Recent advancements in deep learning have greatly enhanced 3D object recognition, but most models are limited to closed-set scenarios, unable to handle unknown samples in real-world applications. Open-set recognition (OSR) addresses this limitation by enabling models to both classify known classes and identify novel classes. However, current OSR methods rely on global features to differentiate known and unknown classes, treating the entire object uniformly and overlooking the varying semantic importance of its different parts. To address this gap, we propose Salience-Aware Structured Separation (SASep), which includes (i) a tunable semantic decomposition (TSD) module to semantically decompose objects into important and unimportant parts, (ii) a geometric synthesis strategy (GSS) to generate pseudo-unknown objects by combining these unimportant parts, and (iii) a synth-aided margin separation (SMS) module to enhance feature-level separation by expanding the feature distributions between classes. Together, these components improve both geometric and feature representations, enhancing the model's ability to effectively distinguish known and unknown classes. Experimental results show that SASep achieves superior performance in 3D OSR, outperforming existing state-of-the-art methods.
Point cloud processing has gained significant attention due to its critical role in applications such as autonomous driving and 3D object recognition. However, deploying high-performance models like Point Transformer V3 in resource-constrained environments remains challenging due to their high computational and memory demands. This work introduces a novel distillation framework that leverages topology-aware representations and gradient-guided knowledge distillation to effectively transfer knowledge from a high-capacity teacher to a lightweight student model. Our approach captures the underlying geometric structures of point clouds while selectively guiding the student model's learning process through gradient-based feature alignment. Experimental results in the Nuscenes, SemanticKITTI, and Waymo datasets demonstrate that the proposed method achieves competitive performance, with an approximately 16x reduction in model size and a nearly 1.9x decrease in inference time compared to its teacher model. Notably, on NuScenes, our method achieves state-of-the-art performance among knowledge distillation techniques trained solely on LiDAR data, surpassing prior knowledge distillation baselines in segmentation performance. Our implementation is available publicly at: https://github.com/HySonLab/PointDistill
Semi-supervised learning (SSL) has shown its effectiveness in learning effective 3D representation from a small amount of labelled data while utilizing large unlabelled data. Traditional semi-supervised approaches rely on the fundamental concept of predicting pseudo-labels for unlabelled data and incorporating them into the learning process. However, we identify that the existing methods do not fully utilize all the unlabelled samples and consequently limit their potential performance. To address this issue, we propose AllMatch, a novel SSL-based 3D classification framework that effectively utilizes all the unlabelled samples. AllMatch comprises three modules: (1) an adaptive hard augmentation module that applies relatively hard augmentations to the high-confident unlabelled samples with lower loss values, thereby enhancing the contribution of such samples, (2) an inverse learning module that further improves the utilization of unlabelled data by learning what not to learn, and (3) a contrastive learning module that ensures learning from all the samples in both supervised and unsupervised settings. Comprehensive experiments on two popular 3D datasets demonstrate a performance improvement of up to 11.2% with 1% labelled data, surpassing the SOTA by a significant margin. Furthermore, AllMatch exhibits its efficiency in effectively leveraging all the unlabelled data, demonstrated by the fact that only 10% of labelled data reaches nearly the same performance as fully-supervised learning with all labelled data. The code of our work is available at: https://github.com/snehaputul/AllMatch.
This paper presents a novel universal perturbation method for generating robust multi-view adversarial examples in 3D object recognition. Unlike conventional attacks limited to single views, our approach operates on multiple 2D images, offering a practical and scalable solution for enhancing model scalability and robustness. This generalizable method bridges the gap between 2D perturbations and 3D-like attack capabilities, making it suitable for real-world applications. Existing adversarial attacks may become ineffective when images undergo transformations like changes in lighting, camera position, or natural deformations. We address this challenge by crafting a single universal noise perturbation applicable to various object views. Experiments on diverse rendered 3D objects demonstrate the effectiveness of our approach. The universal perturbation successfully identified a single adversarial noise for each given set of 3D object renders from multiple poses and viewpoints. Compared to single-view attacks, our universal attacks lower classification confidence across multiple viewing angles, especially at low noise levels. A sample implementation is made available at https://github.com/memoatwit/UniversalPerturbation.
