Related papers: MTVNet: Mapping using Transformers for Volumes -- …

This paper proposes Omnidirectional Representations from Transformers (OmniNet). In OmniNet, instead of maintaining a strictly horizontal receptive field, each token is allowed to attend to all tokens in the entire network. This process can…

Transformers have attracted increasing interests in computer vision, but they still fall behind state-of-the-art convolutional networks. In this work, we show that while Transformers tend to have larger model capacity, their generalization…

Deep CNN-based methods have so far achieved the state of the art results in multi-view 3D object reconstruction. Despite the considerable progress, the two core modules of these methods - multi-view feature extraction and fusion, are…

In recent years, there have been attempts to increase the kernel size of Convolutional Neural Nets (CNNs) to mimic the global receptive field of Vision Transformers' (ViTs) self-attention blocks. That approach, however, quickly hit an upper…

Neural volumetric representations have become a widely adopted model for radiance fields in 3D scenes. These representations are fully implicit or hybrid function approximators of the instantaneous volumetric radiance in a scene, which are…

While convolutional neural networks have shown a tremendous impact on various computer vision tasks, they generally demonstrate limitations in explicitly modeling long-range dependencies due to the intrinsic locality of the convolution…

In the field of medical CT image processing, convolutional neural networks (CNNs) have been the dominant technique.Encoder-decoder CNNs utilise locality for efficiency, but they cannot simulate distant pixel interactions properly.Recent…

We present lambda layers -- an alternative framework to self-attention -- for capturing long-range interactions between an input and structured contextual information (e.g. a pixel surrounded by other pixels). Lambda layers capture such…

We present Token-UNet, adopting the TokenLearner and TokenFuser modules to encase Transformers into UNets. While Transformers have enabled global interactions among input elements in medical imaging, current computational challenges hinder…

Can we leverage high-resolution information without the unsustainable quadratic complexity to input scale? We propose Traversal Network (TNet), a novel multi-scale hard-attention architecture, which traverses image scale-space in a top-down…

Transformers have become a common foundation across deep learning, yet 3D scene understanding still relies on specialized backbones with strong domain priors. This keeps the field isolated from the broader Transformer ecosystem, limiting…

Recent volumetric 3D reconstruction methods can produce very accurate results, with plausible geometry even for unobserved surfaces. However, they face an undesirable trade-off when it comes to multi-view fusion. They can fuse all available…

Window-based transformers have demonstrated outstanding performance in super-resolution tasks due to their adaptive modeling capabilities through local self-attention (SA). However, they exhibit higher computational complexity and inference…

Monocular scene reconstruction from posed images is challenging due to the complexity of a large environment. Recent volumetric methods learn to directly predict the TSDF volume and have demonstrated promising results in this task. However,…

Deep neural networks face numerous challenges in hyperspectral image classification, including high-dimensional data, sparse ground object distributions, and spectral redundancy, which often lead to classification overfitting and limited…

Transformers are widely used deep learning architectures. Existing transformers are mostly designed for sequences (texts or time series), images or videos, and graphs. This paper proposes a novel transformer model for massive (up to a…

Solving image-to-3D from a single view is an ill-posed problem, and current neural reconstruction methods addressing it through diffusion models still rely on scene-specific optimization, constraining their generalization capability. To…

In recent years, transformer-based deep learning networks have gained popularity in Hyperspectral (HS) unmixing applications due to their superior performance. The attention mechanism within transformers facilitates input-dependent…

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…

In recent years, sparse voxel-based methods have become the state-of-the-arts for 3D semantic segmentation of indoor scenes, thanks to the powerful 3D CNNs. Nevertheless, being oblivious to the underlying geometry, voxel-based methods…