Shape and texture recognition is fundamental to visual perception. The ability to identify shapes regardless of orientation, texture, or context, and to recognize textures independently of their associated objects, is essential for general visual understanding of the world. We introduce the Large Shape & Textures dataset (LAS&T), a giant collection of diverse shapes and textures automatically extracted from real-world images. This dataset is used to evaluate how effectively leading Large Vision-Language Models (LVLMs) understand shapes, textures, and materials in both 2D and 3D scenes. For shape recognition, we test models' ability to match identical shapes that differ in orientation, texture, color, or environment. Our results show that LVLMs' shape identification capabilities remain significantly below human performance. Single alterations (orientation, texture) cause minor decreases in matching accuracy, while multiple changes precipitate dramatic drops. LVLMs appear to rely predominantly on high-level and semantic features and struggle with abstract shapes lacking clear class associations. For texture and material recognition, we evaluate models' ability to identify identical textures and materials across different objects and environments. Interestingly, leading LVLMs approach human-level performance in recognizing materials in 3D scenes, yet substantially underperform humans when identifying simpler 2D textures. The LAS&T dataset and benchmark, the largest and most diverse resource for shape and texture evaluation, is freely available with generation and testing scripts.
The inverse scattering problem is of critical importance in a number of fields, including medical imaging, sonar, sensing, non-destructive evaluation, and several others. The problem of interest can vary from detecting the shape to the constitutive properties of the obstacle. The challenge in both is that this problem is ill-posed, more so when there is limited information. That said, significant effort has been expended over the years in developing solutions to this problem. Here, we use a different approach, one that is founded on data. Specifically, we develop a deep learning framework for shape reconstruction using limited information with single incident wave, single frequency, and phase-less far-field data. This is done by (a) using a compact probabilistic shape latent space, learned by a 3D variational auto-encoder, and (b) a convolutional neural network trained to map the acoustic scattering information to this shape representation. The proposed framework is evaluated on a synthetic 3D particle dataset, as well as ShapeNet, a popular 3D shape recognition dataset. As demonstrated via a number of results, the proposed method is able to produce accurate reconstructions for large batches of complex scatterer shapes (such as airplanes and automobiles), despite the significant variation present within the data.
Large vision-language models have impressively promote the performance of 2D visual recognition under zero/few-shot scenarios. In this paper, we focus on exploiting the large vision-language model, i.e., CLIP, to address zero/few-shot 3D shape recognition based on multi-view representations. The key challenge for both tasks is to generate a discriminative descriptor of the 3D shape represented by multiple view images under the scenarios of either without explicit training (zero-shot 3D shape recognition) or training with a limited number of data (few-shot 3D shape recognition). We analyze that both tasks are relevant and can be considered simultaneously. Specifically, leveraging the descriptor which is effective for zero-shot inference to guide the tuning of the aggregated descriptor under the few-shot training can significantly improve the few-shot learning efficacy. Hence, we propose Prompt-Enhanced View Aggregation Network (PEVA-Net) to simultaneously address zero/few-shot 3D shape recognition. Under the zero-shot scenario, we propose to leverage the prompts built up from candidate categories to enhance the aggregation process of multiple view-associated visual features. The resulting aggregated feature serves for effective zero-shot recognition of the 3D shapes. Under the few-shot scenario, we first exploit a transformer encoder to aggregate the view-associated visual features into a global descriptor. To tune the encoder, together with the main classification loss, we propose a self-distillation scheme via a feature distillation loss by treating the zero-shot descriptor as the guidance signal for the few-shot descriptor. This scheme can significantly enhance the few-shot learning efficacy.
