Attention has been proved to be an efficient mechanism to capture long-range dependencies. However, so far it has not been deployed in invertible networks. This is due to the fact that in order to make a network invertible, every component within the network needs to be a bijective transformation, but a normal attention block is not. In this paper, we propose invertible attention that can be plugged into existing invertible models. We mathematically and experimentally prove that the invertibility of an attention model can be achieved by carefully constraining its Lipschitz constant. We validate the invertibility of our invertible attention on image reconstruction task with 3 popular datasets: CIFAR-10, SVHN, and CelebA. We also show that our invertible attention achieves similar performance in comparison with normal non-invertible attention on dense prediction tasks. The code is available at https://github.com/Schwartz-Zha/InvertibleAttention
Camouflaged object detection (COD) aims to segment camouflaged objects hiding in the environment, which is challenging due to the similar appearance of camouflaged objects and their surroundings. Research in biology suggests that depth can provide useful object localization cues for camouflaged object discovery, as all the animals have 3D perception ability. However, the depth information has not been exploited for camouflaged object detection. To explore the contribution of depth for camouflage detection, we present a depth-guided camouflaged object detection network with pre-computed depth maps from existing monocular depth estimation methods. Due to the domain gap between the depth estimation dataset and our camouflaged object detection dataset, the generated depth may not be accurate enough to be directly used in our framework. We then introduce a depth quality assessment module to evaluate the quality of depth based on the model prediction from both RGB COD branch and RGB-D COD branch. During training, only high-quality depth is used to update the modal interaction module for multi-modal learning. During testing, our depth quality assessment module can effectively determine the contribution of depth and select the RGB branch or RGB-D branch for camouflage prediction. Extensive experiments on various camouflaged object detection datasets prove the effectiveness of our solution in exploring the depth information for camouflaged object detection. Our code and data is publicly available at: \url{https://github.com/JingZhang617/RGBD-COD}.
Camouflaged object detection (COD) aims to segment camouflaged objects hiding in the environment, which is challenging due to the similar appearance of camouflaged objects and their surroundings. Research in biology suggests that depth can provide useful object localization cues for camouflaged object discovery, as all the animals have 3D perception ability. However, the depth information has not been exploited for camouflaged object detection. To explore the contribution of depth for camouflage detection, we present a depth-guided camouflaged object detection network with pre-computed depth maps from existing monocular depth estimation methods. Due to the domain gap between the depth estimation dataset and our camouflaged object detection dataset, the generated depth may not be accurate enough to be directly used in our framework. We then introduce a depth quality assessment module to evaluate the quality of depth based on the model prediction from both RGB COD branch and RGB-D COD branch. During training, only high-quality depth is used to update the modal interaction module for multi-modal learning. During testing, our depth quality assessment module can effectively determine the contribution of depth and select the RGB branch or RGB-D branch for camouflage prediction. Extensive experiments on various camouflaged object detection datasets prove the effectiveness of our solution in exploring the depth information for camouflaged object detection. Our code and data is publicly available at: \url{https://github.com/JingZhang617/RGBD-COD}.
Single-image super-resolution (SR) and multi-frame SR are two ways to super resolve low-resolution images. Single-Image SR generally handles each image independently, but ignores the temporal information implied in continuing frames. Multi-frame SR is able to model the temporal dependency via capturing motion information. However, it relies on neighbouring frames which are not always available in the real world. Meanwhile, slight camera shake easily causes heavy motion blur on long-distance-shot low-resolution images. To address these problems, a Blind Motion Deblurring Super-Reslution Networks, BMDSRNet, is proposed to learn dynamic spatio-temporal information from single static motion-blurred images. Motion-blurred images are the accumulation over time during the exposure of cameras, while the proposed BMDSRNet learns the reverse process and uses three-streams to learn Bidirectional spatio-temporal information based on well designed reconstruction loss functions to recover clean high-resolution images. Extensive experiments demonstrate that the proposed BMDSRNet outperforms recent state-of-the-art methods, and has the ability to simultaneously deal with image deblurring and SR.
Visual and audio signals often coexist in natural environments, forming audio-visual events (AVEs). Given a video, we aim to localize video segments containing an AVE and identify its category. In order to learn discriminative features for a classifier, it is pivotal to identify the helpful (or positive) audio-visual segment pairs while filtering out the irrelevant ones, regardless whether they are synchronized or not. To this end, we propose a new positive sample propagation (PSP) module to discover and exploit the closely related audio-visual pairs by evaluating the relationship within every possible pair. It can be done by constructing an all-pair similarity map between each audio and visual segment, and only aggregating the features from the pairs with high similarity scores. To encourage the network to extract high correlated features for positive samples, a new audio-visual pair similarity loss is proposed. We also propose a new weighting branch to better exploit the temporal correlations in weakly supervised setting. We perform extensive experiments on the public AVE dataset and achieve new state-of-the-art accuracy in both fully and weakly supervised settings, thus verifying the effectiveness of our method.
Two-view structure-from-motion (SfM) is the cornerstone of 3D reconstruction and visual SLAM. Existing deep learning-based approaches formulate the problem by either recovering absolute pose scales from two consecutive frames or predicting a depth map from a single image, both of which are ill-posed problems. In contrast, we propose to revisit the problem of deep two-view SfM by leveraging the well-posedness of the classic pipeline. Our method consists of 1) an optical flow estimation network that predicts dense correspondences between two frames; 2) a normalized pose estimation module that computes relative camera poses from the 2D optical flow correspondences, and 3) a scale-invariant depth estimation network that leverages epipolar geometry to reduce the search space, refine the dense correspondences, and estimate relative depth maps. Extensive experiments show that our method outperforms all state-of-the-art two-view SfM methods by a clear margin on KITTI depth, KITTI VO, MVS, Scenes11, and SUN3D datasets in both relative pose and depth estimation.
Video deblurring models exploit consecutive frames to remove blurs from camera shakes and object motions. In order to utilize neighboring sharp patches, typical methods rely mainly on homography or optical flows to spatially align neighboring blurry frames. However, such explicit approaches are less effective in the presence of fast motions with large pixel displacements. In this work, we propose a novel implicit method to learn spatial correspondence among blurry frames in the feature space. To construct distant pixel correspondences, our model builds a correlation volume pyramid among all the pixel-pairs between neighboring frames. To enhance the features of the reference frame, we design a correlative aggregation module that maximizes the pixel-pair correlations with its neighbors based on the volume pyramid. Finally, we feed the aggregated features into a reconstruction module to obtain the restored frame. We design a generative adversarial paradigm to optimize the model progressively. Our proposed method is evaluated on the widely-adopted DVD dataset, along with a newly collected High-Frame-Rate (1000 fps) Dataset for Video Deblurring (HFR-DVD). Quantitative and qualitative experiments show that our model performs favorably on both datasets against previous state-of-the-art methods, confirming the benefit of modeling all-range spatial correspondence for video deblurring.
A depth map can be represented by a set of learned bases and can be efficiently solved in a closed form solution. However, one issue with this method is that it may create artifacts when colour boundaries are inconsistent with depth boundaries. In fact, this is very common in a natural image. To address this issue, we enforce a more strict model in depth recovery: a piece-wise planar model. More specifically, we represent the desired depth map as a collection of 3D planar and the reconstruction problem is formulated as the optimization of planar parameters. Such a problem can be formulated as a continuous CRF optimization problem and can be solved through particle based method (MP-PBP) \cite{Yamaguchi14}. Extensive experimental evaluations on the KITTI visual odometry dataset show that our proposed methods own high resistance to false object boundaries and can generate useful and visually pleasant 3D point clouds.