This paper addresses the problem of novel view synthesis by means of neural rendering, where we are interested in predicting the novel view at an arbitrary camera pose based on a given set of input images from other viewpoints. Using the known query pose and input poses, we create an ordered set of observations that leads to the target view. Thus, the problem of single novel view synthesis is reformulated as a sequential view prediction task. In this paper, the proposed Transformer-based Generative Query Network (T-GQN) extends the neural-rendering methods by adding two new concepts. First, we use multi-view attention learning between context images to obtain multiple implicit scene representations. Second, we introduce a sequential rendering decoder to predict an image sequence, including the target view, based on the learned representations. Finally, we evaluate our model on various challenging datasets and demonstrate that our model not only gives consistent predictions but also doesn't require any retraining for finetuning.
Heidelberg Collaboratory for Image Processing（海德堡图像处理合作实验室）；Heidelberg University（海德堡大学）；IWR（跨学科科学计算中心）
Designed to learn long-range interactions on sequential data, transformers continue to show state-of-the-art results on a wide variety of tasks. In contrast to CNNs, they contain no inductive bias that prioritizes local interactions. This makes them expressive, but also computationally infeasible for long sequences, such as high-resolution images. We demonstrate how combining the effectiveness of the inductive bias of CNNs with the expressivity of transformers enables them to model and thereby synthesize high-resolution images. We show how to (i) use CNNs to learn a context-rich vocabulary of …
Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机研究所）；Peking University（北京大学）
Automatic generation of high-quality Chinese fonts from a few online training samples is a challenging task, especially when the amount of samples is very small. Existing few-shot font generation methods can only synthesize low-resolution glyph images that often possess incorrect topological structures or/and incomplete strokes. To address the problem, this paper proposes FontTransformer, a novel few-shot learning model, for high-resolution Chinese glyph image synthesis by using stacked Transformers. The key idea is to apply the parallel Transformer to avoid the accumulation of prediction erro…
Story Visualization is an advanced task of computed vision that targets sequential image synthesis, where the generated samples need to be realistic, faithful to their conditioning and sequentially consistent. Our work proposes a novel architectural and training approach: the Impartial Transformer achieves both text-relevant plausible scenes and sequential consistency utilizing as few trainable parameters as possible. This enhancement is even able to handle synthesis of 'hard' samples with occluded objects, achieving improved evaluation metrics comparing to past approaches.
VolDiT: Controllable Volumetric Medical Image Synthesis with Diffusion Transformers
Institute for Artificial Intelligence in Cardiovascular Medicine, Medical Faculty of Heidelberg University, Heidelberg University（海德堡大学医学院心血管医学人工智能研究所）；Department of Cardiology, Angiology, Pneumology, Heidelberg University Hospital（海德堡大学医院心脏病学、血管学、肺病学系）；DZHK (German Centre for Cardiovascular Research), Partner Site Heidelberg/Mannheim（德国心血管研究中心（DZHK）海德堡/曼海姆合作站点）；University Medical Center of the Johannes Gutenberg-University Mainz（美因茨约翰内斯·古腾堡大学医学中心）
Transformer is eminently suitable for auto-regressive image synthesis which predicts discrete value from the past values recursively to make up full image. Especially, combined with vector quantised latent representation, the state-of-the-art auto-regressive transformer displays realistic high-resolution images. However, sampling the latent code from discrete probability distribution makes the output unpredictable. Therefore, it requires to generate lots of diverse samples to acquire desired outputs. To alleviate the process of generating lots of samples repetitively, in this article, we propo…
Learning light-weight yet expressive deep networks in both image synthesis and image recognition remains a challenging problem. Inspired by a more recent observation that it is the data-specificity that makes the multi-head self-attention (MHSA) in the Transformer model so powerful, this paper proposes to extend the widely adopted light-weight Squeeze-Excitation (SE) module to be spatially-adaptive to reinforce its data specificity, as a convolutional alternative of the MHSA, while retaining the efficiency of SE and the inductive basis of convolution. It presents two designs of spatially-adapt…
Cosh-DiT: Co-Speech Gesture Video Synthesis via Hybrid Audio-Visual Diffusion Transformers
