Dong Liu

Kaidong Zhang, Dong Liu

We propose SAMed, a general solution for medical image segmentation. Different from the previous methods, SAMed is built upon the large-scale image segmentation model, Segment Anything Model (SAM), to explore the new research paradigm of customizing large-scale models for medical image segmentation. SAMed applies the low-rank-based (LoRA) finetuning strategy to the SAM image encoder and finetunes it together with the prompt encoder and the mask decoder on labeled medical image segmentation datasets. We also observe the warmup finetuning strategy and the AdamW optimizer lead SAMed to successful convergence and lower loss. Different from SAM, SAMed could perform semantic segmentation on medical images. Our trained SAMed model achieves 81.88 DSC and 20.64 HD on the Synapse multi-organ segmentation dataset, which is on par with the state-of-the-art methods. We conduct extensive experiments to validate the effectiveness of our design. Since SAMed only updates a small fraction of the SAM parameters, its deployment cost and storage cost are quite marginal in practical usage. The code of SAMed is available at https://github.com/hitachinsk/SAMed.

Mingxing Li, Li Hu, Zhiwei Xiong et al.

Space-time memory (STM) based video object segmentation (VOS) networks usually keep increasing memory bank every several frames, which shows excellent performance. However, 1) the hardware cannot withstand the ever-increasing memory requirements as the video length increases. 2) Storing lots of information inevitably introduces lots of noise, which is not conducive to reading the most important information from the memory bank. In this paper, we propose a Recurrent Dynamic Embedding (RDE) to build a memory bank of constant size. Specifically, we explicitly generate and update RDE by the proposed Spatio-temporal Aggregation Module (SAM), which exploits the cue of historical information. To avoid error accumulation owing to the recurrent usage of SAM, we propose an unbiased guidance loss during the training stage, which makes SAM more robust in long videos. Moreover, the predicted masks in the memory bank are inaccurate due to the inaccurate network inference, which affects the segmentation of the query frame. To address this problem, we design a novel self-correction strategy so that the network can repair the embeddings of masks with different qualities in the memory bank. Extensive experiments show our method achieves the best tradeoff between performance and speed. Code is available at https://github.com/Limingxing00/RDE-VOS-CVPR2022.

Kaidong Zhang, Jingjing Fu, Dong Liu

We propose a flow-guided transformer, which innovatively leverage the motion discrepancy exposed by optical flows to instruct the attention retrieval in transformer for high fidelity video inpainting. More specially, we design a novel flow completion network to complete the corrupted flows by exploiting the relevant flow features in a local temporal window. With the completed flows, we propagate the content across video frames, and adopt the flow-guided transformer to synthesize the rest corrupted regions. We decouple transformers along temporal and spatial dimension, so that we can easily integrate the locally relevant completed flows to instruct spatial attention only. Furthermore, we design a flow-reweight module to precisely control the impact of completed flows on each spatial transformer. For the sake of efficiency, we introduce window partition strategy to both spatial and temporal transformers. Especially in spatial transformer, we design a dual perspective spatial MHSA, which integrates the global tokens to the window-based attention. Extensive experiments demonstrate the effectiveness of the proposed method qualitatively and quantitatively. Codes are available at https://github.com/hitachinsk/FGT.

Dongmei Xue, Haichuan Ma, Li Li et al.

Volumetric image compression has become an urgent task to effectively transmit and store images produced in biological research and clinical practice. At present, the most commonly used volumetric image compression methods are based on wavelet transform, such as JP3D. However, JP3D employs an ideal, separable, global, and fixed wavelet basis to convert input images from pixel domain to frequency domain, which seriously limits its performance. In this paper, we first design a 3-D trained wavelet-like transform to enable signal-dependent and non-separable transform. Then, an affine wavelet basis is introduced to capture the various local correlations in different regions of volumetric images. Furthermore, we embed the proposed wavelet-like transform to an end-to-end compression framework called aiWave to enable an adaptive compression scheme for various datasets. Last but not least, we introduce the weight sharing strategies of the affine wavelet-like transform according to the volumetric data characteristics in the axial direction to reduce the amount of parameters. The experimental results show that: 1) when cooperating our trained 3-D affine wavelet-like transform with a simple factorized entropy module, aiWave performs better than JP3D and is comparable in terms of encoding and decoding complexities; 2) when adding a context module to further remove signal redundancy, aiWave can achieve a much better performance than HEVC.

Rui Li, Shenglong Zhou, Dong Liu

Video analysis tasks rely heavily on identifying the pixels from different frames that correspond to the same visual target. To tackle this problem, recent studies have advocated feature learning methods that aim to learn distinctive representations to match the pixels, especially in a self-supervised fashion. Unfortunately, these methods have difficulties for tiny or even single-pixel visual targets. Pixel-wise video correspondences were traditionally related to optical flows, which however lead to deterministic correspondences and lack robustness on real-world videos. We address the problem of learning features for establishing pixel-wise correspondences. Motivated by optical flows as well as the self-supervised feature learning, we propose to use not only labeled synthetic videos but also unlabeled real-world videos for learning fine-grained representations in a holistic framework. We adopt an adversarial learning scheme to enhance the generalization ability of the learned features. Moreover, we design a coarse-to-fine framework to pursue high computational efficiency. Our experimental results on a series of correspondence-based tasks demonstrate that the proposed method outperforms state-of-the-art rivals in both accuracy and efficiency.

Cong Huang, Jiahao Li, Bin Li et al.

How to efficiently utilize the temporal features is crucial, yet challenging, for video restoration. The temporal features usually contain various noisy and uncorrelated information, and they may interfere with the restoration of the current frame. This paper proposes learning noise-robust feature representations to help video restoration. We are inspired by that the neural codec is a natural denoiser. In neural codec, the noisy and uncorrelated contents which are hard to predict but cost lots of bits are more inclined to be discarded for bitrate saving. Therefore, we design a neural compression module to filter the noise and keep the most useful information in features for video restoration. To achieve robustness to noise, our compression module adopts a spatial channel-wise quantization mechanism to adaptively determine the quantization step size for each position in the latent. Experiments show that our method can significantly boost the performance on video denoising, where we obtain 0.13 dB improvement over BasicVSR++ with only 0.23x FLOPs. Meanwhile, our method also obtains SOTA results on video deraining and dehazing.

Kaidong Zhang, Jialun Peng, Jingjing Fu et al.

