论文检索

Yuxuan Liu, Haizhou Ai, Junliang Xing, Xuri Li, Xiaoyi Wang, Pin Tao

Multiple views play a vital role in 3D pose estimation tasks. Ideally, multi-view 3D pose estimation tasks should directly utilize naturally collected videos for pose estimation. However, due to the constraints of video synchronization, existing methods often use expensive hardware devices to synchronize the initiation of cameras, which restricts most 3D pose collection scenarios to indoor settings. Some recent works learn deep neural networks to align desynchronized datasets derived from synchronized cameras and can only produce frame-level accuracy. For fractional frame video synchronization, this work proposes an Inter-Frame and Intra-Frame Desynchronized Dataset (IFID), which labels fractional time intervals between two video clips. IFID is the first dataset that annotates inter-frame and intra-frame intervals, with a total of 382,500 video clips annotated, making it the largest dataset to date. We also develop a novel model based on the Transformer architecture, named InSynFormer, for synchronizing inter-frame and intra-frame. Extensive experimental evaluations demonstrate its promising performance. The dataset and source code of the model are available at https://github.com/yuxuan-cser/InSynFormer.

Yutong Liu, Haijiang Zhu, Mengting Liu, Huaiyuan Yu, Zihan Chen, Jie Gao

Medical image segmentation methods based on deep learning network are mainly divided into CNN and Transformer. However, CNN struggles to capture long-distance dependencies, while Transformer suffers from high computational complexity and poor local feature learning. To efficiently extract and fuse local features and long-range dependencies, this paper proposes Rolling-Unet, which is a CNN model combined with MLP. Specifically, we propose the core R-MLP module, which is responsible for learning the long-distance dependency in a single direction of the whole image. By controlling and combining R-MLP modules in different directions, OR-MLP and DOR-MLP modules are formed to capture long-distance dependencies in multiple directions. Further, Lo2 block is proposed to encode both local context information and long-distance dependencies without excessive computational burden. Lo2 block has the same parameter size and computational complexity as a 3×3 convolution. The experimental results on four public datasets show that Rolling-Unet achieves superior performance compared to the state-of-the-art methods.

Yuhao Liu, Zhanghan Ke, Ke Xu, Fang Liu, Zhenwei Wang, Rynson W.H. Lau

Removing shadows requires an understanding of both lighting conditions and object textures in a scene. Existing methods typically learn pixel-level color mappings between shadow and non-shadow images, in which the joint modeling of lighting and object textures is implicit and inadequate. We observe that in a shadow region, the degradation degree of object textures depends on the local illumination, while simply enhancing the local illumination cannot fully recover the attenuated textures. Based on this observation, we propose to condition the restoration of attenuated textures on the corrected local lighting in the shadow region. Specifically, We first design a shadow-aware decomposition network to estimate the illumination and reflectance layers of shadow regions explicitly. We then propose a novel bilateral correction network to recast the lighting of shadow regions in the illumination layer via a novel local lighting correction module, and to restore the textures conditioned on the corrected illumination layer via a novel illumination-guided texture restoration module. We further annotate pixel-wise shadow masks for the public SRD dataset, which originally contains only image pairs. Experiments on three benchmarks show that our method outperforms existing state-of-the-art shadow removal methods. Project page in: yuhaoliu7456.github.io/RRL-Net.

Yuchun Liu, Benjamin Planche, Meng Zheng, Zhongpai Gao, Pierre Sibut-Bourde, Fan Yang, Terrence Chen, Ziyan Wu

Deep implicit functions (DIFs) have emerged as a potent and articulate means of representing 3D shapes. However, methods modeling object categories or non-rigid entities have mainly focused on single-object scenarios. In this work, we propose MODIF, a multi-object deep implicit function that jointly learns the deformation fields and instance-specific latent codes for multiple objects at once. Our emphasis is on non-rigid, non-interpenetrating entities such as organs. To effectively capture the interrelation between these entities and ensure precise, collision-free representations, our approach facilitates signaling between category-specific fields to adequately rectify shapes. We also introduce novel inter-object supervision: an attraction-repulsion loss is formulated to refine contact regions between objects. Our approach is demonstrated on various medical benchmarks, involving modeling different groups of intricate anatomical entities. Experimental results illustrate that our model can proficiently learn the shape representation of each organ and their relations to others, to the point that shapes missing from unseen instances can be consistently recovered by our method. Finally, MODIF can also propagate semantic information throughout the population via accurate point correspondences.

