Related papers: P2PFormer: A Primitive-to-polygon Method for Regul…
Describing a scene in terms of primitives -- geometrically simple shapes that offer a parsimonious but accurate abstraction of structure -- is an established and difficult fitting problem. Different scenes require different numbers of…
The traditional Transformer model encounters challenges with variable-length input sequences, particularly in Hyperspectral Image Classification (HSIC), leading to efficiency and scalability concerns. To overcome this, we propose a…
Computational imaging through scatter generally is accomplished by first characterizing the scattering medium so that its forward operator is obtained; and then imposing additional priors in the form of regularizers on the reconstruction…
Document structure extraction has been a widely researched area for decades with recent works performing it as a semantic segmentation task over document images using fully-convolution networks. Such methods are limited by image resolution…
Topological features play an essential role in ensuring geometric plausibility and structural consistency in image analysis tasks such as segmentation and skeletonization. However, integrating topology-preserving learning based on simple…
The convolutional neural network-based methods have become more and more popular for medical image segmentation due to their outstanding performance. However, they struggle with capturing long-range dependencies, which are essential for…
We introduce PC2WF, the first end-to-end trainable deep network architecture to convert a 3D point cloud into a wireframe model. The network takes as input an unordered set of 3D points sampled from the surface of some object, and outputs a…
Prototypical part network (ProtoPNet) has drawn wide attention and boosted many follow-up studies due to its self-explanatory property for explainable artificial intelligence (XAI). However, when directly applying ProtoPNet on vision…
We investigate the problem of learning to generate 3D parametric surface representations for novel object instances, as seen from one or more views. Previous work on learning shape reconstruction from multiple views uses discrete…
Neural implicit representations have become a popular choice for modeling surfaces due to their adaptability in resolution and support for complex topology. While previous works have achieved impressive reconstruction quality by training on…
Although vision transformers (ViTs) have achieved great success in computer vision, the heavy computational cost hampers their applications to dense prediction tasks such as semantic segmentation on mobile devices. In this paper, we present…
Object recognition using single-point supervision has attracted increasing attention recently. However, the performance gap compared with fully-supervised algorithms remains large. Previous works generated class-agnostic…
Grid-based structures are commonly used to encode explicit features for graphics primitives such as images, signed distance functions (SDF), and neural radiance fields (NeRF) due to their simple implementation. However, in $n$-dimensional…
Motion segmentation in dynamic scenes is highly challenging, as conventional methods heavily rely on estimating camera poses and point correspondences from inherently noisy motion cues. Existing statistical inference or iterative…
Transformers have been seldom employed in point cloud roof plane instance segmentation, which is the focus of this study, and existing superpoint Transformers suffer from limited performance due to the use of low-quality superpoints. To…
Thin structures, such as wire-frame sculptures, fences, cables, power lines, and tree branches, are common in the real world. It is extremely challenging to acquire their 3D digital models using traditional image-based or depth-based…
Stereo image matching is a fundamental task in computer vision, photogrammetry and remote sensing, but there is an almost unexplored field, i.e., polygon matching, which faces the following challenges: disparity discontinuity, scale…
The generalization of the Transformer architecture via MetaFormer has reshaped our understanding of its success in computer vision. By replacing self-attention with simpler token mixers, MetaFormer provides strong baselines for vision…
This paper proposes a simple and efficient method for the reconstruction and extraction of geometric parameters from 3D tubular objects. Our method constructs an image that accumulates surface normal information, then peaks within this…
Recent medical image segmentation methods apply implicit neural representation (INR) to the decoder for achieving a continuous coordinate decoding to tackle the drawback of conventional discrete grid-based data representations. However, the…