（武汉大学计算机学院）；Zhongguancun Academy, China（中关村学院）
Indian Institute of Technology Madras（印度理工学院马德拉斯分校）
Proliferation of touch-based devices has made sketch-based image retrieval practical. While many methods exist for sketch-based object detection/image retrieval on small datasets, relatively less work has been done on large (web)-scale image retrieval. In this paper, we present an efficient approach for image retrieval from millions of images based on user-drawn sketches. Unlike existing methods for this problem which are sensitive to even translation or scale variations, our method handles rotation, translation, scale (i.e. a similarity transformation) and small deformations. The object bound…
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Victoria University of Wellington（惠灵顿维多利亚大学）；Cardiff University（卡迪夫大学）
Fine-grained 3D shape retrieval aims to retrieve 3D shapes similar to a query shape in a repository with models belonging to the same class, which requires shape descriptors to be capable of representing detailed geometric information to discriminate shapes with globally similar structures. Moreover, 3D objects can be placed with arbitrary position and orientation in real-world applications, which further requires shape descriptors to be robust to rigid transformations. The shape descriptions used in existing 3D shape retrieval systems fail to meet the above two criteria. In this paper, we int…
Introduction of Convolutional Neural Networks has improved results on almost every image-based problem and Content-Based Image Retrieval is not an exception. But the CNN features, being rotation invariant, creates problems to build a rotation-invariant CBIR system. Though rotation-invariant features can be hand-engineered, the retrieval accuracy is very low because by hand engineering only low-level features can be created, unlike deep learning models that create high-level features along with low-level features. This paper shows a novel method to build a rotational invariant CBIR system by in…
In recent years, with the explosion of digital images on the Web, content-based retrieval has emerged as a significant research area. Shapes, textures, edges and segments may play a key role in describing the content of an image. Radon and Gabor transforms are both powerful techniques that have been widely studied to extract shape-texture-based information. The combined Radon-Gabor features may be more robust against scale/rotation variations, presence of noise, and illumination changes. The objective of this paper is to harness the potentials of both Gabor and Radon transforms in order to int…
Rotation invariance has been studied in the computer vision community primarily in the context of small in-plane rotations. This is usually achieved by building invariant image features. However, the problem of achieving invariance for large rotation angles remains largely unexplored. In this work, we tackle this problem by directly compensating for large rotations, as opposed to building invariant features. This is inspired by the neuro-scientific concept of mental rotation, which humans use to compare pairs of rotated objects. Our contributions here are three-fold. First, we train a Convolut…
Tshwane University of Technology（茨瓦尼科技大学）；Durban University of Technology（德班科技大学）
Research is taking place to find effective algorithms for content-based image representation and description. There is a substantial amount of algorithms available that use visual features (color, shape, texture). Shape feature has attracted much attention from researchers that there are many shape representation and description algorithms in literature. These shape image representation and description algorithms are usually not application independent or robust, making them undesirable for generic shape description. This paper presents an object shape representation using Kernel Density Featu…
Shape is one of the main features in content based image retrieval (CBIR). This paper proposes a new shape signature. In this technique, features of each shape are extracted based on four sides of the rectangle that covers the shape. The proposed technique is Fourier based and it is invariant to translation, scaling and rotation. The retrieval performance between some commonly used Fourier based signatures and the proposed four sides distance (FSD) signature has been tested using MPEG-7 database. Experimental results are shown that the FSD signature has better performance compared with those s…
Sun Yat-sen University（中山大学）；Pixtalks Tech（Pixtalks科技）
In this paper, we propose a simple yet effective method to endow deep 3D models with rotation invariance by expressing the coordinates in an intrinsic frame determined by the object shape itself. Key to our approach is to find such an intrinsic frame which should be unique to the identical object shape and consistent across different instances of the same category, e.g. the frame axes of desks should be all roughly along the edges. Interestingly, the principal component analysis exactly provides an effective way to define such a frame, i.e. setting the principal components as the frame axes. A…
Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image Retrieval
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Beijing Institute of Technology（北京理工大学）；University of Adelaide（阿德莱德大学）
Mitsubishi Electric Research Laboratories（三菱电机研究实验室）；Massachusetts Institute of Technology（麻省理工学院）
Omnidirectional images and spherical representations of $3D$ shapes cannot be processed with conventional 2D convolutional neural networks (CNNs) as the unwrapping leads to large distortion. Using fast implementations of spherical and $SO(3)$ convolutions, researchers have recently developed deep learning methods better suited for classifying spherical images. These newly proposed convolutional layers naturally extend the notion of convolution to functions on the unit sphere $S^2$ and the group of rotations $SO(3)$ and these layers are equivariant to 3D rotations. In this paper, we consider th…
Most image instance retrieval pipelines are based on comparison of vectors known as global image descriptors between a query image and the database images. Due to their success in large scale image classification, representations extracted from Convolutional Neural Networks (CNN) are quickly gaining ground on Fisher Vectors (FVs) as state-of-the-art global descriptors for image instance retrieval. While CNN-based descriptors are generally remarked for good retrieval performance at lower bitrates, they nevertheless present a number of drawbacks including the lack of robustness to common object …
Technische Universität München（慕尼黑工业大学）；Mercateo AG（Mercateo股份公司）
In this paper, we investigate the problem of retrieving images from a database based on a multi-modal (image-text) query. Specifically, the query text prompts some modification in the query image and the task is to retrieve images with the desired modifications. For instance, a user of an E-Commerce platform is interested in buying a dress, which should look similar to her friend's dress, but the dress should be of white color with a ribbon sash. In this case, we would like the algorithm to retrieve some dresses with desired modifications in the query dress. We propose an autoencoder based mod…
The detection of objects that are multi-oriented is a difficult pattern recognition problem. In this paper, we propose to evaluate the performance of different families of descriptors for the classification of galaxy morphologies. We investigate the performance of the Hu moments, Flusser moments, Zernike moments, Fourier-Mellin moments, and ring projection techniques based on 1D moment and the Fourier transform. We consider two main datasets for the performance evaluation. The first dataset is an artificial dataset based on representative templates from 11 types of galaxies, which are evaluate…
University of Science and Technology of China（中国科学技术大学）；University of Technology Sydney（悉尼科技大学）
Convolutional Neural Networks (CNNs) have demonstrated state-of-the-art performance on many visual recognition tasks. However, the combination of convolution and pooling operations only shows invariance to small local location changes in meaningful objects in input. Sometimes, such networks are trained using data augmentation to encode this invariance into the parameters, which restricts the capacity of the model to learn the content of these objects. A more efficient use of the parameter budget is to encode rotation or translation invariance into the model architecture, which relieves the mod…