King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）；Baidu（百度）；Tokyo Institute of Technology（东京工业大学）；Tsinghua University（清华大学）；University of Science and Technology of China（中国科学技术大学）；Nanyang Technological University（南洋理工大学）
University of Nevada, Reno（内华达大学雷诺分校）；Houston Eye Associates（休斯顿眼科协会）
In Fluorescein Angiography (FA), an exogenous dye is injected in the bloodstream to image the vascular structure of the retina. The injected dye can cause adverse reactions such as nausea, vomiting, anaphylactic shock, and even death. In contrast, color fundus imaging is a non-invasive technique used for photographing the retina but does not have sufficient fidelity for capturing its vascular structure. The only non-invasive method for capturing retinal vasculature is optical coherence tomography-angiography (OCTA). However, OCTA equipment is quite expensive, and stable imaging is limited to s…
MMoT: Mixture-of-Modality-Tokens Transformer for Composed Multimodal Conditional Image Synthesis
South China University of Technology（华南理工大学）；JD Explore Academy（京东探索研究院）；Nanyang Technological University（南洋理工大学）；Shanghai Jiao Tong University（上海交通大学）
School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）；Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education, China（中国教育部机器智能与先进计算重点实验室）；Microsoft Research Asia（微软亚洲研究院）；University of Tokyo（东京大学）
We present a new perspective of achieving image synthesis by viewing this task as a visual token generation problem. Different from existing paradigms that directly synthesize a full image from a single input (e.g., a latent code), the new formulation enables a flexible local manipulation for different image regions, which makes it possible to learn content-aware and fine-grained style control for image synthesis. Specifically, it takes as input a sequence of latent tokens to predict the visual tokens for synthesizing an image. Under this perspective, we propose a token-based generator (i.e.,T…
We present an end-to-end Transformer based Latent Diffusion model for image synthesis. On the ImageNet class conditioned generation task we show that a Transformer based Latent Diffusion model achieves a 14.1FID which is comparable to the 13.1FID score of a UNet based architecture. In addition to showing the application of Transformer models for Diffusion based image synthesis this simplification in architecture allows easy fusion and modeling of text and image data. The multi-head attention mechanism of Transformers enables simplified interaction between the image and text features which remo…
Existing keyframe-based motion synthesis mainly focuses on the generation of cyclic actions or short-term motion, such as walking, running, and transitions between close postures. However, these methods will significantly degrade the naturalness and diversity of the synthesized motion when dealing with complex and impromptu movements, e.g., dance performance and martial arts. In addition, current research lacks fine-grained control over the generated motion, which is essential for intelligent human-computer interaction and animation creation. In this paper, we propose a novel keyframe-based mo…
Conditional image synthesis aims to create an image according to some multi-modal guidance in the forms of textual descriptions, reference images, and image blocks to preserve, as well as their combinations. In this paper, instead of investigating these control signals separately, we propose a new two-stage architecture, M6-UFC, to unify any number of multi-modal controls. In M6-UFC, both the diverse control signals and the synthesized image are uniformly represented as a sequence of discrete tokens to be processed by Transformer. Different from existing two-stage autoregressive approaches suc…
Bilkent University（比尔肯特大学）；National Magnetic Resonance Research Center (UMRAM)（国家磁共振研究中心（UMRAM））；Sabuncu Brain Research Center（萨本库脑研究中心）
Generative adversarial models with convolutional neural network (CNN) backbones have recently been established as state-of-the-art in numerous medical image synthesis tasks. However, CNNs are designed to perform local processing with compact filters, and this inductive bias compromises learning of contextual features. Here, we propose a novel generative adversarial approach for medical image synthesis, ResViT, that leverages the contextual sensitivity of vision transformers along with the precision of convolution operators and realism of adversarial learning.} ResViT's generator employs a cent…
Mammo-Mamba: A Hybrid State-Space and Transformer Architecture with Sequential Mixture of Experts for Multi-View Mammography
Concordia Institute for Information Systems Engineering (CIISE)（康科德信息系统工程研究所）；Concordia University（康科德大学）；Thomas Jefferson University Hospital（托马斯·杰斐逊大学医院）