Transformers have been widely used for video processing owing to the multi-head self attention (MHSA) mechanism. However, the MHSA mechanism encounters an intrinsic difficulty for video inpainting, since the features associated with the corrupted regions are degraded and incur inaccurate self attention. This problem, termed query degradation, may be mitigated by first completing optical flows and then using the flows to guide the self attention, which was verified in our previous work - flow-guided transformer (FGT). We further exploit the flow guidance and propose FGT++ to pursue more effective and efficient video inpainting. First, we design a lightweight flow completion network by using local aggregation and edge loss. Second, to address the query degradation, we propose a flow guidance feature integration module, which uses the motion discrepancy to enhance the features, together with a flow-guided feature propagation module that warps the features according to the flows. Third, we decouple the transformer along the temporal and spatial dimensions, where flows are used to select the tokens through a temporally deformable MHSA mechanism, and global tokens are combined with the inner-window local tokens through a dual perspective MHSA mechanism. FGT++ is experimentally evaluated to be outperforming the existing video inpainting networks qualitatively and quantitatively.

Zhuoyuan Li, Junqi Liao, Chuanbo Tang et al.

Image/video coding has been a remarkable research area for both academia and industry for many years. Testing datasets, especially high-quality image/video datasets are desirable for the justified evaluation of coding-related research, practical applications, and standardization activities. We put forward a test dataset namely USTC-TD, which has been successfully adopted in the practical end-to-end image/video coding challenge of the IEEE International Conference on Visual Communications and Image Processing (VCIP) in 2022 and 2023. USTC-TD contains 40 images at 4K spatial resolution and 10 video sequences at 1080p spatial resolution, featuring various content due to the diverse environmental factors (e.g. scene type, texture, motion, view) and the designed imaging factors (e.g. illumination, lens, shadow). We quantitatively evaluate USTC-TD on different image/video features (spatial, temporal, color, lightness), and compare it with the previous image/video test datasets, which verifies its excellent compensation for the shortcomings of existing datasets. We also evaluate both classic standardized and recently learned image/video coding schemes on USTC-TD using objective quality metrics (PSNR, MS-SSIM, VMAF) and subjective quality metric (MOS), providing an extensive benchmark for these evaluated schemes. Based on the characteristics and specific design of the proposed test dataset, we analyze the benchmark performance and shed light on the future research and development of image/video coding. All the data are released online: https://esakak.github.io/USTC-TD.

Ganlin Yang, Guoqiang Wei, Zhizheng Zhang et al.

Most Neural Radiance Fields (NeRFs) exhibit limited generalization capabilities, which restrict their applicability in representing multiple scenes using a single model. To address this problem, existing generalizable NeRF methods simply condition the model on image features. These methods still struggle to learn precise global representations over diverse scenes since they lack an effective mechanism for interacting among different points and views. In this work, we unveil that 3D implicit representation learning can be significantly improved by mask-based modeling. Specifically, we propose masked ray and view modeling for generalizable NeRF (MRVM-NeRF), which is a self-supervised pretraining target to predict complete scene representations from partially masked features along each ray. With this pretraining target, MRVM-NeRF enables better use of correlations across different points and views as the geometry priors, which thereby strengthens the capability of capturing intricate details within the scenes and boosts the generalization capability across different scenes. Extensive experiments demonstrate the effectiveness of our proposed MRVM-NeRF on both synthetic and real-world datasets, qualitatively and quantitatively. Besides, we also conduct experiments to show the compatibility of our proposed method with various backbones and its superiority under few-shot cases.

Xihua Sheng, Chuanbo Tang, Li Li et al.

The emerging large models have achieved notable progress in the fields of natural language processing and computer vision. However, large models for neural video coding are still unexplored. In this paper, we try to explore how to build a large neural video coding model. Based on a small baseline model, we gradually scale up the model sizes of its different coding parts, including the motion encoder-decoder, motion entropy model, contextual encoder-decoder, contextual entropy model, and temporal context mining module, and analyze the influence of model sizes on video compression performance. Then, we explore to use different architectures, including CNN, mixed CNN-Transformer, and Transformer architectures, to implement the neural video coding model and analyze the influence of model architectures on video compression performance. Based on our exploration results, we design the first neural video coding model with more than 1 billion parameters -- NVC-1B. Experimental results show that our proposed large model achieves a significant video compression performance improvement over the small baseline model, and represents the state-of-the-art compression efficiency. We anticipate large models may bring up the video coding technologies to the next level.

Haotian Zhang, Li Li, Dong Liu

Learned image compression possesses a unique challenge when incorporating non-differentiable quantization into the gradient-based training of the networks. Several quantization surrogates have been proposed to fulfill the training, but they were not systematically justified from a theoretical perspective. We fill this gap by contrasting uniform scalar quantization, the most widely used category with rounding being its simplest case, and its training surrogates. In principle, we find two factors crucial: one is the discrepancy between the surrogate and rounding, leading to train-test mismatch; the other is gradient estimation risk due to the surrogate, which consists of bias and variance of the gradient estimation. Our analyses and simulations imply that there is a tradeoff between the train-test mismatch and the gradient estimation risk, and the tradeoff varies across different network structures. Motivated by these analyses, we present a method based on stochastic uniform annealing, which has an adjustable temperature coefficient to control the tradeoff. Moreover, our analyses enlighten us as to two subtle tricks: one is to set an appropriate lower bound for the variance parameter of the estimated quantized latent distribution, which effectively reduces the train-test mismatch; the other is to use zero-center quantization with partial stop-gradient, which reduces the gradient estimation variance and thus stabilize the training. Our method with the tricks is verified to outperform the existing practices of quantization surrogates on a variety of representative image compression networks.

Zhuoyuan Li, Jiacheng Li, Yao Li et al.

