Related papers: VSFormer: Mining Correlations in Flexible View Set…
We present a new deep learning approach for matching deformable shapes by introducing {\it Shape Deformation Networks} which jointly encode 3D shapes and correspondences. This is achieved by factoring the surface representation into (i) a…
This paper proposes a multi-view collaborative matching strategy for reliable track construction in complex scenarios. We observe that the pairwise matching paradigms applied to image set matching often result in ambiguous estimation when…
Deep learning is providing a wealth of new approaches to the problem of novel view synthesis, from Neural Radiance Field (NeRF) based approaches to end-to-end style architectures. Each approach offers specific strengths but also comes with…
Multiview images have flexible field of view (FoV) but inflexible depth of field (DoF). To overcome the limitation of multiview images on visual tasks, in this paper, we present varifocal multiview (VFMV) images with flexible DoF. VFMV…
Hypergraph can capture complex and higher-order dependencies among learners and learning resources in personalized educational recommender systems. Many existing hypergraph-based recommendation approaches underexplored the dynamic…
Camera and LiDAR sensor modalities provide complementary appearance and geometric information useful for detecting 3D objects for autonomous vehicle applications. However, current end-to-end fusion methods are challenging to train and…
If robots could reliably manipulate the shape of 3D deformable objects, they could find applications in fields ranging from home care to warehouse fulfillment to surgical assistance. Analytic models of elastic, 3D deformable objects require…
Feature representation learning is the key recipe for learning-based Multi-View Stereo (MVS). As the common feature extractor of learning-based MVS, vanilla Feature Pyramid Networks (FPNs) suffer from discouraged feature representations for…
This paper presents a novel framework for processing volumetric medical information using Visual Transformers (ViTs). First, We extend the state-of-the-art Swin Transformer model to the 3D medical domain. Second, we propose a new approach…
It is a challenging task to learn discriminative representation from images and videos, due to large local redundancy and complex global dependency in these visual data. Convolution neural networks (CNNs) and vision transformers (ViTs) have…
Recently, a growing number of work design unsupervised paradigms for point cloud processing to alleviate the limitation of expensive manual annotation and poor transferability of supervised methods. Among them, CrossPoint follows the…
Multiple-view visualization (MV) is a layout design technique often employed to help users see a large number of data attributes and values in a single cohesive representation. Because of its generalizability, the MV design has been widely…
This work proposes a new formulation to the long-standing problem of convex decomposition through learning feature fields, enabling the first feed-forward model for open-world convex decomposition. Our method produces high-quality…
Although multi-view learning has made signifificant progress over the past few decades, it is still challenging due to the diffificulty in modeling complex correlations among different views, especially under the context of view missing. To…
Skeleton-based human action recognition has recently attracted increasing attention thanks to the accessibility and the popularity of 3D skeleton data. One of the key challenges in skeleton-based action recognition lies in the large view…
Multi-view action recognition aims to recognize human actions using multiple camera views and deals with occlusion caused by obstacles or crowds. In this task, cooperation among views, which generates a joint representation by combining…
Directed graphs are widely used to model asymmetric relationships in real-world systems. However, existing directed graph neural networks often struggle to jointly capture directional semantics and global structural patterns due to their…
Recently, multi-view learning (MVL) has garnered significant attention due to its ability to fuse discriminative information from multiple views. However, real-world multi-view datasets are often heterogeneous and imperfect, which usually…
Understanding the mechanisms underlying deep neural networks remains a fundamental challenge in machine learning and computer vision. One promising, yet only preliminarily explored approach, is feature inversion, which attempts to…
We introduce a new framework for learning dense correspondence between deformable 3D shapes. Existing learning based approaches model shape correspondence as a labelling problem, where each point of a query shape receives a label…