Recently, learning-based algorithms have shown impressive performance in underwater image enhancement. Most of them resort to training on synthetic data and obtain outstanding performance. However, these deep methods ignore the significant domain gap between the synthetic and real data (i.e., inter-domain gap), and thus the models trained on synthetic data often fail to generalize well to real-world underwater scenarios. Moreover, the complex and changeable underwater environment also causes a great distribution gap among the real data itself (i.e., intra-domain gap). However, almost no research focuses on this problem and thus their techniques often produce visually unpleasing artifacts and color distortions on various real images. Motivated by these observations, we propose a novel Two-phase Underwater Domain Adaptation network (TUDA) to simultaneously minimize the inter-domain and intra-domain gap. Concretely, in the first phase, a new triple-alignment network is designed, including a translation part for enhancing realism of input images, followed by a task-oriented enhancement part. With performing image-level, feature-level and output-level adaptation in these two parts through jointly adversarial learning, the network can better build invariance across domains and thus bridging the inter-domain gap. In the second phase, an easy-hard classification of real data according to the assessed quality of enhanced images is performed, in which a new rank-based underwater quality assessment method is embedded. By leveraging implicit quality information learned from rankings, this method can more accurately assess the perceptual quality of enhanced images. Using pseudo labels from the easy part, an easy-hard adaptation technique is then conducted to effectively decrease the intra-domain gap between easy and hard samples. Extensive experimental results demonstrate that the proposed TUDA is significantly superior to existing works in terms of both visual quality and quantitative metrics.

Quatree with nested multi-type tree (QTMT) partition structure is an efficient improvement in versatile video coding (VVC) over the quadtree structure in the advanced high efficiency video coding (HEVC) standard. With the exception of the recursive quadtree partition structure, recursive multi-type tree partition is applied to each leaf node, which generates more flexible block sizes. Besides, intra prediction modes are extended from 35 to 67 so as to satisfy various texture patterns. These newly developed techniques achieve high coding efficiency, but also result in very high computational complexity. To tackle this problem, we propose a fast intra coding algorithm consisting of low complexity coding tree units (CTU) structure decision and fast intra mode decision in this paper. The contributions of the proposed algorithm lie in the following aspects: 1) the new block size and coding mode distribution features are firstly explored for a reasonable fast coding scheme; 2) a novel fast QTMT partition decision framework is developed, which can determine the partition decision on both quadtree and multi-type tree with a novel cascade decision structure; 3) fast intra mode decision with gradient descent search is introduced, while the best initial search point and search step are also investigated in this paper. Simulation results show that the complexity reduction of the proposed algorithm is up to 70% compared to VVC reference software (VTM), and averagely 63% encoding time saving is achieved with 1.93% BDBR increasing. Such results demonstrate that our method yields a superior performance in terms of computational complexity and compression quality compared to the state-of-the-art methods.

To achieve higher coding efficiency, the latest Versatile Video Coding (VVC) standard adopts a series of new intra coding techniques, including the quadtree plus multi-type tree (QTMT), intra sub-partitions (ISP) and intra block copy (IBC). However, this makes the intra coding more complicated, as VVC needs to traverse all prediction modes and partition types of QTMT to find the optimal combination. In this paper, we propose a fast algorithm for VVC from two aspects of mode selection and prediction terminating to reduce coding complexity. For the mode selection, adaptive mode pruning (AMP) is proposed to remove non-promising modes. First, since the newly introduced modes (IBC and ISP) are not effective for all blocks, learning-based classifiers are designed to remove them intelligently. Second, for normal modes, an ensemble decision strategy is proposed to sort the candidate modes and increase the probability of being the optimal mode for the first few candidates; thus, we can remove redundant candidates more efficiently. In terms of prediction terminating, we find that different optimal modes of current depth level lead to different termination probabilities of remaining intra predictions. Therefore, mode-dependent termination (MDT) is proposed to select an appropriate model through the optimal mode and terminate unnecessary intra predictions of remaining depth levels. The proposed algorithm is implemented on VVC test model, and simulation results show that it can achieve 51% $\sim$ 53% time savings with only 0.93% $\sim$ 1.08% BDBR increases.