Person Search aims to simultaneously localize and recognize a target person from realistic and uncropped gallery images. One major challenge of person search comes from the contradictory goals of the two sub-tasks, i.e., person detection focuses on finding the commonness of all persons so as to distinguish persons from the background, while person re-identification (re-ID) focuses on the differences among different persons. In this paper, we propose a novel Sequential Transformer (SeqTR) for end-to-end person search to deal with this challenge. Our SeqTR contains a detection transformer and a …
3D hand pose estimation (HPE) is the process of locating the joints of the hand in 3D from any visual input. HPE has recently received an increased amount of attention due to its key role in a variety of human-computer interaction applications. Recent HPE methods have demonstrated the advantages of employing videos or multi-view images, allowing for more robust HPE systems. Accordingly, in this study, we propose a new method to perform Sequential learning with Transformer for Hand Pose (SeTHPose) estimation. Our SeTHPose pipeline begins by extracting visual embeddings from individual hand imag…
Interactive Gadolinium-Free MRI Synthesis: A Transformer with Localization Prompt Learning
School of Artificial Intelligence, Hebei University of Technology（河北工业大学人工智能学院）；The First Hospital of Jilin University（吉林大学第一医院）；Research Center for Medical AI, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院医学人工智能研究中心）
Beijing Institute of Technology（北京理工大学）；National University of Defense Technology（国防科技大学）
Place recognition is an important component for autonomous vehicles to achieve loop closing or global localization. In this paper, we tackle the problem of place recognition based on sequential 3D LiDAR scans obtained by an onboard LiDAR sensor. We propose a transformer-based network named SeqOT to exploit the temporal and spatial information provided by sequential range images generated from the LiDAR data. It uses multi-scale transformers to generate a global descriptor for each sequence of LiDAR range images in an end-to-end fashion. During online operation, our SeqOT finds similar places b…
Deep Convolutional Neural Networks (CNNs) are powerful models that have achieved excellent performance on difficult computer vision tasks. Although CNNs perform well whenever large labeled training samples are available, they work badly on video frame synthesis due to objects deforming and moving, scene lighting changes, and cameras moving in video sequence. In this paper, we present a novel and general end-to-end architecture, called convolutional Transformer or ConvTransformer, for video frame sequence learning and video frame synthesis. The core ingredient of ConvTransformer is the proposed…
The use of coarse-grained layouts for controllable synthesis of complex scene images via deep generative models has recently gained popularity. However, results of current approaches still fall short of their promise of high-resolution synthesis. We hypothesize that this is mostly due to the highly engineered nature of these approaches which often rely on auxiliary losses and intermediate steps such as mask generators. In this note, we present an orthogonal approach to this task, where the generative model is based on pure likelihood training without additional objectives. To do so, we first o…
CVSformer: Cross-View Synthesis Transformer for Semantic Scene Completion
Tianjin University（天津大学）；Shenzhen University（深圳大学）；A*STAR（新加坡科技研究局）；The Hong Kong Polytechnic University（香港理工大学）；South China University of Technology（华南理工大学）；Alibaba Damo Academy（阿里巴巴达摩院）
Ludwig Maximilian University of Munich（慕尼黑大学）；IWR Heidelberg University（海德堡大学跨学科科学计算中心）
Is a geometric model required to synthesize novel views from a single image? Being bound to local convolutions, CNNs need explicit 3D biases to model geometric transformations. In contrast, we demonstrate that a transformer-based model can synthesize entirely novel views without any hand-engineered 3D biases. This is achieved by (i) a global attention mechanism for implicitly learning long-range 3D correspondences between source and target views, and (ii) a probabilistic formulation necessary to capture the ambiguity inherent in predicting novel views from a single image, thereby overcoming th…
We consider the problem of synthesizing multi-action human motion sequences of arbitrary lengths. Existing approaches have mastered motion sequence generation in single action scenarios, but fail to generalize to multi-action and arbitrary-length sequences. We fill this gap by proposing a novel efficient approach that leverages expressiveness of Recurrent Transformers and generative richness of conditional Variational Autoencoders. The proposed iterative approach is able to generate smooth and realistic human motion sequences with an arbitrary number of actions and frames while doing so in lin…