Yongxu Liu, Yinghui Quan, Guoyao Xiao, Aobo Li, Jinjian Wu

Quality assessment of images and videos emphasizes both local details and global semantics, whereas general data sampling methods (e.g., resizing, cropping or grid-based fragment) fail to catch them simultaneously. To address the deficiency, current approaches have to adopt multi-branch models and take as input the multi-resolution data, which burdens the model complexity. In this work, instead of stacking up models, a more elegant data sampling method (named as SAMA, scaling and masking) is explored, which compacts both the local and global content in a regular input size. The basic idea is to scale the data into a pyramid first, and reduce the pyramid into a regular data dimension with a masking strategy. Benefiting from the spatial and temporal redundancy in images and videos, the processed data maintains the multi-scale characteristics with a regular input size, thus can be processed by a single-branch model. We verify the sampling method in image and video quality assessment. Experiments show that our sampling method can improve the performance of current single-branch models significantly, and achieves competitive performance to the multi-branch models without extra model complexity. The source code will be available at https://github.com/Sissuire/SAMA.

Yixin Liu, Kaidi Xu, Xun Chen, Lichao Sun

The open sourcing of large amounts of image data promotes the development of deep learning techniques. Along with this comes the privacy risk of these image datasets being exploited by unauthorized third parties to train deep learning models for commercial or illegal purposes. To avoid the abuse of data, a poisoning-based technique, "unlearnable example", has been proposed to significantly degrade the generalization performance of models by adding imperceptible noise to the data. To further enhance its robustness against adversarial training, existing works leverage iterative adversarial training on both the defensive noise and the surrogate model. However, it still remains unknown whether the robustness of unlearnable examples primarily comes from the effect of enhancement in the surrogate model or the defensive noise. Observing that simply removing the adversarial perturbation on the training process of the defensive noise can improve the performance of robust unlearnable examples, we identify that solely the surrogate model's robustness contributes to the performance. Furthermore, we found a negative correlation exists between the robustness of defensive noise and the protection performance, indicating defensive noise's instability issue. Motivated by this, to further boost the robust unlearnable example, we introduce Stable Error-Minimizing noise (SEM), which trains the defensive noise against random perturbation instead of the time-consuming adversarial perturbation to improve the stability of defensive noise. Through comprehensive experiments, we demonstrate that SEM achieves a new state-of-the-art performance on CIFAR-10, CIFAR-100, and ImageNet Subset regarding both effectiveness and efficiency.

Yitian Liu, Zhouhui Lian

Few-shot font generation, especially for Chinese calligraphy fonts, is a challenging and ongoing problem. With the help of prior knowledge that is mainly based on glyph consistency assumptions, some recently proposed methods can synthesize high-quality Chinese glyph images. However, glyphs in calligraphy font styles often do not meet these assumptions. To address this problem, we propose a novel model, DeepCalliFont, for few-shot Chinese calligraphy font synthesis by integrating dual-modality generative models. Specifically, the proposed model consists of image synthesis and sequence generation branches, generating consistent results via a dual-modality representation learning strategy. The two modalities (i.e., glyph images and writing sequences) are properly integrated using a feature recombination module and a rasterization loss function. Furthermore, a new pre-training strategy is adopted to improve the performance by exploiting large amounts of uni-modality data. Both qualitative and quantitative experiments have been conducted to demonstrate the superiority of our method to other state-of-the-art approaches in the task of few-shot Chinese calligraphy font synthesis. The source code can be found at https://github.com/lsflyt-pku/DeepCalliFont.

