2022-03-04 更新
ARCH++: Animation-Ready Clothed Human Reconstruction Revisited
Authors:Tong He, Yuanlu Xu, Shunsuke Saito, Stefano Soatto, Tony Tung
We present ARCH++, an image-based method to reconstruct 3D avatars with arbitrary clothing styles. Our reconstructed avatars are animation-ready and highly realistic, in both the visible regions from input views and the unseen regions. While prior work shows great promise of reconstructing animatable clothed humans with various topologies, we observe that there exist fundamental limitations resulting in sub-optimal reconstruction quality. In this paper, we revisit the major steps of image-based avatar reconstruction and address the limitations with ARCH++. First, we introduce an end-to-end point based geometry encoder to better describe the semantics of the underlying 3D human body, in replacement of previous hand-crafted features. Second, in order to address the occupancy ambiguity caused by topological changes of clothed humans in the canonical pose, we propose a co-supervising framework with cross-space consistency to jointly estimate the occupancy in both the posed and canonical spaces. Last, we use image-to-image translation networks to further refine detailed geometry and texture on the reconstructed surface, which improves the fidelity and consistency across arbitrary viewpoints. In the experiments, we demonstrate improvements over the state of the art on both public benchmarks and user studies in reconstruction quality and realism.
PDF published at ICCV 2021, project page: https://tonghehehe.com/archpp
论文截图
FedMed-GAN: Federated Domain Translation on Unsupervised Cross-Modality Brain Image Synthesis
Authors:Guoyang Xie, Jinbao Wang, Yawen Huang, Yuexiang Li, Yefeng Zheng, Feng Zheng, Yaochu Jin
Utilizing multi-modal neuroimaging data has been proved to be effective to investigate human cognitive activities and certain pathologies. However, it is not practical to obtain the full set of paired neuroimaging data centrally since the collection faces several constraints, e.g., high examination cost, long acquisition time, and image corruption. In addition, these data are dispersed into different medical institutions and thus cannot be aggregated for centralized training considering the privacy issues. There is a clear need to launch a federated learning and facilitate the integration of the dispersed data from different institutions. In this paper, we propose a new benchmark for federated domain translation on unsupervised brain image synthesis (termed as FedMed-GAN) to bridge the gap between federated learning and medical GAN. FedMed-GAN mitigates the mode collapse without sacrificing the performance of generators, and is widely applied to different proportions of unpaired and paired data with variation adaptation property. We treat the gradient penalties by federally averaging algorithm and then leveraging differential privacy gradient descent to regularize the training dynamics. A comprehensive evaluation is provided for comparing FedMed-GAN and other centralized methods, which shows the new state-of-the-art performance by our FedMed-GAN. Our code has been released on the website: https://github.com/M-3LAB/FedMed-GAN
PDF
论文截图
Learning Efficient GANs for Image Translation via Differentiable Masks and co-Attention Distillation
Authors:Shaojie Li, Mingbao Lin, Yan Wang, Fei Chao, Ling Shao, Rongrong Ji
Generative Adversarial Networks (GANs) have been widely-used in image translation, but their high computation and storage costs impede the deployment on mobile devices. Prevalent methods for CNN compression cannot be directly applied to GANs due to the peculiarties of GAN tasks and the unstable adversarial training. To solve these, in this paper, we introduce a novel GAN compression method, termed DMAD, by proposing a Differentiable Mask and a co-Attention Distillation. The former searches for a light-weight generator architecture in a training-adaptive manner. To overcome channel inconsistency when pruning the residual connections, an adaptive cross-block group sparsity is further incorporated. The latter simultaneously distills informative attention maps from both the generator and discriminator of a pre-trained model to the searched generator, effectively stabilizing the adversarial training of our light-weight model. Experiments show that DMAD can reduce the Multiply Accumulate Operations (MACs) of CycleGAN by 13x and that of Pix2Pix by 4x while retaining a comparable performance against the full model. Our code can be available at https://github.com/SJLeo/DMAD.