We propose a Transformer-based NeRF (TransNeRF) to learn a generic neural radiance field conditioned on observed-view images for the novel view synthesis task. By contrast, existing MLP-based NeRFs are not able to directly receive observed views with an arbitrary number and require an auxiliary pooling-based operation to fuse source-view information, resulting in the missing of complicated relationships between source views and the target rendering view. Furthermore, current approaches process each 3D point individually and ignore the local consistency of a radiance field scene representation.…
McGill University（麦吉尔大学）；Sunnybrook Research Institute（桑尼布鲁克研究所）；University of Toronto（多伦多大学）
Most hard attention models initially observe a complete scene to locate and sense informative glimpses, and predict class-label of a scene based on glimpses. However, in many applications (e.g., aerial imaging), observing an entire scene is not always feasible due to the limited time and resources available for acquisition. In this paper, we develop a Sequential Transformers Attention Model (STAM) that only partially observes a complete image and predicts informative glimpse locations solely based on past glimpses. We design our agent using DeiT-distilled and train it with a one-step actor-cri…
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Max Planck ETH Center for Learning Systems（马克斯·普朗克 ETH 学习系统中心）；NVIDIA（英伟达）；University of Toronto（多伦多大学）；Vector Institute（向量研究所）；University of Tübingen（蒂宾根大学）
The ability to synthesize realistic and diverse indoor furniture layouts automatically or based on partial input, unlocks many applications, from better interactive 3D tools to data synthesis for training and simulation. In this paper, we present ATISS, a novel autoregressive transformer architecture for creating diverse and plausible synthetic indoor environments, given only the room type and its floor plan. In contrast to prior work, which poses scene synthesis as sequence generation, our model generates rooms as unordered sets of objects. We argue that this formulation is more natural, as i…
A classical problem in computer vision is to infer a 3D scene representation from few images that can be used to render novel views at interactive rates. Previous work focuses on reconstructing pre-defined 3D representations, e.g. textured meshes, or implicit representations, e.g. radiance fields, and often requires input images with precise camera poses and long processing times for each novel scene. In this work, we propose the Scene Representation Transformer (SRT), a method which processes posed or unposed RGB images of a new area, infers a "set-latent scene representation", and synthesise…
We tackle the task of synthesizing novel views of an object given a few input images and associated camera viewpoints. Our work is inspired by recent 'geometry-free' approaches where multi-view images are encoded as a (global) set-latent representation, which is then used to predict the color for arbitrary query rays. While this representation yields (coarsely) accurate images corresponding to novel viewpoints, the lack of geometric reasoning limits the quality of these outputs. To overcome this limitation, we propose 'Geometry-biased Transformers' (GBTs) that incorporate geometric inductive b…
Huazhong University of Science and Technology（华中科技大学）；Bytedance（字节跳动）
In this work, we present SeqFormer for video instance segmentation. SeqFormer follows the principle of vision transformer that models instance relationships among video frames. Nevertheless, we observe that a stand-alone instance query suffices for capturing a time sequence of instances in a video, but attention mechanisms shall be done with each frame independently. To achieve this, SeqFormer locates an instance in each frame and aggregates temporal information to learn a powerful representation of a video-level instance, which is used to predict the mask sequences on each frame dynamically. …
LIGM, École des Ponts, Univ Gustave Eiffel, CNRS（LIGM, 巴黎综合理工学院桥路学校, 古斯塔夫·埃菲尔大学, 法国国家科学研究中心）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）
We tackle the problem of action-conditioned generation of realistic and diverse human motion sequences. In contrast to methods that complete, or extend, motion sequences, this task does not require an initial pose or sequence. Here we learn an action-aware latent representation for human motions by training a generative variational autoencoder (VAE). By sampling from this latent space and querying a certain duration through a series of positional encodings, we synthesize variable-length motion sequences conditioned on a categorical action. Specifically, we design a Transformer-based architectu…
BodyFormer: Semantics-guided 3D Body Gesture Synthesis with Transformer
Guangdong Academy of Sciences（广东省科学院）；The University of Hong Kong（香港大学）；The University of Edinburgh（爱丁堡大学）；Meta Reality Labs Research（Meta现实实验室）；National Institute of Informatics（国立信息学研究所）；Tohoku University（东北大学）