Xiulong Liu, Sudipta Paul, Moitreya Chatterjee, Anoop Cherian

Audio-visual navigation of an agent towards locating an audio goal is a challenging task especially when the audio is sporadic or the environment is noisy. In this paper, we present CAVEN, a Conversation-based Audio-Visual Embodied Navigation framework in which the agent may interact with a human/oracle for solving the task of navigating to an audio goal. Specifically, CAVEN is modeled as a budget-aware partially observable semi-Markov decision process that implicitly learns the uncertainty in the audio-based navigation policy to decide when and how the agent may interact with the oracle. Our CAVEN agent can engage in fully-bidirectional natural language conversations by producing relevant questions and interpret free-form, potentially noisy responses from the oracle based on the audio-visual context. To enable such a capability, CAVEN is equipped with: i) a trajectory forecasting network that is grounded in audio-visual cues to produce a potential trajectory to the estimated goal, and (ii) a natural language based question generation and reasoning network to pose an interactive question to the oracle or interpret the oracle's response to produce navigation instructions. To train the interactive modules, we present a large scale dataset: AVN-Instruct, based on the Landmark-RxR dataset. To substantiate the usefulness of conversations, we present experiments on the benchmark audio-goal task using the SoundSpaces simulator under various noisy settings. Our results reveal that our fully-conversational approach leads to nearly an order-of-magnitude improvement in success rate, especially in localizing new sound sources and against methods that use only uni-directional interaction.

Xingyu Liu, Pengfei Ren, Yuanyuan Gao, Jingyu Wang, Haifeng Sun, Qi Qi, Zirui Zhuang, Jianxin Liao

Previous 3D hand pose estimation methods primarily rely on a single modality, either RGB or depth, and the comprehensive utilization of the dual modalities has not been extensively explored. RGB and depth data provide complementary information and thus can be fused to enhance the robustness of 3D hand pose estimation. However, there exist two problems for applying existing fusion methods in 3D hand pose estimation: redundancy of dense feature fusion and ambiguity of visual features. First, pixel-wise feature interactions introduce high computational costs and ineffective calculations of invalid pixels. Second, visual features suffer from ambiguity due to color and texture similarities, as well as depth holes and noise caused by frequent hand movements, which interferes with modeling cross-modal correlations. In this paper, we propose Keypoint-Fusion for RGB-D based 3D hand pose estimation, which leverages the unique advantages of dual modalities to mutually eliminate the feature ambiguity, and performs cross-modal feature fusion in a more efficient way. Specifically, we focus cross-modal fusion on sparse yet informative spatial regions (i.e. keypoints). Meanwhile, by explicitly extracting relatively more reliable information as disambiguation evidence, depth modality provides 3D geometric information for RGB feature pixels, and RGB modality complements the precise edge information lost due to the depth noise. Keypoint-Fusion achieves state-of-the-art performance on two challenging hand datasets, significantly decreasing the error compared with previous single-modal methods.

Xingyu Liu, Xu Cheng, Haoyu Chen, Hao Yu, Guoying Zhao

Sketch re-identification (Re-ID) seeks to match pedestrians' photos from surveillance videos with corresponding sketches. However, we observe that existing works still have two critical limitations: (i) cross- and intra-modality discrepancies hinder the extraction of modality-shared features, (ii) standard triplet loss fails to constrain latent feature distribution in each modality with inadequate samples. To overcome the above issues, we propose a differentiable auxiliary learning network (DALNet) to explore a robust auxiliary modality for Sketch Re-ID. Specifically, for (i) we construct an auxiliary modality by using a dynamic auxiliary generator (DAG) to bridge the gap between sketch and photo modalities. The auxiliary modality highlights the described person in photos to mitigate background clutter and learns sketch style through style refinement. Moreover, a modality interactive attention module (MIA) is presented to align the features and learn the invariant patterns of two modalities by auxiliary modality. To address (ii), we propose a multi-modality collaborative learning scheme (MMCL) to align the latent distribution of three modalities. An intra-modality circle loss in MMCL brings learned global and modality-shared features of the same identity closer in the case of insufficient samples within each modality. Extensive experiments verify the superior performance of our DALNet over the state-of-the-art methods for Sketch Re-ID, and the generalization in sketch-based image retrieval and sketch-photo face recognition tasks.