In-loop filtering (ILF) is a key technology for removing the artifacts in image/video coding standards. Recently, neural network-based in-loop filtering methods achieve remarkable coding gains beyond the capability of advanced video coding standards, which becomes a powerful coding tool candidate for future video coding standards. However, the utilization of deep neural networks brings heavy time and computational complexity, and high demands of high-performance hardware, which is challenging to apply to the general uses of coding scene. To address this limitation, inspired by explorations in image restoration, we propose an efficient and practical in-loop filtering scheme by adopting the Look-up Table (LUT). We train the DNN of in-loop filtering within a fixed filtering reference range, and cache the output values of the DNN into a LUT via traversing all possible inputs. At testing time in the coding process, the filtered pixel is generated by locating input pixels (to-be-filtered pixel with reference pixels) and interpolating cached filtered pixel values. To further enable the large filtering reference range with the limited storage cost of LUT, we introduce the enhanced indexing mechanism in the filtering process, and clipping/finetuning mechanism in the training. The proposed method is implemented into the Versatile Video Coding (VVC) reference software, VTM-11.0. Experimental results show that the ultrafast, very fast, and fast mode of the proposed method achieves on average 0.13%/0.34%/0.51%, and 0.10%/0.27%/0.39% BD-rate reduction, under the all intra (AI) and random access (RA) configurations. Especially, our method has friendly time and computational complexity, only 101%/102%-104%/108% time increase with 0.13-0.93 kMACs/pixel, and only 164-1148 KB storage cost for a single model. Our solution may shed light on the journey of practical neural network-based coding tool evolution.

Yifan Li, Zhixin Lai, Wentao Bao et al.

Visual-language models (VLM) have emerged as a powerful tool for learning a unified embedding space for vision and language. Inspired by large language models, which have demonstrated strong reasoning and multi-task capabilities, visual large language models (VLLMs) are gaining increasing attention for building general-purpose VLMs. Despite the significant progress made in VLLMs, the related literature remains limited, particularly from a comprehensive application perspective, encompassing generalized and specialized applications across vision (image, video, depth), action, and language modalities. In this survey, we focus on the diverse applications of VLLMs, examining their using scenarios, identifying ethics consideration and challenges, and discussing future directions for their development. By synthesizing these contents, we aim to provide a comprehensive guide that will pave the way for future innovations and broader applications of VLLMs. The paper list repository is available: https://github.com/JackYFL/awesome-VLLMs.

Xihua Sheng, Li Li, Dong Liu et al.

Video compression performance is closely related to the accuracy of inter prediction. It tends to be difficult to obtain accurate inter prediction for the local video regions with inconsistent motion and occlusion. Traditional video coding standards propose various technologies to handle motion inconsistency and occlusion, such as recursive partitions, geometric partitions, and long-term references. However, existing learned video compression schemes focus on obtaining an overall minimized prediction error averaged over all regions while ignoring the motion inconsistency and occlusion in local regions. In this paper, we propose a spatial decomposition and temporal fusion based inter prediction for learned video compression. To handle motion inconsistency, we propose to decompose the video into structure and detail (SDD) components first. Then we perform SDD-based motion estimation and SDD-based temporal context mining for the structure and detail components to generate short-term temporal contexts. To handle occlusion, we propose to propagate long-term temporal contexts by recurrently accumulating the temporal information of each historical reference feature and fuse them with short-term temporal contexts. With the SDD-based motion model and long short-term temporal contexts fusion, our proposed learned video codec can obtain more accurate inter prediction. Comprehensive experimental results demonstrate that our codec outperforms the reference software of H.266/VVC on all common test datasets for both PSNR and MS-SSIM.

Yunwei Lan, Zhigao Cui, Chang Liu et al.

Unpaired training has been verified as one of the most effective paradigms for real scene dehazing by learning from unpaired real-world hazy and clear images. Although numerous studies have been proposed, current methods demonstrate limited generalization for various real scenes due to limited feature representation and insufficient use of real-world prior. Inspired by the strong generative capabilities of diffusion models in producing both hazy and clear images, we exploit diffusion prior for real-world image dehazing, and propose an unpaired framework named Diff-Dehazer. Specifically, we leverage diffusion prior as bijective mapping learners within the CycleGAN, a classic unpaired learning framework. Considering that physical priors contain pivotal statistics information of real-world data, we further excavate real-world knowledge by integrating physical priors into our framework. Furthermore, we introduce a new perspective for adequately leveraging the representation ability of diffusion models by removing degradation in image and text modalities, so as to improve the dehazing effect. Extensive experiments on multiple real-world datasets demonstrate the superior performance of our method. Our code https://github.com/ywxjm/Diff-Dehazer.

Tianyu Zhang, Haotian Zhang, Yuqi Li et al.

Learned image compression (LIC) has achieved state-of-the-art rate-distortion performance, deemed promising for next-generation image compression techniques. However, pre-trained LIC models usually suffer from significant performance degradation when applied to out-of-training-domain images, implying their poor generalization capabilities. To tackle this problem, we propose a few-shot domain adaptation method for LIC by integrating plug-and-play adapters into pre-trained models. Drawing inspiration from the analogy between latent channels and frequency components, we examine domain gaps in LIC and observe that out-of-training-domain images disrupt pre-trained channel-wise decomposition. Consequently, we introduce a method for channel-wise re-allocation using convolution-based adapters and low-rank adapters, which are lightweight and compatible to mainstream LIC schemes. Extensive experiments across multiple domains and multiple representative LIC schemes demonstrate that our method significantly enhances pre-trained models, achieving comparable performance to H.266/VVC intra coding with merely 25 target-domain samples. Additionally, our method matches the performance of full-model finetune while transmitting fewer than $2\%$ of the parameters.

Yuqi Li, Haotian Zhang, Li Li et al.

Context modeling is essential in learned image compression for accurately estimating the distribution of latents. While recent advanced methods have expanded context modeling capacity, they still struggle to efficiently exploit long-range dependency and diverse context information across different coding steps. In this paper, we introduce a novel Hierarchical Progressive Context Model (HPCM) for more efficient context information acquisition. Specifically, HPCM employs a hierarchical coding schedule to sequentially model the contextual dependencies among latents at multiple scales, which enables more efficient long-range context modeling. Furthermore, we propose a progressive context fusion mechanism that incorporates contextual information from previous coding steps into the current step, effectively exploiting diverse contextual information. Experimental results demonstrate that our method achieves state-of-the-art rate-distortion performance and strikes a better balance between compression performance and computational complexity. The code is available at https://github.com/lyq133/LIC-HPCM.

Yifan Yang, Peili Song, Enfan Lan et al.