Taking advantage of multi-view aggregation presents a promising solution to tackle challenges such as occlusion and missed detection in multi-object tracking and detection. Recent advancements in multi-view detection and 3D object recognition have significantly improved performance by strategically projecting all views onto the ground plane and conducting detection analysis from a Bird's Eye View. In this paper, we compare modern lifting methods, both parameter-free and parameterized, to multi-view aggregation. Additionally, we present an architecture that aggregates the features of multiple times steps to learn robust detection and combines appearance- and motion-based cues for tracking. Most current tracking approaches either focus on pedestrians or vehicles. In our work, we combine both branches and add new challenges to multi-view detection with cross-scene setups. Our method generalizes to three public datasets across two domains: (1) pedestrian: Wildtrack and MultiviewX, and (2) roadside perception: Synthehicle, achieving state-of-the-art performance in detection and tracking. https://github.com/tteepe/TrackTacular
In this work, we address the challenging task of 3D object recognition without the reliance on real-world 3D labeled data. Our goal is to predict the 3D shape, size, and 6D pose of objects within a single RGB-D image, operating at the category level and eliminating the need for CAD models during inference. While existing self-supervised methods have made strides in this field, they often suffer from inefficiencies arising from non-end-to-end processing, reliance on separate models for different object categories, and slow surface extraction during the training of implicit reconstruction models; thus hindering both the speed and real-world applicability of the 3D recognition process. Our proposed method leverages a multi-stage training pipeline, designed to efficiently transfer synthetic performance to the real-world domain. This approach is achieved through a combination of 2D and 3D supervised losses during the synthetic domain training, followed by the incorporation of 2D supervised and 3D self-supervised losses on real-world data in two additional learning stages. By adopting this comprehensive strategy, our method successfully overcomes the aforementioned limitations and outperforms existing self-supervised 6D pose and size estimation baselines on the NOCS test-set with a 16.4% absolute improvement in mAP for 6D pose estimation while running in near real-time at 5 Hz.
Robots operating in human-centered environments, such as retail stores, restaurants, and households, are often required to distinguish between similar objects in different contexts with a high degree of accuracy. However, fine-grained object recognition remains a challenge in robotics due to the high intra-category and low inter-category dissimilarities. In addition, the limited number of fine-grained 3D datasets poses a significant problem in addressing this issue effectively. In this paper, we propose a hybrid multi-modal Vision Transformer (ViT) and Convolutional Neural Networks (CNN) approach to improve the performance of fine-grained visual classification (FGVC). To address the shortage of FGVC 3D datasets, we generated two synthetic datasets. The first dataset consists of 20 categories related to restaurants with a total of 100 instances, while the second dataset contains 120 shoe instances. Our approach was evaluated on both datasets, and the results indicate that it outperforms both CNN-only and ViT-only baselines, achieving a recognition accuracy of 94.50 % and 93.51 % on the restaurant and shoe datasets, respectively. Additionally, we have made our FGVC RGB-D datasets available to the research community to enable further experimentation and advancement. Furthermore, we successfully integrated our proposed method with a robot framework and demonstrated its potential as a fine-grained perception tool in both simulated and real-world robotic scenarios.
Recently, vision architectures based exclusively on multi-layer perceptrons (MLPs) have gained much attention in the computer vision community. MLP-like models achieve competitive performance on a single 2D image classification with less inductive bias without hand-crafted convolution layers. In this work, we explore the effectiveness of MLP-based architecture for the view-based 3D object recognition task. We present an MLP-based architecture termed as Round-Roll MLP (R$^2$-MLP). It extends the spatial-shift MLP backbone by considering the communications between patches from different views. R$^2$-MLP rolls part of the channels along the view dimension and promotes information exchange between neighboring views. We benchmark MLP results on ModelNet10 and ModelNet40 datasets with ablations in various aspects. The experimental results show that, with a conceptually simple structure, our R$^2$-MLP achieves competitive performance compared with existing state-of-the-art methods.
Recognizing scenes and objects in 3D from a single image is a longstanding goal of computer vision with applications in robotics and AR/VR. For 2D recognition, large datasets and scalable solutions have led to unprecedented advances. In 3D, existing benchmarks are small in size and approaches specialize in few object categories and specific domains, e.g. urban driving scenes. Motivated by the success of 2D recognition, we revisit the task of 3D object detection by introducing a large benchmark, called Omni3D. Omni3D re-purposes and combines existing datasets resulting in 234k images annotated with more than 3 million instances and 98 categories. 3D detection at such scale is challenging due to variations in camera intrinsics and the rich diversity of scene and object types. We propose a model, called Cube R-CNN, designed to generalize across camera and scene types with a unified approach. We show that Cube R-CNN outperforms prior works on the larger Omni3D and existing benchmarks. Finally, we prove that Omni3D is a powerful dataset for 3D object recognition and show that it improves single-dataset performance and can accelerate learning on new smaller datasets via pre-training.
Data augmentation is an important technique to reduce overfitting and improve learning performance, but existing works on data augmentation for 3D point cloud data are based on heuristics. In this work, we instead propose to automatically learn a data augmentation strategy using bilevel optimization. An augmentor is designed in a similar fashion to a conditional generator and is optimized by minimizing a base model's loss on a validation set when the augmented input is used for training the model. This formulation provides a more principled way to learn data augmentation on 3D point clouds. We evaluate our approach on standard point cloud classification tasks and a more challenging setting with pose misalignment between training and validation/test sets. The proposed strategy achieves competitive performance on both tasks and we provide further insight into the augmentor's ability to learn the validation set distribution.