In recent years, the results of view-based 3D shape recognition methods have saturated, and models with excellent performance cannot be deployed on memory-limited devices due to their huge size of parameters. To address this problem, we introduce a compression method based on knowledge distillation for this field, which largely reduces the number of parameters while preserving model performance as much as possible. Specifically, to enhance the capabilities of smaller models, we design a high-performing large model called Group Multi-view Vision Transformer (GMViT). In GMViT, the view-level ViT first establishes relationships between view-level features. Additionally, to capture deeper features, we employ the grouping module to enhance view-level features into group-level features. Finally, the group-level ViT aggregates group-level features into complete, well-formed 3D shape descriptors. Notably, in both ViTs, we introduce spatial encoding of camera coordinates as innovative position embeddings. Furthermore, we propose two compressed versions based on GMViT, namely GMViT-simple and GMViT-mini. To enhance the training effectiveness of the small models, we introduce a knowledge distillation method throughout the GMViT process, where the key outputs of each GMViT component serve as distillation targets. Extensive experiments demonstrate the efficacy of the proposed method. The large model GMViT achieves excellent 3D classification and retrieval results on the benchmark datasets ModelNet, ShapeNetCore55, and MCB. The smaller models, GMViT-simple and GMViT-mini, reduce the parameter size by 8 and 17.6 times, respectively, and improve shape recognition speed by 1.5 times on average, while preserving at least 90% of the classification and retrieval performance. The code is available at https://github.com/bigdata-graph/GMViT.
Large-scale pre-trained models have demonstrated impressive performance in vision and language tasks within open-world scenarios. Due to the lack of comparable pre-trained models for 3D shapes, recent methods utilize language-image pre-training to realize zero-shot 3D shape recognition. However, due to the modality gap, pretrained language-image models are not confident enough in the generalization to 3D shape recognition. Consequently, this paper aims to improve the confidence with view selection and hierarchical prompts. Leveraging the CLIP model as an example, we employ view selection on the vision side by identifying views with high prediction confidence from multiple rendered views of a 3D shape. On the textual side, the strategy of hierarchical prompts is proposed for the first time. The first layer prompts several classification candidates with traditional class-level descriptions, while the second layer refines the prediction based on function-level descriptions or further distinctions between the candidates. Remarkably, without the need for additional training, our proposed method achieves impressive zero-shot 3D classification accuracies of 84.44%, 91.51%, and 66.17% on ModelNet40, ModelNet10, and ShapeNet Core55, respectively. Furthermore, we will make the code publicly available to facilitate reproducibility and further research in this area.
This paper presents ViewFormer, a simple yet effective model for multi-view 3d shape recognition and retrieval. We systematically investigate the existing methods for aggregating multi-view information and propose a novel ``view set" perspective, which minimizes the relation assumption about the views and releases the representation flexibility. We devise an adaptive attention model to capture pairwise and higher-order correlations of the elements in the view set. The learned multi-view correlations are aggregated into an expressive view set descriptor for recognition and retrieval. Experiments show the proposed method unleashes surprising capabilities across different tasks and datasets. For instance, with only 2 attention blocks and 4.8M learnable parameters, ViewFormer reaches 98.8% recognition accuracy on ModelNet40 for the first time, exceeding previous best method by 1.1% . On the challenging RGBD dataset, our method achieves 98.4% recognition accuracy, which is a 4.1% absolute improvement over the strongest baseline. ViewFormer also sets new records in several evaluation dimensions of 3D shape retrieval defined on the SHREC'17 benchmark.
Multi-view projection techniques have shown themselves to be highly effective in achieving top-performing results in the recognition of 3D shapes. These methods involve learning how to combine information from multiple view-points. However, the camera view-points from which these views are obtained are often fixed for all shapes. To overcome the static nature of current multi-view techniques, we propose learning these view-points. Specifically, we introduce the Multi-View Transformation Network (MVTN), which uses differentiable rendering to determine optimal view-points for 3D shape recognition. As a result, MVTN can be trained end-to-end with any multi-view network for 3D shape classification. We integrate MVTN into a novel adaptive multi-view pipeline that is capable of rendering both 3D meshes and point clouds. Our approach demonstrates state-of-the-art performance in 3D classification and shape retrieval on several benchmarks (ModelNet40, ScanObjectNN, ShapeNet Core55). Further analysis indicates that our approach exhibits improved robustness to occlusion compared to other methods. We also investigate additional aspects of MVTN, such as 2D pretraining and its use for segmentation. To support further research in this area, we have released MVTorch, a PyTorch library for 3D understanding and generation using multi-view projections.
