Transformers are becoming increasingly popular due to their superior performance over conventional convolutional neural networks(CNNs). However, transformers usually require a much larger amount of memory to train than CNNs, which prevents their application in many low resource settings. Local learning, which divides the network into several distinct modules and trains them individually, is a promising alternative to the end-to-end (E2E) training approach to reduce the amount of memory for training and to increase parallelism. This paper is the first to apply Local Learning on transformers for this purpose. The standard CNN-based local learning method, InfoPro [32], reconstructs the input images for each module in a CNN. However, reconstructing the entire image does not generalize well. In this paper, we propose a new mechanism for each local module, where instead of reconstructing the entire image, we reconstruct its input features, generated from previous modules. We evaluate our approach on 4 commonly used datasets and 3 commonly used decoder structures on Swin-Tiny. The experiments show that our approach outperforms InfoPro-Transformer, the InfoPro with Transfomer backbone we introduced, by at up to 0.58% on CIFAR-10, CIFAR-100, STL-10 and SVHN datasets, while using up to 12% less memory. Compared to the E2E approach, we require 36% less GPU memory when the network is divided into 2 modules and 45% less GPU memory when the network is divided into 4 modules.
ETH Zurich（苏黎世联邦理工学院）；RWTH Aachen（亚琛工业大学）；LMU Munich（慕尼黑大学）
3D reconstruction aims to reconstruct 3D objects from 2D views. Previous works for 3D reconstruction mainly focus on feature matching between views or using CNNs as backbones. Recently, Transformers have been shown effective in multiple applications of computer vision. However, whether or not Transformers can be used for 3D reconstruction is still unclear. In this paper, we fill this gap by proposing 3D-RETR, which is able to perform end-to-end 3D REconstruction with TRansformers. 3D-RETR first uses a pretrained Transformer to extract visual features from 2D input images. 3D-RETR then uses ano…
Deep Learning (DL) based methods for magnetic resonance (MR) image reconstruction have been shown to produce superior performance in recent years. However, these methods either only leverage under-sampled data or require a paired fully-sampled auxiliary modality to perform multi-modal reconstruction. Consequently, existing approaches neglect to explore attention mechanisms that can transfer textures from reference fully-sampled data to under-sampled data within a single modality, which limits these approaches in challenging cases. In this paper, we propose a novel Texture Transformer Module (T…
Deep learning-based 3D object reconstruction has achieved unprecedented results. Among those, the transformer deep neural model showed outstanding performance in many applications of computer vision. We introduce SnakeVoxFormer, a novel, 3D object reconstruction in voxel space from a single image using the transformer. The input to SnakeVoxFormer is a 2D image, and the result is a 3D voxel model. The key novelty of our approach is in using the run-length encoding that traverses (like a snake) the voxel space and encodes wide spatial differences into a 1D structure that is suitable for transfor…
Anomaly detection with only prior knowledge from normal samples attracts more attention because of the lack of anomaly samples. Existing CNN-based pixel reconstruction approaches suffer from two concerns. First, the reconstruction source and target are raw pixel values that contain indistinguishable semantic information. Second, CNN tends to reconstruct both normal samples and anomalies well, making them still hard to distinguish. In this paper, we propose Anomaly Detection TRansformer (ADTR) to apply a transformer to reconstruct pre-trained features. The pre-trained features contain distingui…
University of British Columbia（不列颠哥伦比亚大学）；University of Science and Technology of China（中国科学技术大学）；University of Michigan（密歇根大学）；NetEase Fuxi AI Lab（网易伏羲人工智能实验室）
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 usually investigated separately, and the object relations in different views are rarely explored. In this paper, inspired by the recent great success in self-attention-based Transformer models, we reformulate the multi-view 3D reconstruction as a sequence-to-sequence prediction problem and propose a new framework named 3D Volume Transformer (VolT) for such a task.…
Technical University of Munich（慕尼黑工业大学）；Google Inc（谷歌公司）
Most modern deep learning-based multi-view 3D reconstruction techniques use RNNs or fusion modules to combine information from multiple images after independently encoding them. These two separate steps have loose connections and do not allow easy information sharing among views. We propose LegoFormer, a transformer model for voxel-based 3D reconstruction that uses the attention layers to share information among views during all computational stages. Moreover, instead of predicting each voxel independently, we propose to parametrize the output with a series of low-rank decomposition factors. T…
We present a new method, called MEsh TRansfOrmer (METRO), to reconstruct 3D human pose and mesh vertices from a single image. Our method uses a transformer encoder to jointly model vertex-vertex and vertex-joint interactions, and outputs 3D joint coordinates and mesh vertices simultaneously. Compared to existing techniques that regress pose and shape parameters, METRO does not rely on any parametric mesh models like SMPL, thus it can be easily extended to other objects such as hands. We further relax the mesh topology and allow the transformer self-attention mechanism to freely attend between …