Inspired by the great success achieved by CNN in image recognition, view-based methods applied CNNs to model the projected views for 3D object understanding and achieved excellent performance. Nevertheless, multi-view CNN models cannot model the communications between patches from different views, limiting its effectiveness in 3D object recognition. Inspired by the recent success gained by vision Transformer in image recognition, we propose a Multi-view Vision Transformer (MVT) for 3D object recognition. Since each patch feature in a Transformer block has a global reception field, it naturally achieves communications between patches from different views. Meanwhile, it takes much less inductive bias compared with its CNN counterparts. Considering both effectiveness and efficiency, we develop a global-local structure for our MVT. Our experiments on two public benchmarks, ModelNet40 and ModelNet10, demonstrate the competitive performance of our MVT.
With the proposition of neural networks for point clouds, deep learning has started to shine in the field of 3D object recognition while researchers have shown an increased interest to investigate the reliability of point cloud networks by adversarial attacks. However, most of the existing studies aim to deceive humans or defense algorithms, while the few that address the operation principles of the models themselves remain flawed in terms of critical point selection. In this work, we propose two adversarial methods: One Point Attack (OPA) and Critical Traversal Attack (CTA), which incorporate the explainability technologies and aim to explore the intrinsic operating principle of point cloud networks and their sensitivity against critical points perturbations. Our results show that popular point cloud networks can be deceived with almost $100\%$ success rate by shifting only one point from the input instance. In addition, we show the interesting impact of different point attribution distributions on the adversarial robustness of point cloud networks. Finally, we discuss how our approaches facilitate the explainability study for point cloud networks. To the best of our knowledge, this is the first point-cloud-based adversarial approach concerning explainability. Our code is available at https://github.com/Explain3D/Exp-One-Point-Atk-PC.
Humans learn to recognize and manipulate new objects in lifelong settings without forgetting the previously gained knowledge under non-stationary and sequential conditions. In autonomous systems, the agents also need to mitigate similar behavior to continually learn the new object categories and adapt to new environments. In most conventional deep neural networks, this is not possible due to the problem of catastrophic forgetting, where the newly gained knowledge overwrites existing representations. Furthermore, most state-of-the-art models excel either in recognizing the objects or in grasp prediction, while both tasks use visual input. The combined architecture to tackle both tasks is very limited. In this paper, we proposed a hybrid model architecture consists of a dynamically growing dual-memory recurrent neural network (GDM) and an autoencoder to tackle object recognition and grasping simultaneously. The autoencoder network is responsible to extract a compact representation for a given object, which serves as input for the GDM learning, and is responsible to predict pixel-wise antipodal grasp configurations. The GDM part is designed to recognize the object in both instances and categories levels. We address the problem of catastrophic forgetting using the intrinsic memory replay, where the episodic memory periodically replays the neural activation trajectories in the absence of external sensory information. To extensively evaluate the proposed model in a lifelong setting, we generate a synthetic dataset due to lack of sequential 3D objects dataset. Experiment results demonstrated that the proposed model can learn both object representation and grasping simultaneously in continual learning scenarios.
Most attempts to represent 3D shapes for deep learning have focused on volumetric grids, multi-view images and point clouds. In this paper we look at the most popular representation of 3D shapes in computer graphics - a triangular mesh - and ask how it can be utilized within deep learning. The few attempts to answer this question propose to adapt convolutions & pooling to suit Convolutional Neural Networks (CNNs). This paper proposes a very different approach, termed MeshWalker, to learn the shape directly from a given mesh. The key idea is to represent the mesh by random walks along the surface, which "explore" the mesh's geometry and topology. Each walk is organized as a list of vertices, which in some manner imposes regularity on the mesh. The walk is fed into a Recurrent Neural Network (RNN) that "remembers" the history of the walk. We show that our approach achieves state-of-the-art results for two fundamental shape analysis tasks: shape classification and semantic segmentation. Furthermore, even a very small number of examples suffices for learning. This is highly important, since large datasets of meshes are difficult to acquire.
Three dimensional (3D) object recognition is becoming a key desired capability for many computer vision systems such as autonomous vehicles, service robots and surveillance drones to operate more effectively in unstructured environments. These real-time systems require effective classification methods that are robust to various sampling resolutions, noisy measurements, and unconstrained pose configurations. Previous research has shown that points' sparsity, rotation and positional inherent variance can lead to a significant drop in the performance of point cloud based classification techniques. However, neither of them is sufficiently robust to multifactorial variance and significant sparsity. In this regard, we propose a novel approach for 3D classification that can simultaneously achieve invariance towards rotation, positional shift, scaling, and is robust to point sparsity. To this end, we introduce a new feature that utilizes graph structure of point clouds, which can be learned end-to-end with our proposed neural network to acquire a robust latent representation of the 3D object. We show that such latent representations can significantly improve the performance of object classification and retrieval tasks when points are sparse. Further, we show that our approach outperforms PointNet and 3DmFV by 35.0% and 28.1% respectively in ModelNet 40 classification tasks using sparse point clouds of only 16 points under arbitrary SO(3) rotation.