Forward-looking sonar (FLS) imagery system plays a significant role in oceanic object recognition and detection since it can overcome the limitation of lighting conditions and reflect the real situation of the underwater environment. However, object detection algorithms for FLS images remain challenging for two main reasons: 1) The noise caused by the coherent characteristic of the scattering phenomenon impairs the detector capture of target information; 2) The scene prior based on the uneven target scale distribution is generally neglected, which leads to the detector generating redundant anchors and slows down detection efficiency. Confronting such challenges, this paper characterizes the noise and the uneven target scale distribution in FLS images as multiplicative speckle noise and scene prior, respectively. Therefore, we propose a novel underwater FLS image detection network, namely UFIDNet, to further improve detection performance by considering speckle noise reduction and scene prior in FLS images. More specifically, a speckle reduction auxiliary branch (SRAB) is designed to introduce additional despeckled supervision information to encourage the feature extractor to produce clean features and share them with the detection pipeline during the training phase. In particular, the noise distribution of FLS images is excavated for synthetic dataset construction and Despeckle Network (DSN) design to obtain despeckled supervision images. In addition, a feature selection strategy (FSS) embedded in detection branch is designed to screen out feature levels that do not match the target size, thus significantly reducing the generation of redundant anchors and improving detection speed. Experimental results show that our UFIDNet achieves 70.5% and 47.3% average precision (AP), 81.3% and 54.6% average recall (AR _max=10 ), 27.0 and 26.1 FPS on two real FLS datasets respectively, outperforming many state-of-the-art general detectors and sonar image detectors.

The captured underwater images suffer from color cast and haze effect caused by absorption and scattering. These interdependent phenomena jointly degrade images, resulting in failure of autonomous machines to recognize image contents. Most existing learning-based methods for underwater image enhancement (UIE) treat the degraded process as a whole and ignore the interaction between color correction and dehazing. Thus, they often obtain unnatural results. To this end, we propose a novel joint network to optimize the results of color correction and dehazing in multiple iterations. Firstly, a novel triplet-based color correction module is proposed to obtain color-balanced images with identical distribution of color channels. By means of inherent constraints of the triplet structure, the information of channel with less distortion is utilized to recover the information of other channels. Secondly, a recurrent dehazing module is designed to alleviate haze effect in images, where the Gated Recurrent Unit (GRU) as the memory module optimizes the results in multiple cycles to deal with severe underwater distortions. Finally, an iterative mechanism is proposed to jointly optimize the color correction and dehazing. By learning transform coefficients from dehazing features, color features and basic features of raw images are progressively refined, which maintains color balanced during the dehazing process and further improves clarity of images. Experimental results show that our network is superior to the existing state-of-the-art approaches for UIE and provides improved performance for underwater object detection.

Recently, many deep learning based researches are conducted to explore the potential quality improvement of compressed videos. These methods mostly utilize either the spatial or temporal information to perform frame-level video enhancement. However, they fail in combining different spatial-temporal information to adaptively utilize adjacent patches to enhance the current patch and achieve limited enhancement performance especially on scene-changing and strong-motion videos. To overcome these limitations, we propose a patch-wise spatial-temporal quality enhancement network which firstly extracts spatial and temporal features, then recalibrates and fuses the obtained spatial and temporal features. Specifically, we design a temporal and spatial-wise attention-based feature distillation structure to adaptively utilize the adjacent patches for distilling patch-wise temporal features. For adaptively enhancing different patch with spatial and temporal information, a channel and spatial-wise attention fusion block is proposed to achieve patch-wise recalibration and fusion of spatial and temporal features. Experimental results demonstrate our network achieves peak signal-to-noise ratio improvement, 0.55 - 0.69 dB compared with the compressed videos at different quantization parameters, outperforming state-of-the-art approach.