As two fundamental representation modalities of 3D objects, 3D point clouds and multi-view 2D images record shape information from different domains of geometric structures and visual appearances. In the current deep learning era, remarkable progress in processing such two data modalities has been achieved through respectively customizing compatible 3D and 2D network architectures. However, unlike multi-view image-based 2D visual modeling paradigms, which have shown leading performance in several common 3D shape recognition benchmarks, point cloud-based 3D geometric modeling paradigms are still highly limited by insufficient learning capacity, due to the difficulty of extracting discriminative features from irregular geometric signals. In this paper, we explore the possibility of boosting deep 3D point cloud encoders by transferring visual knowledge extracted from deep 2D image encoders under a standard teacher-student distillation workflow. Generally, we propose PointMCD, a unified multi-view cross-modal distillation architecture, including a pretrained deep image encoder as the teacher and a deep point encoder as the student. To perform heterogeneous feature alignment between 2D visual and 3D geometric domains, we further investigate visibility-aware feature projection (VAFP), by which point-wise embeddings are reasonably aggregated into view-specific geometric descriptors. By pair-wisely aligning multi-view visual and geometric descriptors, we can obtain more powerful deep point encoders without exhausting and complicated network modification. Experiments on 3D shape classification, part segmentation, and unsupervised learning strongly validate the effectiveness of our method. The code and data will be publicly available at https://github.com/keeganhk/PointMCD.
While the Transformer architecture has become ubiquitous in the machine learning field, its adaptation to 3D shape recognition is non-trivial. Due to its quadratic computational complexity, the self-attention operator quickly becomes inefficient as the set of input points grows larger. Furthermore, we find that the attention mechanism struggles to find useful connections between individual points on a global scale. In order to alleviate these problems, we propose a two-stage Point Transformer-in-Transformer (Point-TnT) approach which combines local and global attention mechanisms, enabling both individual points and patches of points to attend to each other effectively. Experiments on shape classification show that such an approach provides more useful features for downstream tasks than the baseline Transformer, while also being more computationally efficient. In addition, we also extend our method to feature matching for scene reconstruction, showing that it can be used in conjunction with existing scene reconstruction pipelines.
The fields of SocialVR, performance capture, and virtual try-on are often faced with a need to faithfully reproduce real garments in the virtual world. One critical task is the disentanglement of the intrinsic garment shape from deformations due to fabric properties, physical forces, and contact with the body. We propose to use a garment sewing pattern, a realistic and compact garment descriptor, to facilitate the intrinsic garment shape estimation. Another major challenge is a high diversity of shapes and designs in the domain. The most common approach for Deep Learning on 3D garments is to build specialized models for individual garments or garment types. We argue that building a unified model for various garment designs has the benefit of generalization to novel garment types, hence covering a larger design domain than individual models would. We introduce NeuralTailor, a novel architecture based on point-level attention for set regression with variable cardinality, and apply it to the task of reconstructing 2D garment sewing patterns from the 3D point could garment models. Our experiments show that NeuralTailor successfully reconstructs sewing patterns and generalizes to garment types with pattern topologies unseen during training.
3D shape representation and its processing have substantial effects on 3D shape recognition. The polygon mesh as a 3D shape representation has many advantages in computer graphics and geometry processing. However, there are still some challenges for the existing deep neural network (DNN)-based methods on polygon mesh representation, such as handling the variations in the degree and permutations of the vertices and their pairwise distances. To overcome these challenges, we propose a DNN-based method (PolyNet) and a specific polygon mesh representation (PolyShape) with a multi-resolution structure. PolyNet contains two operations; (1) a polynomial convolution (PolyConv) operation with learnable coefficients, which learns continuous distributions as the convolutional filters to share the weights across different vertices, and (2) a polygonal pooling (PolyPool) procedure by utilizing the multi-resolution structure of PolyShape to aggregate the features in a much lower dimension. Our experiments demonstrate the strength and the advantages of PolyNet on both 3D shape classification and retrieval tasks compared to existing polygon mesh-based methods and its superiority in classifying graph representations of images. The code is publicly available from https://myavartanoo.github.io/polynet/.