PDF Accepted by IEEE Transactions on Multimedia (IEEE TMM)
论文截图
Multi-domain Unsupervised Image-to-Image Translation with Appearance Adaptive Convolution
Authors:Somi Jeong, Jiyoung Lee, Kwanghoon Sohn
Over the past few years, image-to-image (I2I) translation methods have been proposed to translate a given image into diverse outputs. Despite the impressive results, they mainly focus on the I2I translation between two domains, so the multi-domain I2I translation still remains a challenge. To address this problem, we propose a novel multi-domain unsupervised image-to-image translation (MDUIT) framework that leverages the decomposed content feature and appearance adaptive convolution to translate an image into a target appearance while preserving the given geometric content. We also exploit a contrast learning objective, which improves the disentanglement ability and effectively utilizes multi-domain image data in the training process by pairing the semantically similar images. This allows our method to learn the diverse mappings between multiple visual domains with only a single framework. We show that the proposed method produces visually diverse and plausible results in multiple domains compared to the state-of-the-art methods.
PDF ICASSP 2022
论文截图
Adverse Weather Image Translation with Asymmetric and Uncertainty-aware GAN
Authors:Jeong-gi Kwak, Youngsaeng Jin, Yuanming Li, Dongsik Yoon, Donghyeon Kim, Hanseok Ko
Adverse weather image translation belongs to the unsupervised image-to-image (I2I) translation task which aims to transfer adverse condition domain (eg, rainy night) to standard domain (eg, day). It is a challenging task because images from adverse domains have some artifacts and insufficient information. Recently, many studies employing Generative Adversarial Networks (GANs) have achieved notable success in I2I translation but there are still limitations in applying them to adverse weather enhancement. Symmetric architecture based on bidirectional cycle-consistency loss is adopted as a standard framework for unsupervised domain transfer methods. However, it can lead to inferior translation result if the two domains have imbalanced information. To address this issue, we propose a novel GAN model, i.e., AU-GAN, which has an asymmetric architecture for adverse domain translation. We insert a proposed feature transfer network (${T}$-net) in only a normal domain generator (i.e., rainy night-> day) to enhance encoded features of the adverse domain image. In addition, we introduce asymmetric feature matching for disentanglement of encoded features. Finally, we propose uncertainty-aware cycle-consistency loss to address the regional uncertainty of a cyclic reconstructed image. We demonstrate the effectiveness of our method by qualitative and quantitative comparisons with state-of-the-art models. Codes are available at https://github.com/jgkwak95/AU-GAN.
PDF BMVC 2021, codes are available in here: https://github.com/jgkwak95/AU-GAN
论文截图
OVE6D: Object Viewpoint Encoding for Depth-based 6D Object Pose Estimation
Authors:Dingding Cai, Janne Heikkilä, Esa Rahtu
This paper proposes a universal framework, called OVE6D, for model-based 6D object pose estimation from a single depth image and a target object mask. Our model is trained using purely synthetic data rendered from ShapeNet, and, unlike most of the existing methods, it generalizes well on new real-world objects without any fine-tuning. We achieve this by decomposing the 6D pose into viewpoint, in-plane rotation around the camera optical axis and translation, and introducing novel lightweight modules for estimating each component in a cascaded manner. The resulting network contains less than 4M parameters while demonstrating excellent performance on the challenging T-LESS and Occluded LINEMOD datasets without any dataset-specific training. We show that OVE6D outperforms some contemporary deep learning-based pose estimation methods specifically trained for individual objects or datasets with real-world training data. The implementation and the pre-trained model will be made publicly available.
PDF
论文截图
Optimal Transport-based Graph Matching for 3D retinal OCT image registration
Authors:Xin Tian, Nantheera Anantrasirichai, Lindsay Nicholson, Alin Achim
Registration of longitudinal optical coherence tomography (OCT) images assists disease monitoring and is essential in image fusion applications. Mouse retinal OCT images are often collected for longitudinal study of eye disease models such as uveitis, but their quality is often poor compared with human imaging. This paper presents a novel but efficient framework involving an optimal transport based graph matching (OT-GM) method for 3D mouse OCT image registration. We first perform registration of fundus-like images obtained by projecting all b-scans of a volume on a plane orthogonal to them, hereafter referred to as the x-y plane. We introduce Adaptive Weighted Vessel Graph Descriptors (AWVGD) and 3D Cube Descriptors (CD) to identify the correspondence between nodes of graphs extracted from segmented vessels within the OCT projection images. The AWVGD comprises scaling, translation and rotation, which are computationally efficient, whereas CD exploits 3D spatial and frequency domain information. The OT-GM method subsequently performs the correct alignment in the x-y plane. Finally, registration along the direction orthogonal to the x-y plane (the z-direction) is guided by the segmentation of two important anatomical features peculiar to mouse b-scans, the Internal Limiting Membrane (ILM) and the hyaloid remnant (HR). Both subjective and objective evaluation results demonstrate that our framework outperforms other well-established methods on mouse OCT images within a reasonable execution time.