Category-level object pose estimation, which predicts the pose of objects within a known category without prior knowledge of individual instances, is essential in applications like warehouse automation and manufacturing. Existing methods relying on RGB images or point cloud data often struggle with object occlusion and generalization across different instances and categories. This paper proposes a multimodal-based keypoint learning framework (MK-Pose) that integrates RGB images, point clouds, and category-level textual descriptions. The model uses a self-supervised keypoint detection module enhanced with attention-based query generation, soft heatmap matching and graph-based relational modeling. Additionally, a graph-enhanced feature fusion module is designed to integrate local geometric information and global context. MK-Pose is evaluated on CAMERA25 and REAL275 dataset, and is further tested for cross-dataset capability on HouseCat6D dataset. The results demonstrate that MK-Pose outperforms existing state-of-the-art methods in both IoU and average precision without shape priors. Codes will be released at \href{https://github.com/yangyifanYYF/MK-Pose}{https://github.com/yangyifanYYF/MK-Pose}.

Bohao Yang, Dong Liu, Chenghao Xiao et al.

Large Language Models (LLMs) demonstrate remarkable ability to comprehend instructions and generate human-like text, enabling sophisticated agent simulation beyond basic behavior replication. However, the potential for creating freely customisable characters remains underexplored. We introduce the Customisable Conversation Agent Framework, which employs LLMs to simulate real-world characters through personalised characteristic feature injection, enabling diverse character creation according to user preferences. We propose the SimsConv dataset, comprising 68 customised characters and 13,971 multi-turn role-playing dialogues across 1,360 real-world scenes. Characters are initially customised using pre-defined elements (career, aspiration, traits, skills), then expanded through personal and social profiles. Building on this, we present SimsChat, a freely customisable role-playing agent incorporating various realistic settings and topic-specified character interactions. Experimental results on both SimsConv and WikiRoleEval datasets demonstrate SimsChat's superior performance in maintaining character consistency, knowledge accuracy, and appropriate question rejection compared to existing models. Our framework provides valuable insights for developing more accurate and customisable human simulacra. Our data and code are publicly available at https://github.com/Bernard-Yang/SimsChat.

Mingxing Li, Shenglong Zhou, Chang Chen et al.

Accurate retinal vessel segmentation is challenging because of the complex texture of retinal vessels and low imaging contrast. Previous methods generally refine segmentation results by cascading multiple deep networks, which are time-consuming and inefficient. In this paper, we propose two novel methods to address these challenges. First, we devise a light-weight module, named multi-scale residual similarity gathering (MRSG), to generate pixel-wise adaptive filters (PA-Filters). Different from cascading multiple deep networks, only one PA-Filter layer can improve the segmentation results. Second, we introduce a response cue erasing (RCE) strategy to enhance the segmentation accuracy. Experimental results on the DRIVE, CHASE_DB1, and STARE datasets demonstrate that our proposed method outperforms state-of-the-art methods while maintaining a compact structure. Code is available at https://github.com/Limingxing00/Retinal-Vessel-Segmentation-ISBI20222.

Rui Li, Yiheng Zhang, Zhaofan Qiu et al.

Motion, as the most distinct phenomenon in a video to involve the changes over time, has been unique and critical to the development of video representation learning. In this paper, we ask the question: how important is the motion particularly for self-supervised video representation learning. To this end, we compose a duet of exploiting the motion for data augmentation and feature learning in the regime of contrastive learning. Specifically, we present a Motion-focused Contrastive Learning (MCL) method that regards such duet as the foundation. On one hand, MCL capitalizes on optical flow of each frame in a video to temporally and spatially sample the tubelets (i.e., sequences of associated frame patches across time) as data augmentations. On the other hand, MCL further aligns gradient maps of the convolutional layers to optical flow maps from spatial, temporal and spatio-temporal perspectives, in order to ground motion information in feature learning. Extensive experiments conducted on R(2+1)D backbone demonstrate the effectiveness of our MCL. On UCF101, the linear classifier trained on the representations learnt by MCL achieves 81.91% top-1 accuracy, outperforming ImageNet supervised pre-training by 6.78%. On Kinetics-400, MCL achieves 66.62% top-1 accuracy under the linear protocol. Code is available at https://github.com/YihengZhang-CV/MCL-Motion-Focused-Contrastive-Learning.

Zeyuan Chen, Yifan Jiang, Dong Liu et al.

Low-light images captured in the real world are inevitably corrupted by sensor noise. Such noise is spatially variant and highly dependent on the underlying pixel intensity, deviating from the oversimplified assumptions in conventional denoising. Existing light enhancement methods either overlook the important impact of real-world noise during enhancement, or treat noise removal as a separate pre- or post-processing step. We present \underline{C}oordinated \underline{E}nhancement for \underline{R}eal-world \underline{L}ow-light Noisy Images (CERL), that seamlessly integrates light enhancement and noise suppression parts into a unified and physics-grounded optimization framework. For the real low-light noise removal part, we customize a self-supervised denoising model that can easily be adapted without referring to clean ground-truth images. For the light enhancement part, we also improve the design of a state-of-the-art backbone. The two parts are then joint formulated into one principled plug-and-play optimization. Our approach is compared against state-of-the-art low-light enhancement methods both qualitatively and quantitatively. Besides standard benchmarks, we further collect and test on a new realistic low-light mobile photography dataset (RLMP), whose mobile-captured photos display heavier realistic noise than those taken by high-quality cameras. CERL consistently produces the most visually pleasing and artifact-free results across all experiments. Our RLMP dataset and codes are available at: https://github.com/VITA-Group/CERL.

Haisheng Fu, Feng Liang, Jianping Lin et al.

Recently deep learning-based image compression methods have achieved significant achievements and gradually outperformed traditional approaches including the latest standard Versatile Video Coding (VVC) in both PSNR and MS-SSIM metrics. Two key components of learned image compression are the entropy model of the latent representations and the encoding/decoding network architectures. Various models have been proposed, such as autoregressive, softmax, logistic mixture, Gaussian mixture, and Laplacian. Existing schemes only use one of these models. However, due to the vast diversity of images, it is not optimal to use one model for all images, even different regions within one image. In this paper, we propose a more flexible discretized Gaussian-Laplacian-Logistic mixture model (GLLMM) for the latent representations, which can adapt to different contents in different images and different regions of one image more accurately and efficiently, given the same complexity. Besides, in the encoding/decoding network design part, we propose a concatenated residual blocks (CRB), where multiple residual blocks are serially connected with additional shortcut connections. The CRB can improve the learning ability of the network, which can further improve the compression performance. Experimental results using the Kodak, Tecnick-100 and Tecnick-40 datasets show that the proposed scheme outperforms all the leading learning-based methods and existing compression standards including VVC intra coding (4:4:4 and 4:2:0) in terms of the PSNR and MS-SSIM. The source code is available at \url{https://github.com/fengyurenpingsheng}

Jiawei Liu, Zhipeng Huang, Kecheng Zheng et al.