BlenderProc is a modular procedural pipeline, which helps in generating real looking images for the training of convolutional neural networks. These can be used in a variety of use cases including segmentation, depth, normal and pose estimation and many others. A key feature of our extension of blender is the simple to use modular pipeline, which was designed to be easily extendable. By offering standard modules, which cover a variety of scenarios, we provide a starting point on which new modules can be created.
Monocular depth estimation enables 3D perception from a single 2D image, thus attracting much research attention for years. Almost all methods treat foreground and background regions ("things and stuff") in an image equally. However, not all pixels are equal. Depth of foreground objects plays a crucial role in 3D object recognition and localization. To date how to boost the depth prediction accuracy of foreground objects is rarely discussed. In this paper, we first analyse the data distributions and interaction of foreground and background, then propose the foreground-background separated monocular depth estimation (ForeSeE) method, to estimate the foreground depth and background depth using separate optimization objectives and depth decoders. Our method significantly improves the depth estimation performance on foreground objects. Applying ForeSeE to 3D object detection, we achieve 7.5 AP gains and set new state-of-the-art results among other monocular methods. Code will be available at: https://github.com/WXinlong/ForeSeE.
In this paper we propose a neural message passing approach to augment an input 3D indoor scene with new objects matching their surroundings. Given an input, potentially incomplete, 3D scene and a query location, our method predicts a probability distribution over object types that fit well in that location. Our distribution is predicted though passing learned messages in a dense graph whose nodes represent objects in the input scene and edges represent spatial and structural relationships. By weighting messages through an attention mechanism, our method learns to focus on the most relevant surrounding scene context to predict new scene objects. We found that our method significantly outperforms state-of-the-art approaches in terms of correctly predicting objects missing in a scene based on our experiments in the SUNCG dataset. We also demonstrate other applications of our method, including context-based 3D object recognition and iterative scene generation.
View based strategies for 3D object recognition have proven to be very successful. The state-of-the-art methods now achieve over 90% correct category level recognition performance on appearance images. We improve upon these methods by introducing a view clustering and pooling layer based on dominant sets. The key idea is to pool information from views which are similar and thus belong to the same cluster. The pooled feature vectors are then fed as inputs to the same layer, in a recurrent fashion. This recurrent clustering and pooling module, when inserted in an off-the-shelf pretrained CNN, boosts performance for multi-view 3D object recognition, achieving a new state of the art test set recognition accuracy of 93.8% on the ModelNet 40 database. We also explore a fast approximate learning strategy for our cluster-pooling CNN, which, while sacrificing end-to-end learning, greatly improves its training efficiency with only a slight reduction of recognition accuracy to 93.3%. Our implementation is available at https://github.com/fate3439/dscnn.
In this study, we present an analysis of model-based ensemble learning for 3D point-cloud object classification and detection. An ensemble of multiple model instances is known to outperform a single model instance, but there is little study of the topic of ensemble learning for 3D point clouds. First, an ensemble of multiple model instances trained on the same part of the $\textit{ModelNet40}$ dataset was tested for seven deep learning, point cloud-based classification algorithms: $\textit{PointNet}$, $\textit{PointNet++}$, $\textit{SO-Net}$, $\textit{KCNet}$, $\textit{DeepSets}$, $\textit{DGCNN}$, and $\textit{PointCNN}$. Second, the ensemble of different architectures was tested. Results of our experiments show that the tested ensemble learning methods improve over state-of-the-art on the $\textit{ModelNet40}$ dataset, from $92.65\%$ to $93.64\%$ for the ensemble of single architecture instances, $94.03\%$ for two different architectures, and $94.15\%$ for five different architectures. We show that the ensemble of two models with different architectures can be as effective as the ensemble of 10 models with the same architecture. Third, a study on classic bagging i.e. with different subsets used for training multiple model instances) was tested and sources of ensemble accuracy growth were investigated for best-performing architecture, i.e. $\textit{SO-Net}$. We also investigate the ensemble learning of $\textit{Frustum PointNet}$ approach in the task of 3D object detection, increasing the average precision of 3D box detection on the $\textit{KITTI}$ dataset from $63.1\%$ to $66.5\%$ using only three model instances. We measure the inference time of all 3D classification architectures on a $\textit{Nvidia Jetson TX2}$, a common embedded computer for mobile robots, to allude to the use of these models in real-life applications.