PDF
论文截图
Multimodal Image-to-Image Translation via a Single Generative Adversarial Network
Authors:Shihua Huang, Cheng He, Ran Cheng
Despite significant advances in image-to-image (I2I) translation with generative adversarial networks (GANs), it remains challenging to effectively translate an image to a set of diverse images in multiple target domains using a pair of generators and discriminators. Existing multimodal I2I translation methods adopt multiple domain-specific content encoders for different domains, where each domain-specific content encoder is trained with images from the same domain only. Nevertheless, we argue that the content (domain-invariance) features should be learned from images among all of the domains. Consequently, each domain-specific content encoder of existing schemes fails to extract the domain-invariant features efficiently. To address this issue, we present a flexible and general SoloGAN model for efficient multimodal I2I translation among multiple domains with unpaired data. In contrast to existing methods, the SoloGAN algorithm uses a single projection discriminator with an additional auxiliary classifier and shares the encoder and generator for all domains. As such, the SoloGAN model can be trained effectively with images from all domains so that the domain-invariance content representation can be efficiently extracted. Qualitative and quantitative results over a wide range of datasets against several counterparts and variants of the SoloGAN model demonstrate the merits of the method, especially for challenging I2I translation tasks, i.e. tasks that involve extreme shape variations or need to keep the complex backgrounds unchanged after translations. Furthermore, we demonstrate the contribution of each component using ablation studies.
PDF pages 13, 15 figures
论文截图
Image-to-Image Translation-based Data Augmentation for Robust EV Charging Inlet Detection
Authors:Yeonjun Bang, Yeejin Lee, Byeongkeun Kang
This work addresses the task of electric vehicle (EV) charging inlet detection for autonomous EV charging robots. Recently, automated EV charging systems have received huge attention to improve users’ experience and to efficiently utilize charging infrastructures and parking lots. However, most related works have focused on system design, robot control, planning, and manipulation. Towards robust EV charging inlet detection, we propose a new dataset (EVCI dataset) and a novel data augmentation method that is based on image-to-image translation where typical image-to-image translation methods synthesize a new image in a different domain given an image. To the best of our knowledge, the EVCI dataset is the first EV charging inlet dataset. For the data augmentation method, we focus on being able to control synthesized images’ captured environments (e.g., time, lighting) in an intuitive way. To achieve this, we first propose the environment guide vector that humans can intuitively interpret. We then propose a novel image-to-image translation network that translates a given image towards the environment described by the vector. Accordingly, it aims to synthesize a new image that has the same content as the given image while looking like captured in the provided environment by the environment guide vector. Lastly, we train a detection method using the augmented dataset. Through experiments on the EVCI dataset, we demonstrate that the proposed method outperforms the state-of-the-art methods. We also show that the proposed method is able to control synthesized images using an image and environment guide vectors.
PDF 8 pages
论文截图
Relational Surrogate Loss Learning
Authors:Tao Huang, Zekang Li, Hua Lu, Yong Shan, Shusheng Yang, Yang Feng, Fei Wang, Shan You, Chang Xu
Evaluation metrics in machine learning are often hardly taken as loss functions, as they could be non-differentiable and non-decomposable, e.g., average precision and F1 score. This paper aims to address this problem by revisiting the surrogate loss learning, where a deep neural network is employed to approximate the evaluation metrics. Instead of pursuing an exact recovery of the evaluation metric through a deep neural network, we are reminded of the purpose of the existence of these evaluation metrics, which is to distinguish whether one model is better or worse than another. In this paper, we show that directly maintaining the relation of models between surrogate losses and metrics suffices, and propose a rank correlation-based optimization method to maximize this relation and learn surrogate losses. Compared to previous works, our method is much easier to optimize and enjoys significant efficiency and performance gains. Extensive experiments show that our method achieves improvements on various tasks including image classification and neural machine translation, and even outperforms state-of-the-art methods on human pose estimation and machine reading comprehension tasks. Code is available at: https://github.com/hunto/ReLoss.