Although existing person re-identification (Re-ID) methods have shown impressive accuracy, most of them usually suffer from poor generalization on unseen target domain. Thus, generalizable person Re-ID has recently drawn increasing attention, which trains a model on source domains that generalizes well on unseen target domain without model updating. In this work, we propose a novel adaptive domain-specific normalization approach (AdsNorm) for generalizable person Re-ID. It describes unseen target domain as a combination of the known source ones, and explicitly learns domain-specific representation with target distribution to improve the model's generalization by a meta-learning pipeline. Specifically, AdsNorm utilizes batch normalization layers to collect individual source domains' characteristics, and maps source domains into a shared latent space by using these characteristics, where the domain relevance is measured by a distance function of different domain-specific normalization statistics and features. At the testing stage, AdsNorm projects images from unseen target domain into the same latent space, and adaptively integrates the domain-specific features carrying the source distributions by domain relevance for learning more generalizable aggregated representation on unseen target domain. Considering that target domain is unavailable during training, a meta-learning algorithm combined with a customized relation loss is proposed to optimize an effective and efficient ensemble model. Extensive experiments demonstrate that AdsNorm outperforms the state-of-the-art methods. The code is available at: https://github.com/hzphzp/AdsNorm.

Jialun Peng, Dong Liu, Songcen Xu et al.

Given an incomplete image without additional constraint, image inpainting natively allows for multiple solutions as long as they appear plausible. Recently, multiplesolution inpainting methods have been proposed and shown the potential of generating diverse results. However, these methods have difficulty in ensuring the quality of each solution, e.g. they produce distorted structure and/or blurry texture. We propose a two-stage model for diverse inpainting, where the first stage generates multiple coarse results each of which has a different structure, and the second stage refines each coarse result separately by augmenting texture. The proposed model is inspired by the hierarchical vector quantized variational auto-encoder (VQ-VAE), whose hierarchical architecture isentangles structural and textural information. In addition, the vector quantization in VQVAE enables autoregressive modeling of the discrete distribution over the structural information. Sampling from the distribution can easily generate diverse and high-quality structures, making up the first stage of our model. In the second stage, we propose a structural attention module inside the texture generation network, where the module utilizes the structural information to capture distant correlations. We further reuse the VQ-VAE to calculate two feature losses, which help improve structure coherence and texture realism, respectively. Experimental results on CelebA-HQ, Places2, and ImageNet datasets show that our method not only enhances the diversity of the inpainting solutions but also improves the visual quality of the generated multiple images. Code and models are available at: https://github.com/USTC-JialunPeng/Diverse-Structure-Inpainting.

Ke Sun, Zigang Geng, Depu Meng et al.

The typical bottom-up human pose estimation framework includes two stages, keypoint detection and grouping. Most existing works focus on developing grouping algorithms, e.g., associative embedding, and pixel-wise keypoint regression that we adopt in our approach. We present several schemes that are rarely or unthoroughly studied before for improving keypoint detection and grouping (keypoint regression) performance. First, we exploit the keypoint heatmaps for pixel-wise keypoint regression instead of separating them for improving keypoint regression. Second, we adopt a pixel-wise spatial transformer network to learn adaptive representations for handling the scale and orientation variance to further improve keypoint regression quality. Last, we present a joint shape and heatvalue scoring scheme to promote the estimated poses that are more likely to be true poses. Together with the tradeoff heatmap estimation loss for balancing the background and keypoint pixels and thus improving heatmap estimation quality, we get the state-of-the-art bottom-up human pose estimation result. Code is available at https://github.com/HRNet/HRNet-Bottom-up-Pose-Estimation.

Hengrui Zhao, Dong Liu, Houqiang Li

Integer-arithmetic-only networks have been demonstrated effective to reduce computational cost and to ensure cross-platform consistency. However, previous works usually report a decline in the inference accuracy when converting well-trained floating-point-number (FPN) networks into integer networks. We analyze this phonomenon and find that the decline is due to activation quantization. Specifically, when we replace conventional ReLU with Bounded ReLU, how to set the bound for each neuron is a key problem. Considering the tradeoff between activation quantization error and network learning ability, we set an empirical rule to tune the bound of each Bounded ReLU. We also design a mechanism to handle the cases of feature map addition and feature map concatenation. Based on the proposed method, our trained 8-bit integer ResNet outperforms the 8-bit networks of Google's TensorFlow and NVIDIA's TensorRT for image recognition. We also experiment on VDSR for image super-resolution and on VRCNN for compression artifact reduction, both of which serve for regression tasks that natively require high inference accuracy. Our integer networks achieve equivalent performance as the corresponding FPN networks, but have only 1/4 memory cost and run 2x faster on modern GPUs. Our code and models can be found at github.com/HengRuiZ/brelu.

Joya Chen, Dong Liu, Tong Xu et al.

To train accurate deep object detectors under the extreme foreground-background imbalance, heuristic sampling methods are always necessary, which either re-sample a subset of all training samples (hard sampling methods, \eg biased sampling, OHEM), or use all training samples but re-weight them discriminatively (soft sampling methods, \eg Focal Loss, GHM). In this paper, we challenge the necessity of such hard/soft sampling methods for training accurate deep object detectors. While previous studies have shown that training detectors without heuristic sampling methods would significantly degrade accuracy, we reveal that this degradation comes from an unreasonable classification gradient magnitude caused by the imbalance, rather than a lack of re-sampling/re-weighting. Motivated by our discovery, we propose a simple yet effective \emph{Sampling-Free} mechanism to achieve a reasonable classification gradient magnitude by initialization and loss scaling. Unlike heuristic sampling methods with multiple hyperparameters, our Sampling-Free mechanism is fully data diagnostic, without laborious hyperparameters searching. We verify the effectiveness of our method in training anchor-based and anchor-free object detectors, where our method always achieves higher detection accuracy than heuristic sampling methods on COCO and PASCAL VOC datasets. Our Sampling-Free mechanism provides a new perspective to address the foreground-background imbalance. Our code is released at \url{https://github.com/ChenJoya/sampling-free}.

Ke Sun, Bin Xiao, Dong Liu et al.