Déjà View: Looping Transformers for Multi-View 3D Reconstruction
NVIDIA；University of Modena and Reggio Emilia, AImageLab（摩德纳和雷焦艾米利亚大学，AImageLab）；University of Toronto, Vector Institute（多伦多大学，向量研究所）；ETH Zürich（苏黎世联邦理工学院）
Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Harvard University（哈佛大学）；ETH Zürich（苏黎世联邦理工学院）；CAIDAS, JMU Würzburg（维尔茨堡大学CAIDAS研究所）
Existing leading methods for spectral reconstruction (SR) focus on designing deeper or wider convolutional neural networks (CNNs) to learn the end-to-end mapping from the RGB image to its hyperspectral image (HSI). These CNN-based methods achieve impressive restoration performance while showing limitations in capturing the long-range dependencies and self-similarity prior. To cope with this problem, we propose a novel Transformer-based method, Multi-stage Spectral-wise Transformer (MST++), for efficient spectral reconstruction. In particular, we employ Spectral-wise Multi-head Self-attention (…
Simon Fraser University（西蒙弗雷泽大学）；University of Manitoba（曼尼托巴大学）
This paper presents a novel attention-based neural network for structured reconstruction, which takes a 2D raster image as an input and reconstructs a planar graph depicting an underlying geometric structure. The approach detects corners and classifies edge candidates between corners in an end-to-end manner. Our contribution is a holistic edge classification architecture, which 1) initializes the feature of an edge candidate by a trigonometric positional encoding of its end-points; 2) fuses image feature to each edge candidate by deformable attention; 3) employs two weight-sharing Transformer …
We present THUNDR, a transformer-based deep neural network methodology to reconstruct the 3d pose and shape of people, given monocular RGB images. Key to our methodology is an intermediate 3d marker representation, where we aim to combine the predictive power of model-free-output architectures and the regularizing, anthropometrically-preserving properties of a statistical human surface model like GHUM -- a recently introduced, expressive full body statistical 3d human model, trained end-to-end. Our novel transformer-based prediction pipeline can focus on image regions relevant to the task, sup…
Traditional methods of reconstructing 3D human pose and mesh from single images rely on paired image-mesh datasets, which can be difficult and expensive to obtain. Due to this limitation, model scalability is constrained as well as reconstruction performance. Towards addressing the challenge, we introduce Mesh Pre-Training (MPT), an effective pre-training strategy that leverages large amounts of MoCap data to effectively perform pre-training at scale. We introduce the use of MoCap-generated heatmaps as input representations to the mesh regression transformer and propose a Masked Heatmap Modeli…
University of California, Irvine（加州大学欧文分校）；Georgia Institute of Technology（佐治亚理工学院）
We tackle the problem of automatically reconstructing a complete 3D model of a scene from a single RGB image. This challenging task requires inferring the shape of both visible and occluded surfaces. Our approach utilizes viewer-centered, multi-layer representation of scene geometry adapted from recent methods for single object shape completion. To improve the accuracy of view-centered representations for complex scenes, we introduce a novel "Epipolar Feature Transformer" that transfers convolutional network features from an input view to other virtual camera viewpoints, and thus better covers…
Reconstructing a 3D object from a 2D image is a well-researched vision problem, with many kinds of deep learning techniques having been tried. Most commonly, 3D convolutional approaches are used, though previous work has shown state-of-the-art methods using 2D convolutions that are also significantly more efficient to train. With the recent rise of transformers for vision tasks, often outperforming convolutional methods, along with some earlier attempts to use transformers for 3D object reconstruction, we set out to use visual transformers in place of convolutions in existing efficient, high-p…
MGRQ: Post-Training Quantization For Vision Transformer With Mixed Granularity Reconstruction
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Technical University of Munich（慕尼黑工业大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）
We introduce TransformerFusion, a transformer-based 3D scene reconstruction approach. From an input monocular RGB video, the video frames are processed by a transformer network that fuses the observations into a volumetric feature grid representing the scene; this feature grid is then decoded into an implicit 3D scene representation. Key to our approach is the transformer architecture that enables the network to learn to attend to the most relevant image frames for each 3D location in the scene, supervised only by the scene reconstruction task. Features are fused in a coarse-to-fine fashion, s…
Shenzhen Institute of Future Media Technology（深圳未来媒体技术研究院）；Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Westlake University（西湖大学）；ETH Zürich（苏黎世联邦理工学院）
Many algorithms have been developed to solve the inverse problem of coded aperture snapshot spectral imaging (CASSI), i.e., recovering the 3D hyperspectral images (HSIs) from a 2D compressive measurement. In recent years, learning-based methods have demonstrated promising performance and dominated the mainstream research direction. However, existing CNN-based methods show limitations in capturing long-range dependencies and non-local self-similarity. Previous Transformer-based methods densely sample tokens, some of which are uninformative, and calculate the multi-head self-attention (MSA) betw…