PDF Accepted to ICLR 2022
论文截图
Paired Image to Image Translation for Strikethrough Removal From Handwritten Words
Authors:Raphaela Heil, Ekta Vats, Anders Hast
Transcribing struck-through, handwritten words, for example for the purpose of genetic criticism, can pose a challenge to both humans and machines, due to the obstructive properties of the superimposed strokes. This paper investigates the use of paired image to image translation approaches to remove strikethrough strokes from handwritten words. Four different neural network architectures are examined, ranging from a few simple convolutional layers to deeper ones, employing Dense blocks. Experimental results, obtained from one synthetic and one genuine paired strikethrough dataset, confirm that the proposed paired models outperform the CycleGAN-based state of the art, while using less than a sixth of the trainable parameters.
PDF under review at DAS2022
论文截图
PnP-DETR: Towards Efficient Visual Analysis with Transformers
Authors:Tao Wang, Li Yuan, Yunpeng Chen, Jiashi Feng, Shuicheng Yan
Recently, DETR pioneered the solution of vision tasks with transformers, it directly translates the image feature map into the object detection result. Though effective, translating the full feature map can be costly due to redundant computation on some area like the background. In this work, we encapsulate the idea of reducing spatial redundancy into a novel poll and pool (PnP) sampling module, with which we build an end-to-end PnP-DETR architecture that adaptively allocates its computation spatially to be more efficient. Concretely, the PnP module abstracts the image feature map into fine foreground object feature vectors and a small number of coarse background contextual feature vectors. The transformer models information interaction within the fine-coarse feature space and translates the features into the detection result. Moreover, the PnP-augmented model can instantly achieve various desired trade-offs between performance and computation with a single model by varying the sampled feature length, without requiring to train multiple models as existing methods. Thus it offers greater flexibility for deployment in diverse scenarios with varying computation constraint. We further validate the generalizability of the PnP module on panoptic segmentation and the recent transformer-based image recognition model ViT and show consistent efficiency gain. We believe our method makes a step for efficient visual analysis with transformers, wherein spatial redundancy is commonly observed. Code will be available at \url{https://github.com/twangnh/pnp-detr}.
PDF accepted by ICCV 2021
论文截图
Radon cumulative distribution transform subspace modeling for image classification
Authors:Mohammad Shifat-E-Rabbi, Xuwang Yin, Abu Hasnat Mohammad Rubaiyat, Shiying Li, Soheil Kolouri, Akram Aldroubi, Jonathan M. Nichols, Gustavo K. Rohde
We present a new supervised image classification method applicable to a broad class of image deformation models. The method makes use of the previously described Radon Cumulative Distribution Transform (R-CDT) for image data, whose mathematical properties are exploited to express the image data in a form that is more suitable for machine learning. While certain operations such as translation, scaling, and higher-order transformations are challenging to model in native image space, we show the R-CDT can capture some of these variations and thus render the associated image classification problems easier to solve. The method — utilizing a nearest-subspace algorithm in R-CDT space — is simple to implement, non-iterative, has no hyper-parameters to tune, is computationally efficient, label efficient, and provides competitive accuracies to state-of-the-art neural networks for many types of classification problems. In addition to the test accuracy performances, we show improvements (with respect to neural network-based methods) in terms of computational efficiency (it can be implemented without the use of GPUs), number of training samples needed for training, as well as out-of-distribution generalization. The Python code for reproducing our results is available at https://github.com/rohdelab/rcdt_ns_classifier.