This is an official pytorch implementation of Deep High-Resolution Representation Learning for Human Pose Estimation. In this work, we are interested in the human pose estimation problem with a focus on learning reliable high-resolution representations. Most existing methods recover high-resolution representations from low-resolution representations produced by a high-to-low resolution network. Instead, our proposed network maintains high-resolution representations through the whole process. We start from a high-resolution subnetwork as the first stage, gradually add high-to-low resolution subnetworks one by one to form more stages, and connect the mutli-resolution subnetworks in parallel. We conduct repeated multi-scale fusions such that each of the high-to-low resolution representations receives information from other parallel representations over and over, leading to rich high-resolution representations. As a result, the predicted keypoint heatmap is potentially more accurate and spatially more precise. We empirically demonstrate the effectiveness of our network through the superior pose estimation results over two benchmark datasets: the COCO keypoint detection dataset and the MPII Human Pose dataset. The code and models have been publicly available at \url{https://github.com/leoxiaobin/deep-high-resolution-net.pytorch}.

Xiaofeng Zhang, Zhangyang Wang, Dong Liu et al.

Deep learning has revolutionized the performance of classification, but meanwhile demands sufficient labeled data for training. Given insufficient data, while many techniques have been developed to help combat overfitting, the challenge remains if one tries to train deep networks, especially in the ill-posed extremely low data regimes: only a small set of labeled data are available, and nothing -- including unlabeled data -- else. Such regimes arise from practical situations where not only data labeling but also data collection itself is expensive. We propose a deep adversarial data augmentation (DADA) technique to address the problem, in which we elaborately formulate data augmentation as a problem of training a class-conditional and supervised generative adversarial network (GAN). Specifically, a new discriminator loss is proposed to fit the goal of data augmentation, through which both real and augmented samples are enforced to contribute to and be consistent in finding the decision boundaries. Tailored training techniques are developed accordingly. To quantitatively validate its effectiveness, we first perform extensive simulations to show that DADA substantially outperforms both traditional data augmentation and a few GAN-based options. We then extend experiments to three real-world small labeled datasets where existing data augmentation and/or transfer learning strategies are either less effective or infeasible. All results endorse the superior capability of DADA in enhancing the generalization ability of deep networks trained in practical extremely low data regimes. Source code is available at https://github.com/SchafferZhang/DADA.

Ganlin Yang, Kaidong Zhang, Jingjing Fu et al.

Aliasing artifacts in renderings produced by Neural Radiance Field (NeRF) is a long-standing but complex issue in the field of 3D implicit representation, which arises from a multitude of intricate causes and was mitigated by designing more advanced but complex scene parameterization methods before. In this paper, we present a Diffusion-based restoration method for anti-aliasing Neural Radiance Field (Drantal-NeRF). We consider the anti-aliasing issue from a low-level restoration perspective by viewing aliasing artifacts as a kind of degradation model added to clean ground truths. By leveraging the powerful prior knowledge encapsulated in diffusion model, we could restore the high-realism anti-aliasing renderings conditioned on aliased low-quality counterparts. We further employ a feature-wrapping operation to ensure multi-view restoration consistency and finetune the VAE decoder to better adapt to the scene-specific data distribution. Our proposed method is easy to implement and agnostic to various NeRF backbones. We conduct extensive experiments on challenging large-scale urban scenes as well as unbounded 360-degree scenes and achieve substantial qualitative and quantitative improvements.

Zhuoyuan Li, Zikun Yuan, Li Li et al.

In modern video coding standards, block-based inter prediction is widely adopted, which brings high compression efficiency. However, in natural videos, there are usually multiple moving objects of arbitrary shapes, resulting in complex motion fields that are difficult to represent compactly. This problem has been tackled by more flexible block partitioning methods in the Versatile Video Coding (VVC) standard, but the more flexible partitions require more overhead bits to signal and still cannot be made arbitrarily shaped. To address this limitation, we propose an object segmentation-assisted inter prediction method (SAIP), where objects in the reference frames are segmented by some advanced technologies. With a proper indication, the object segmentation mask is translated from the reference frame to the current frame as the arbitrary-shaped partition of different regions without any extra signal. Using the segmentation mask, motion compensation is separately performed for different regions, achieving higher prediction accuracy. The segmentation mask is further used to code the motion vectors of different regions more efficiently. Moreover, the segmentation mask is considered in the joint rate-distortion optimization for motion estimation and partition estimation to derive the motion vector of different regions and partition more accurately. The proposed method is implemented into the VVC reference software, VTM version 12.0. Experimental results show that the proposed method achieves up to 1.98%, 1.14%, 0.79%, and on average 0.82%, 0.49%, 0.37% BD-rate reduction for common test sequences, under the Low-delay P, Low-delay B, and Random Access configurations, respectively.

Chang Liu, Rui Li, Kaidong Zhang et al.

Recent advancements of generative AI have significantly promoted content creation and editing, where prevailing studies further extend this exciting progress to video editing. In doing so, these studies mainly transfer the inherent motion patterns from the source videos to the edited ones, where results with inferior consistency to user prompts are often observed, due to the lack of particular alignments between the delivered motions and edited contents. To address this limitation, we present a shape-consistent video editing method, namely StableV2V, in this paper. Our method decomposes the entire editing pipeline into several sequential procedures, where it edits the first video frame, then establishes an alignment between the delivered motions and user prompts, and eventually propagates the edited contents to all other frames based on such alignment. Furthermore, we curate a testing benchmark, namely DAVIS-Edit, for a comprehensive evaluation of video editing, considering various types of prompts and difficulties. Experimental results and analyses illustrate the outperforming performance, visual consistency, and inference efficiency of our method compared to existing state-of-the-art studies.

Haotian Zhang, Li Li, Dong Liu

In learned image compression, probabilistic models play an essential role in characterizing the distribution of latent variables. The Gaussian model with mean and scale parameters has been widely used for its simplicity and effectiveness. Probabilistic models with more parameters, such as the Gaussian mixture models, can fit the distribution of latent variables more precisely, but the corresponding complexity is higher. To balance the compression performance and complexity, we extend the Gaussian model to the generalized Gaussian family for more flexible latent distribution modeling, introducing only one additional shape parameter beta than the Gaussian model. To enhance the performance of the generalized Gaussian model by alleviating the train-test mismatch, we propose improved training methods, including beta-dependent lower bounds for scale parameters and gradient rectification. Our proposed generalized Gaussian model, coupled with the improved training methods, is demonstrated to outperform the Gaussian and Gaussian mixture models on a variety of learned image compression networks.