Recently, 3D shape understanding has achieved significant progress due to the advances of deep learning models on various data formats like images, voxels, and point clouds. Among them, point clouds and multi-view images are two complementary modalities of 3D objects and learning representations by fusing both of them has been proven to be fairly effective. While prior works typically focus on exploiting global features of the two modalities, herein we argue that more discriminative features can be derived by modeling ``where to fuse''. To investigate this, we propose a novel Locality-Aware Point-View Fusion Transformer (LATFormer) for 3D shape retrieval and classification. The core component of LATFormer is a module named Locality-Aware Fusion (LAF) which integrates the local features of correlated regions across the two modalities based on the co-occurrence scores. We further propose to filter out scores with low values to obtain salient local co-occurring regions, which reduces redundancy for the fusion process. In our LATFormer, we utilize the LAF module to fuse the multi-scale features of the two modalities both bidirectionally and hierarchically to obtain more informative features. Comprehensive experiments on four popular 3D shape benchmarks covering 3D object retrieval and classification validate its effectiveness.
In this paper, we focus on recognizing 3D shapes from arbitrary views, i.e., arbitrary numbers and positions of viewpoints. It is a challenging and realistic setting for view-based 3D shape recognition. We propose a canonical view representation to tackle this challenge. We first transform the original features of arbitrary views to a fixed number of view features, dubbed canonical view representation, by aligning the arbitrary view features to a set of learnable reference view features using optimal transport. In this way, each 3D shape with arbitrary views is represented by a fixed number of canonical view features, which are further aggregated to generate a rich and robust 3D shape representation for shape recognition. We also propose a canonical view feature separation constraint to enforce that the view features in canonical view representation can be embedded into scattered points in a Euclidean space. Experiments on the ModelNet40, ScanObjectNN, and RGBD datasets show that our method achieves competitive results under the fixed viewpoint settings, and significantly outperforms the applicable methods under the arbitrary view setting.
In 3D shape recognition, multi-view based methods leverage human's perspective to analyze 3D shapes and have achieved significant outcomes. Most existing research works in deep learning adopt handcrafted networks as backbones due to their high capacity of feature extraction, and also benefit from ImageNet pretraining. However, whether these network architectures are suitable for 3D analysis or not remains unclear. In this paper, we propose a neural architecture search method named Auto-MVCNN which is particularly designed for optimizing architecture in multi-view 3D shape recognition. Auto-MVCNN extends gradient-based frameworks to process multi-view images, by automatically searching the fusion cell to explore intrinsic correlation among view features. Moreover, we develop an end-to-end scheme to enhance retrieval performance through the trade-off parameter search. Extensive experimental results show that the searched architectures significantly outperform manually designed counterparts in various aspects, and our method achieves state-of-the-art performance at the same time.
Multi-view projection methods have demonstrated their ability to reach state-of-the-art performance on 3D shape recognition. Those methods learn different ways to aggregate information from multiple views. However, the camera view-points for those views tend to be heuristically set and fixed for all shapes. To circumvent the lack of dynamism of current multi-view methods, we propose to learn those view-points. In particular, we introduce the Multi-View Transformation Network (MVTN) that regresses optimal view-points for 3D shape recognition, building upon advances in differentiable rendering. As a result, MVTN can be trained end-to-end along with any multi-view network for 3D shape classification. We integrate MVTN in a novel adaptive multi-view pipeline that can render either 3D meshes or point clouds. MVTN exhibits clear performance gains in the tasks of 3D shape classification and 3D shape retrieval without the need for extra training supervision. In these tasks, MVTN achieves state-of-the-art performance on ModelNet40, ShapeNet Core55, and the most recent and realistic ScanObjectNN dataset (up to 6% improvement). Interestingly, we also show that MVTN can provide network robustness against rotation and occlusion in the 3D domain. The code is available at https://github.com/ajhamdi/MVTN .
In this paper PREMONN (PREdictive MOdular Neural Networks) model/architecture is generalized to functions of two variables and to non-Euclidean spaces. It is presented in the context of 3D invariant shape recognition and texture recognition. PREMONN uses local relation, it is modular and exhibits incremental learning. The recognition process can start at any point on a shape or texture, so a reference point is not needed. Its local relation characteristic enables it to recognize shape and texture even in presence of occlusion. The analysis is mainly mathematical. However, we present some experimental results. The methods presented in this paper can be applied to many problems such as gesture recognition, action recognition, dynamic texture recognition etc.