Xiaohui Liu, Zhilu Zhang, Xiaohe Wu, Chaoyu Feng, Xiaotao Wang, Lei Lei, Wangmeng Zuo

Real-world image de-weathering aims at removing various undesirable weather-related artifacts. Owing to the impossibility of capturing image pairs concurrently, existing real-world de-weathering datasets often exhibit inconsistent illumination, position, and textures between the ground-truth images and the input degraded images, resulting in imperfect supervision. Such non-ideal supervision negatively affects the training process of learning-based de-weathering methods. In this work, we attempt to address the problem with a unified solution for various inconsistencies. Specifically, inspired by information bottleneck theory, we first develop a Consistent Label Constructor (CLC) to generate a pseudo-label as consistent as possible with the input degraded image while removing most weather-related degradation. In particular, multiple adjacent frames of the current input are also fed into CLC to enhance the pseudo-label. Then we combine the original imperfect labels and pseudo-labels to jointly supervise the de-weathering model by the proposed Information Allocation Strategy (IAS). During testing, only the de-weathering model is used for inference. Experiments on two real-world de-weathering datasets show that our method helps existing de-weathering models achieve better performance. Code is available at https://github.com/1180300419/imperfect-deweathering.

Wensi Liu, Xiao-Yu Tang, Chong Yang, Chunjie Yang

Semantic segmentation is one of the tasks concerned in the field of computer vision. However, the cost of capturing large numbers of pixel-level annotations is expensive. Semi-supervised learning can utilize labeled and unlabeled data, providing new ideas for solving the problem of insufficient labeled data. In this work, we propose a data-reliability weighted multi-phase learning method for semi-supervised segmentation (RWMS). Under the framework of self-training, we train two different teacher models to evaluate the reliability of pseudo labels. By selecting reliable data at the image level and reweighting pseudo labels at the pixel level, multi-phase training is guided to focus on more reliable knowledge. Besides, we also inject strong data augmentations on unlabeled images while training. Through extensive experiments, we demonstrate that our method performs remarkably well compared to baseline methods and substantially outperforms them, more than 3% on VOC and Cityscapes.

Wang Liu, Wei Gao, Xingming Mu

Recent years have witnessed the success of deep learning methods in quality enhancement of compressed point cloud. However, existing methods focus on geometry and attribute enhancement of single-frame point cloud. This paper proposes a novel compressed quality enhancement method for dynamic point cloud (DAE-MP). Specifically, we propose a fast inter-frame motion prediction module (IFMP) to explicitly estimate motion displacement and achieve inter-frame feature alignment. To maintain motion continuity between consecutive frames, we propose a motion consistency loss for supervised learning. Furthermore, a frequency component separation and fusion module is designed to extract rich frequency features adaptively. To the best of our knowledge, the proposed method is the first deep learning-based work to enhance the quality for compressed dynamic point cloud. Experimental results show that the proposed method can greatly improve the quality of compressed dynamic point cloud and provide a fast and efficient motion prediction plug-in for large-scale point cloud. For dynamic point cloud attribute with severely compressed artifact, our proposed DAE-MP method achieves up to 0.52dB (PSNR) performance gain. Moreover, the proposed IFMP module has a certain real-time processing ability for calculating the motion offset between dynamic point cloud frame.