Jiawen Wang, Yinda Chen, Xiaoyu Liu et al.

Recent works have correlated Masked Image Modeling (MIM) with consistency regularization in Unsupervised Domain Adaptation (UDA). However, they merely treat masking as a special form of deformation on the input images and neglect the theoretical analysis, which leads to a superficial understanding of masked reconstruction and insufficient exploitation of its potential in enhancing feature extraction and representation learning. In this paper, we reframe masked reconstruction as a sparse signal reconstruction problem and theoretically prove that the dual form of complementary masks possesses superior capabilities in extracting domain-agnostic image features. Based on this compelling insight, we propose MaskTwins, a simple yet effective UDA framework that integrates masked reconstruction directly into the main training pipeline. MaskTwins uncovers intrinsic structural patterns that persist across disparate domains by enforcing consistency between predictions of images masked in complementary ways, enabling domain generalization in an end-to-end manner. Extensive experiments verify the superiority of MaskTwins over baseline methods in natural and biological image segmentation. These results demonstrate the significant advantages of MaskTwins in extracting domain-invariant features without the need for separate pre-training, offering a new paradigm for domain-adaptive segmentation.

Xinmin Feng, Zhuoyuan Li, Li Li et al.

Among the new techniques of Versatile Video Coding (VVC), the quadtree with nested multi-type tree (QT+MTT) block structure yields significant coding gains by providing more flexible block partitioning patterns. However, the recursive partition search in the VVC encoder increases the encoder complexity substantially. To address this issue, we propose a partition map-based algorithm to pursue fast block partitioning in inter coding. Based on our previous work on partition map-based methods for intra coding, we analyze the characteristics of VVC inter coding, and thus improve the partition map by incorporating an MTT mask for early termination. Next, we develop a neural network that uses both spatial and temporal features to predict the partition map. It consists of several special designs including stacked top-down and bottom-up processing, quantization parameter modulation layers, and partitioning-adaptive warping. Furthermore, we present a dual-threshold decision scheme to achieve a fine-grained trade-off between complexity reduction and rate-distortion (RD) performance loss. The experimental results demonstrate that the proposed method achieves an average 51.30% encoding time saving with a 2.12% Bjontegaard Delta Bit Rate (BDBR) under the random access configuration.

Haotian Zhang, Dong Liu

Lossy image coding is the art of computing that is principally bounded by the image's rate-distortion function. This bound, though never accurately characterized, has been approached practically via deep learning technologies in recent years. Indeed, learned image coding schemes allow direct optimization of the joint rate-distortion cost, thereby outperforming the handcrafted image coding schemes by a large margin. Still, it is observed that there is room for further improvement in the rate-distortion performance of learned image coding. In this article, we identify the gap between the ideal rate-distortion function forecasted by Shannon's information theory and the empirical rate-distortion function achieved by the state-of-the-art learned image coding schemes, revealing that the gap is incurred by five different effects: modeling effect, approximation effect, amortization effect, digitization effect, and asymptotic effect. We design simulations and experiments to quantitively evaluate the last three effects, which demonstrates the high potential of future lossy image coding technologies.

Yiheng Jiang, Haotian Zhang, Li Li et al.

In the field of autonomous driving, a variety of sensor data types exist, each representing different modalities of the same scene. Therefore, it is feasible to utilize data from other sensors to facilitate image compression. However, few techniques have explored the potential benefits of utilizing inter-modality correlations to enhance the image compression performance. In this paper, motivated by the recent success of learned image compression, we propose a new framework that uses sparse point clouds to assist in learned image compression in the autonomous driving scenario. We first project the 3D sparse point cloud onto a 2D plane, resulting in a sparse depth map. Utilizing this depth map, we proceed to predict camera images. Subsequently, we use these predicted images to extract multi-scale structural features. These features are then incorporated into learned image compression pipeline as additional information to improve the compression performance. Our proposed framework is compatible with various mainstream learned image compression models, and we validate our approach using different existing image compression methods. The experimental results show that incorporating point cloud assistance into the compression pipeline consistently enhances the performance.

Menglin Zhang, Xin Luo, Yunwei Lan et al.

Recent advances in NeRF inpainting have leveraged pretrained diffusion models to enhance performance. However, these methods often yield suboptimal results due to their ineffective utilization of 2D diffusion priors. The limitations manifest in two critical aspects: the inadequate capture of geometric information by pretrained diffusion models and the suboptimal guidance provided by existing Score Distillation Sampling (SDS) methods. To address these problems, we introduce GB-NeRF, a novel framework that enhances NeRF inpainting through improved utilization of 2D diffusion priors. Our approach incorporates two key innovations: a fine-tuning strategy that simultaneously learns appearance and geometric priors and a specialized normal distillation loss that integrates these geometric priors into NeRF inpainting. We propose a technique called Balanced Score Distillation (BSD) that surpasses existing methods such as Score Distillation (SDS) and the improved version, Conditional Score Distillation (CSD). BSD offers improved inpainting quality in appearance and geometric aspects. Extensive experiments show that our method provides superior appearance fidelity and geometric consistency compared to existing approaches.

Tianyu Zhang, Dong Liu, Chang Wen Chen

Ultra-low bitrate image compression (below 0.05 bits per pixel) is increasingly critical for bandwidth-constrained and computation-limited encoding scenarios such as edge devices. Existing frameworks typically rely on large pretrained encoders (e.g., VAEs or tokenizer-based models) and perform transform coding within their generative latent space. While these approaches achieve impressive perceptual fidelity, their reliance on heavy encoder networks makes them unsuitable for deployment on weak sender devices. In this work, we explore the feasibility of applying shallow encoders for ultra-low bitrate compression and propose a novel Asymmetric Extreme Image Compression (AEIC) framework that pursues simultaneously encoding simplicity and decoding quality. Specifically, AEIC employs moderate or even shallow encoder networks, while leveraging an one-step diffusion decoder to maintain high-fidelity and high-realism reconstructions under extreme bitrates. To further enhance the efficiency of shallow encoders, we design a dual-side feature distillation scheme that transfers knowledge from AEIC with moderate encoders to its shallow encoder variants. Experiments demonstrate that AEIC not only outperforms existing methods on rate-distortion-perception performance at ultra-low bitrates, but also delivers exceptional encoding efficiency for 35.8 FPS on 1080P input images, while maintaining competitive decoding speed compared to existing methods.