The success of supervised learning requires large-scale ground truth labels which are very expensive, time-consuming, or may need special skills to annotate. To address this issue, many self- or un-supervised methods are developed. Unlike most existing self-supervised methods to learn only 2D image features or only 3D point cloud features, this paper presents a novel and effective self-supervised learning approach to jointly learn both 2D image features and 3D point cloud features by exploiting cross-modality and cross-view correspondences without using any human annotated labels. Specifically, 2D image features of rendered images from different views are extracted by a 2D convolutional neural network, and 3D point cloud features are extracted by a graph convolution neural network. Two types of features are fed into a two-layer fully connected neural network to estimate the cross-modality correspondence. The three networks are jointly trained (i.e. cross-modality) by verifying whether two sampled data of different modalities belong to the same object, meanwhile, the 2D convolutional neural network is additionally optimized through minimizing intra-object distance while maximizing inter-object distance of rendered images in different views (i.e. cross-view). The effectiveness of the learned 2D and 3D features is evaluated by transferring them on five different tasks including multi-view 2D shape recognition, 3D shape recognition, multi-view 2D shape retrieval, 3D shape retrieval, and 3D part-segmentation. Extensive evaluations on all the five different tasks across different datasets demonstrate strong generalization and effectiveness of the learned 2D and 3D features by the proposed self-supervised method.
3D shape recognition has attracted more and more attention as a task of 3D vision research. The proliferation of 3D data encourages various deep learning methods based on 3D data. Now there have been many deep learning models based on point-cloud data or multi-view data alone. However, in the era of big data, integrating data of two different modals to obtain a unified 3D shape descriptor is bound to improve the recognition accuracy. Therefore, this paper proposes a fusion network based on multimodal attention mechanism for 3D shape recognition. Considering the limitations of multi-view data, we introduce a soft attention scheme, which can use the global point-cloud features to filter the multi-view features, and then realize the effective fusion of the two features. More specifically, we obtain the enhanced multi-view features by mining the contribution of each multi-view image to the overall shape recognition, and then fuse the point-cloud features and the enhanced multi-view features to obtain a more discriminative 3D shape descriptor. We have performed relevant experiments on the ModelNet40 dataset, and experimental results verify the effectiveness of our method.
Learning from unordered sets is a fundamental learning setup, recently attracting increasing attention. Research in this area has focused on the case where elements of the set are represented by feature vectors, and far less emphasis has been given to the common case where set elements themselves adhere to their own symmetries. That case is relevant to numerous applications, from deblurring image bursts to multi-view 3D shape recognition and reconstruction. In this paper, we present a principled approach to learning sets of general symmetric elements. We first characterize the space of linear layers that are equivariant both to element reordering and to the inherent symmetries of elements, like translation in the case of images. We further show that networks that are composed of these layers, called Deep Sets for Symmetric Elements (DSS) layers, are universal approximators of both invariant and equivariant functions, and that these networks are strictly more expressive than Siamese networks. DSS layers are also straightforward to implement. Finally, we show that they improve over existing set-learning architectures in a series of experiments with images, graphs, and point-clouds.
Existing networks directly learn feature representations on 3D point clouds for shape analysis. We argue that 3D point clouds are highly redundant and hold irregular (permutation-invariant) structure, which makes it difficult to achieve inter-class discrimination efficiently. In this paper, we propose a two-faceted solution to this problem that is seamlessly integrated in a single `Blended Convolution and Synthesis' layer. This fully differentiable layer performs two critical tasks in succession. In the first step, it projects the input 3D point clouds into a latent 3D space to synthesize a highly compact and more inter-class discriminative point cloud representation. Since, 3D point clouds do not follow a Euclidean topology, standard 2/3D Convolutional Neural Networks offer limited representation capability. Therefore, in the second step, it uses a novel 3D convolution operator functioning inside the unit ball ($\mathbb{B}^3$) to extract useful volumetric features. We extensively derive formulae to achieve both translation and rotation of our novel convolution kernels. Finally, using the proposed techniques we present an extremely light-weight, end-to-end architecture that achieves compelling results on 3D shape recognition and retrieval.