Siqi Liu, Yong-Lu Li, Zhou Fang, Xinpeng Liu, Yang You, Cewu Lu

Embedding Human and Articulated Object Interaction (HAOI) in 3D is an important direction for a deeper human activity understanding. Different from previous works that use parametric and CAD models to represent humans and objects, in this work, we propose a novel 3D geometric primitive-based language to encode both humans and objects. Given our new paradigm, humans and objects are all compositions of primitives instead of heterogeneous entities. Thus, mutual information learning may be achieved between the limited 3D data of humans and different object categories. Moreover, considering the simplicity of the expression and the richness of the information it contains, we choose the superquadric as the primitive representation. To explore an effective embedding of HAOI for the machine, we build a new benchmark on 3D HAOI consisting of primitives together with their images and propose a task requiring machines to recover 3D HAOI using primitives from images. Moreover, we propose a baseline of single-view 3D reconstruction on HAOI. We believe this primitive-based 3D HAOI representation would pave the way for 3D HAOI studies. Our code and data are available at https://mvig-rhos.com/p3haoi.

Ruixin Liu, Zejian Yuan

High-definition (HD) map construction requires a comprehensive understanding of traffic environments, encompassing centimeter-level localization and rich semantic information. Previous works face challenges in redundant point representation or high-complexity curve modeling. In this paper, we present a flexible yet effective map element detector that synthesizes hierarchical information with a compact Douglas-Peucker (DP) point representation in a transformer architecture for robust and reliable predictions. Specifically, our proposed representation approximates class-agnostic map elements with DP points, which are sparsely located in crucial positions of structures and can get rid of redundancy and complexity. Besides, we design a position constraint with uncertainty to avoid potential ambiguities. Moreover, pairwise-point shape matching constraints are proposed to balance local structural information of different scales. Experiments on the public nuScenes dataset demonstrate that our method overwhelms current SOTAs. Extensive ablation studies validate each component of our methods. Codes will be released at https://github.com/sweety121/DPFormer.

Ruicong Liu, Feng Lu

Gaze estimation has become a subject of growing interest in recent research. Most of the current methods rely on single-view facial images as input. Yet, it is hard for these approaches to handle large head angles, leading to potential inaccuracies in the estimation. To address this issue, adding a second-view camera can help better capture eye appearance. However, existing multi-view methods have two limitations. 1) They require multi-view annotations for training, which are expensive. 2) More importantly, during testing, the exact positions of the multiple cameras must be known and match those used in training, which limits the application scenario. To address these challenges, we propose a novel 1-view-to-2-views (1-to-2 views) adaptation solution in this paper, the Unsupervised 1-to-2 Views Adaptation framework for Gaze estimation (UVAGaze). Our method adapts a traditional single-view gaze estimator for flexibly placed dual cameras. Here, the "flexibly" means we place the dual cameras in arbitrary places regardless of the training data, without knowing their extrinsic parameters. Specifically, the UVAGaze builds a dual-view mutual supervision adaptation strategy, which takes advantage of the intrinsic consistency of gaze directions between both views. In this way, our method can not only benefit from common single-view pre-training, but also achieve more advanced dual-view gaze estimation. The experimental results show that a single-view estimator, when adapted for dual views, can achieve much higher accuracy, especially in cross-dataset settings, with a substantial improvement of 47.0%. Project page: https://github.com/MickeyLLG/UVAGaze.

Liu Liu, Anran Huang, Qi Wu, Dan Guo, Xun Yang, Meng Wang

Our life is populated with articulated objects. Current category-level articulation estimation works largely focus on predicting part-level 6D poses on static point cloud observations. In this paper, we tackle the problem of category-level online robust and real-time 6D pose tracking of articulated objects, where we propose KPA-Tracker, a novel 3D KeyPoint based Articulated object pose Tracker. Given an RGB-D image or a partial point cloud at the current frame as well as the estimated per-part 6D poses from the last frame, our KPA-Tracker can effectively update the poses with learned 3D keypoints between the adjacent frames. Specifically, we first canonicalize the input point cloud and formulate the pose tracking as an inter-frame pose increment estimation task. To learn consistent and separate 3D keypoints for every rigid part, we build KPA-Gen that outputs the high-quality ordered 3D keypoints in an unsupervised manner. During pose tracking on the whole video, we further propose a keypoint-based articulation tracking algorithm that mines keyframes as reference for accurate pose updating. We provide extensive experiments on validating our KPA-Tracker on various datasets ranging from synthetic point cloud observation to real-world scenarios, which demonstrates the superior performance and robustness of the KPA-Tracker. We believe that our work has the potential to be applied in many fields including robotics, embodied intelligence and augmented reality. All the datasets and codes are available at https://github.com/hhhhhar/KPA-Tracker.