PDF 14 pages, 11 figures
论文截图
A Multi-scale Transformer for Medical Image Segmentation: Architectures, Model Efficiency, and Benchmarks
Authors:Yunhe Gao, Mu Zhou, Di Liu, Dimitris Metaxas
Transformers have emerged to be successful in a number of natural language processing and vision tasks, but their potential applications to medical imaging remain largely unexplored due to the unique difficulties of this field. In this study, we present UTNetV2, a simple yet powerful backbone model that combines the strengths of the convolutional neural network and Transformer for enhancing performance and efficiency in medical image segmentation. The critical design of UTNetV2 includes three innovations: (1) We used a hybrid hierarchical architecture by introducing depthwise separable convolution to projection and feed-forward network in the Transformer block, which brings local relationship modeling and desirable properties of CNNs (translation invariance) to Transformer, thus eliminate the requirement of large-scale pre-training. (2) We proposed efficient bidirectional attention (B-MHA) that reduces the quadratic computation complexity of self-attention to linear by introducing an adaptively updated semantic map. The efficient attention makes it possible to capture long-range relationship and correct the fine-grained errors in high-resolution token maps. (3) The semantic maps in the B-MHA allow us to perform semantically and spatially global multi-scale feature fusion without introducing much computational overhead. Furthermore, we provide a fair comparison codebase of CNN-based and Transformer-based on various medical image segmentation tasks to evaluate the merits and defects of both architectures. UTNetV2 demonstrated state-of-the-art performance across various settings, including large-scale datasets, small-scale datasets, 2D and 3D settings.
PDF
论文截图
Edge Augmentation for Large-Scale Sketch Recognition without Sketches
Authors:Nikos Efthymiadis, Giorgos Tolias, Ondrej Chum
This work addresses scaling up the sketch classification task into a large number of categories. Collecting sketches for training is a slow and tedious process that has so far precluded any attempts to large-scale sketch recognition. We overcome the lack of training sketch data by exploiting labeled collections of natural images that are easier to obtain. To bridge the domain gap we present a novel augmentation technique that is tailored to the task of learning sketch recognition from a training set of natural images. Randomization is introduced in the parameters of edge detection and edge selection. Natural images are translated to a pseudo-novel domain called “randomized Binary Thin Edges” (rBTE), which is used as a training domain instead of natural images. The ability to scale up is demonstrated by training CNN-based sketch recognition of more than 2.5 times larger number of categories than used previously. For this purpose, a dataset of natural images from 874 categories is constructed by combining a number of popular computer vision datasets. The categories are selected to be suitable for sketch recognition. To estimate the performance, a subset of 393 categories with sketches is also collected.
PDF
论文截图
Meta-Learning and Self-Supervised Pretraining for Real World Image Translation
Authors:Ileana Rugina, Rumen Dangovski, Mark Veillette, Pooya Khorrami, Brian Cheung, Olga Simek, Marin Soljačić
Recent advances in deep learning, in particular enabled by hardware advances and big data, have provided impressive results across a wide range of computational problems such as computer vision, natural language, or reinforcement learning. Many of these improvements are however constrained to problems with large-scale curated data-sets which require a lot of human labor to gather. Additionally, these models tend to generalize poorly under both slight distributional shifts and low-data regimes. In recent years, emerging fields such as meta-learning or self-supervised learning have been closing the gap between proof-of-concept results and real-life applications of machine learning by extending deep-learning to the semi-supervised and few-shot domains. We follow this line of work and explore spatio-temporal structure in a recently introduced image-to-image translation problem in order to: i) formulate a novel multi-task few-shot image generation benchmark and ii) explore data augmentations in contrastive pre-training for image translation downstream tasks. We present several baselines for the few-shot problem and discuss trade-offs between different approaches. Our code is available at https://github.com/irugina/meta-image-translation.
PDF 10 pages, 8 figures, 2 tables
论文截图
ISF-GAN: An Implicit Style Function for High-Resolution Image-to-Image Translation
Authors:Yahui Liu, Yajing Chen, Linchao Bao, Nicu Sebe, Bruno Lepri, Marco De Nadai
Recently, there has been an increasing interest in image editing methods that employ pre-trained unconditional image generators (e.g., StyleGAN). However, applying these methods to translate images to multiple visual domains remains challenging. Existing works do not often preserve the domain-invariant part of the image (e.g., the identity in human face translations), they do not usually handle multiple domains, or do not allow for multi-modal translations. This work proposes an implicit style function (ISF) to straightforwardly achieve multi-modal and multi-domain image-to-image translation from pre-trained unconditional generators. The ISF manipulates the semantics of an input latent code to make the image generated from it lying in the desired visual domain. Our results in human face and animal manipulations show significantly improved results over the baselines. Our model enables cost-effective multi-modal unsupervised image-to-image translations at high resolution using pre-trained unconditional GANs. The code and data are available at: \url{https://github.com/yhlleo/stylegan-mmuit}.
PDF 14 pages, 15 figures
论文截图