NOVA3R: Non-pixel-aligned Visual Transformer for Amodal 3D Reconstruction
Technical University of Munich（慕尼黑技术大学）；Munich Center for Machine Learning（慕尼黑机器学习中心）；University of Oxford（牛津大学）；Nanyang Technological University（南洋理工大学）
STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer
S-Lab, Nanyang Technological University, Singapore（南洋理工大学S实验室）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；WICT, Peking University（北京大学WICT学院）；The University of Hong Kong（香港大学）
Xiamen University（厦门大学）；Central China Normal University（华中师范大学）
The neuron reconstruction from raw Optical Microscopy (OM) image stacks is the basis of neuroscience. Manual annotation and semi-automatic neuron tracing algorithms are time-consuming and inefficient. Existing deep learning neuron reconstruction methods, although demonstrating exemplary performance, greatly demand complex rule-based components. Therefore, a crucial challenge is designing an end-to-end neuron reconstruction method that makes the overall framework simpler and model training easier. We propose a Neuron Reconstruction Transformer (NRTR) that, discarding the complex rule-based comp…
We propose a transformer-based neural network architecture for multi-object 3D reconstruction from RGB videos. It relies on two alternative ways to represent its knowledge: as a global 3D grid of features and an array of view-specific 2D grids. We progressively exchange information between the two with a dedicated bidirectional attention mechanism. We exploit knowledge about the image formation process to significantly sparsify the attention weight matrix, making our architecture feasible on current hardware, both in terms of memory and computation. We attach a DETR-style head on top of the 3D…
This paper considers the problem of undersampled MRI reconstruction. We propose a novel Transformer-based framework for directly processing signal in k-space, going beyond the limitation of regular grids as ConvNets do. We adopt an implicit representation of k-space spectrogram, treating spatial coordinates as inputs, and dynamically query the sparsely sampled points to reconstruct the spectrogram, i.e. learning the inductive bias in k-space. To strike a balance between computational cost and reconstruction quality, we build the decoder with hierarchical structure to generate low-resolution an…
The Athenian School（雅典纳中学）；Cornell University（康奈尔大学）
Because of the necessity to obtain high-quality images with minimal radiation doses, such as in low-field magnetic resonance imaging, super-resolution reconstruction in medical imaging has become more popular (MRI). However, due to the complexity and high aesthetic requirements of medical imaging, image super-resolution reconstruction remains a difficult challenge. In this paper, we offer a deep learning-based strategy for reconstructing medical images from low resolutions utilizing Transformer and Generative Adversarial Networks (T-GAN). The integrated system can extract more precise texture …
University of Maryland, College Park（马里兰大学学院公园分校）；State Key Laboratory of General Artificial Intelligence, BIGAI（通用人工智能国家重点实验室，BIGAI）；ETH Zurich（苏黎世联邦理工学院）
Imperial College London（帝国理工学院）；Royal Brompton Hospital（皇家布朗普顿医院）
Magnetic resonance imaging (MRI) is a widely used non-radiative and non-invasive method for clinical interrogation of organ structures and metabolism, with an inherently long scanning time. Methods by k-space undersampling and deep learning based reconstruction have been popularised to accelerate the scanning process. This work focuses on investigating how powerful transformers are for fast MRI by exploiting and comparing different novel network architectures. In particular, a generative adversarial network (GAN) based Swin transformer (ST-GAN) was introduced for the fast MRI reconstruction. T…
Accelerating magnetic resonance image (MRI) reconstruction process is a challenging ill-posed inverse problem due to the excessive under-sampling operation in k-space. In this paper, we propose a recurrent transformer model, namely ReconFormer, for MRI reconstruction which can iteratively reconstruct high fertility magnetic resonance images from highly under-sampled k-space data. In particular, the proposed architecture is built upon Recurrent Pyramid Transformer Layers (RPTL), which jointly exploits intrinsic multi-scale information at every architecture unit as well as the dependencies of th…
SHFormer: Dynamic Spectral Filtering Convolutional Neural Network and High-pass Kernel Generation Transformer for Adaptive MRI Reconstruction
Indian Institute of Technology Madras (IITM)（印度理工学院马德拉斯分校）；Healthcare Technology Innovation Centre（医疗技术创新中心）；GE John F Welch Technology Center（通用电气约翰·F·韦尔奇技术中心）
TranSG: Transformer-Based Skeleton Graph Prototype Contrastive Learning with Structure-Trajectory Prompted Reconstruction for Person Re-Identification
LILY Research Center, Nanyang Technological University（南洋理工大学LILY研究中心）；School of Computer Science and Engineering, Nanyang Technological University（南洋理工大学计算机科学与工程学院）
Combining Microscopy Data and Metadata for Reconstruction of Cellular Traction Forces Using a Hybrid Vision Transformer-U-Net
Fakultät Physik, Technische Universität Dortmund（物理系，德意志理工大学多特蒙德分校）；Faculty of Physics and Center for NanoScience, Ludwig-Maximilians-Universität München（物理系和纳米科学中心，路德维希-马克西米利安大学慕尼黑分校）；Department of Veterinary Sciences, Ludwig-Maximilians-Universität München（兽医学系，路德维希-马克西米利安大学慕尼黑分校）