Lijun Liu, Rui Wang, Yuan Wang, Lihua Jing, Chuan Wang

Open-Set Recognition (OSR) aims to accurately identify known classes while effectively rejecting unknown classes to guarantee reliability. Most existing OSR methods focus on learning in the spatial domain, where subtle texture and global structure are potentially intertwined. Empirical studies have shown that DNNs trained in the original spatial domain are inclined to over-perceive subtle texture. The biased semantic perception could lead to catastrophic over-confidence when predicting both known and unknown classes. To this end, we propose an innovative approach by decomposing the spatial domain to the frequency domain to separately consider global (low-frequency) and subtle (high-frequency) information, named Frequency Shuffling and Enhancement (FreSH). To alleviate the overfitting of subtle texture, we introduce the High-Frequency Shuffling (HFS) strategy that generates diverse high-frequency information and promotes the capture of low-frequency invariance. Moreover, to enhance the perception of global structure, we propose the Low-Frequency Residual (LFR) learning procedure that constructs a composite feature space, integrating low-frequency and original spatial features. Experiments on various benchmarks demonstrate that the proposed FreSH consistently trumps the state-of-the-arts by a considerable margin.

Jun Liu, Jiantao Zhou, Jiandian Zeng, Jinyu Tian

This work investigates efficient score-based black-box adversarial attacks with high Attack Success Rate (ASR) and good generalizability. We design a novel attack method based on a Disentangled Feature space, called DifAttack, which differs significantly from the existing ones operating over the entire feature space. Specifically, DifAttack firstly disentangles an image's latent feature into an adversarial feature and a visual feature, where the former dominates the adversarial capability of an image, while the latter largely determines its visual appearance. We train an autoencoder for the disentanglement by using pairs of clean images and their Adversarial Examples (AEs) generated from available surrogate models via white-box attack methods. Eventually, DifAttack iteratively optimizes the adversarial feature according to the query feedback from the victim model until a successful AE is generated, while keeping the visual feature unaltered. In addition, due to the avoidance of using surrogate models' gradient information when optimizing AEs for black-box models, our proposed DifAttack inherently possesses better attack capability in the open-set scenario, where the training dataset of the victim model is unknown. Extensive experimental results demonstrate that our method achieves significant improvements in ASR and query efficiency simultaneously, especially in the targeted attack and open-set scenarios. The code is available The code is available at https://github.com/csjunjun/DifAttack.git.

Jinxiu Liu, Qi Liu

Image generation tasks have achieved remarkable performance using large-scale diffusion models. However, these models are limited to capturing the abstract relations (viz., interactions excluding positional relations) among multiple entities of complex scene graphs. Two main problems exist: 1) fail to depict more concise and accurate interactions via abstract relations; 2) fail to generate complete entities. To address that, we propose a novel Relation-aware Compositional Contrastive Control Diffusion method, dubbed as R3CD, that leverages large-scale diffusion models to learn abstract interactions from scene graphs. Herein, a scene graph transformer based on node and edge encoding is first designed to perceive both local and global information from input scene graphs, whose embeddings are initialized by a T5 model. Then a joint contrastive loss based on attention maps and denoising steps is developed to control the diffusion model to understand and further generate images, whose spatial structures and interaction features are consistent with a priori relation. Extensive experiments are conducted on two datasets: Visual Genome and COCO-Stuff, and demonstrate that the proposal outperforms existing models both in quantitative and qualitative metrics to generate more realistic and diverse images according to different scene graph specifications.