Yuqi Li, Haotian Zhang, Li Li et al.

Recent advances in large language models (LLMs) highlight a strong connection between intelligence and compression. Learned image compression, a fundamental task in modern data compression, has made significant progress in recent years. However, current models remain limited in scale, restricting their representation capacity, and how scaling model size influences compression performance remains unexplored. In this work, we present a pioneering study on scaling up learned image compression models and revealing the performance trends through scaling laws. Using the recent state-of-the-art HPCM model as baseline, we scale model parameters from 68.5 millions to 1 billion and fit power-law relations between test loss and key scaling variables, including model size and optimal training compute. The results reveal a scaling trend, enabling extrapolation to larger scale models. Experimental results demonstrate that the scaled-up HPCM-1B model achieves state-of-the-art rate-distortion performance. We hope this work inspires future exploration of large-scale compression models and deeper investigations into the connection between compression and intelligence.

Dong Liu, Yanxuan Yu

As large language models (LLMs) grow in size and deployment scale, quantization has become an essential technique for reducing memory footprint and improving inference efficiency. However, existing quantization toolkits often lack transparency, flexibility, and system-level scalability across GPUs and distributed environments. We present \textbf{LLMEasyQuant}, a modular, system-aware quantization framework designed for efficient, low-bit inference of LLMs on single-node multi-GPU, multi-node, and edge hardware. LLMEasyQuant supports a wide range of quantization methods -- including Symmetric Quantization, ZeroQuant, SmoothQuant, and SimQuant -- with unified interfaces for per-layer calibration, bitwidth assignment, and runtime adaptation. It integrates fused CUDA kernels with NCCL-based distributed synchronization and supports both static and online quantization. Empirical results show that LLMEasyQuant can achieve substantial speedup in GEMM execution, HBM load time, and near-linear multi-GPU scaling. Ablation studies further validate its ability to balance latency, memory, and accuracy under diverse deployment conditions. LLMEasyQuant offers a practical quantization serving system for scalable, hardware-optimized LLM inference.

Xihua Sheng, Li Li, Dong Liu et al.

Temporal prediction is one of the most important technologies for video compression. Various prediction coding modes are designed in traditional video codecs. Traditional video codecs will adaptively to decide the optimal coding mode according to the prediction quality and reference quality. Recently, learned video codecs have made great progress. However, they did not effectively address the problem of prediction and reference quality adaptation, which limits the effective utilization of temporal prediction and reduction of reconstruction error propagation. Therefore, in this paper, we first propose a confidence-based prediction quality adaptation (PQA) module to provide explicit discrimination for the spatial and channel-wise prediction quality difference. With this module, the prediction with low quality will be suppressed and that with high quality will be enhanced. The codec can adaptively decide which spatial or channel location of predictions to use. Then, we further propose a reference quality adaptation (RQA) module and an associated repeat-long training strategy to provide dynamic spatially variant filters for diverse reference qualities. With these filters, our codec can adapt to different reference qualities, making it easier to achieve the target reconstruction quality and reduce the reconstruction error propagation. Experimental results verify that our proposed modules can effectively help our codec achieve a higher compression performance.

Xihua Sheng, Li Li, Dong Liu et al.

Geometry-based point cloud compression (G-PCC) can achieve remarkable compression efficiency for point clouds. However, it still leads to serious attribute compression artifacts, especially under low bitrate scenarios. In this paper, we propose a Multi-Scale Graph Attention Network (MS-GAT) to remove the artifacts of point cloud attributes compressed by G-PCC. We first construct a graph based on point cloud geometry coordinates and then use the Chebyshev graph convolutions to extract features of point cloud attributes. Considering that one point may be correlated with points both near and far away from it, we propose a multi-scale scheme to capture the short- and long-range correlations between the current point and its neighboring and distant points. To address the problem that various points may have different degrees of artifacts caused by adaptive quantization, we introduce the quantization step per point as an extra input to the proposed network. We also incorporate a weighted graph attentional layer into the network to pay special attention to the points with more attribute artifacts. To the best of our knowledge, this is the first attribute artifacts removal method for G-PCC. We validate the effectiveness of our method over various point clouds. Objective comparison results show that our proposed method achieves an average of 9.74% BD-rate reduction compared with Predlift and 10.13% BD-rate reduction compared with RAHT. Subjective comparison results present that visual artifacts such as color shifting, blurring, and quantization noise are reduced.

Xihua Sheng, Jiahao Li, Bin Li et al.

We address end-to-end learned video compression with a special focus on better learning and utilizing temporal contexts. For temporal context mining, we propose to store not only the previously reconstructed frames, but also the propagated features into the generalized decoded picture buffer. From the stored propagated features, we propose to learn multi-scale temporal contexts, and re-fill the learned temporal contexts into the modules of our compression scheme, including the contextual encoder-decoder, the frame generator, and the temporal context encoder. Our scheme discards the parallelization-unfriendly auto-regressive entropy model to pursue a more practical decoding time. We compare our scheme with x264 and x265 (representing industrial software for H.264 and H.265, respectively) as well as the official reference software for H.264, H.265, and H.266 (JM, HM, and VTM, respectively). When intra period is 32 and oriented to PSNR, our scheme outperforms H.265--HM by 14.4% bit rate saving; when oriented to MS-SSIM, our scheme outperforms H.266--VTM by 21.1% bit rate saving.

Haichuan Ma, Dong Liu, Cunhui Dong et al.

Lossy image compression is a many-to-one process, thus one bitstream corresponds to multiple possible original images, especially at low bit rates. However, this nature was seldom considered in previous studies on image compression, which usually chose one possible image as reconstruction, e.g. the one with the maximal a posteriori probability. We propose a learned image compression framework to natively support probabilistic decoding. The compressed bitstream is decoded into a series of parameters that instantiate a pre-chosen distribution; then the distribution is used by the decoder to sample and reconstruct images. The decoder may adopt different sampling strategies and produce diverse reconstructions, among which some have higher signal fidelity and some others have better visual quality. The proposed framework is dependent on a revertible neural network-based transform to convert pixels into coefficients that obey the pre-chosen distribution as much as possible. Our code and models will be made publicly available.

Dongmei Xue, Haichuan Ma, Li Li et al.

With the rapid development of whole brain imaging technology, a large number of brain images have been produced, which puts forward a great demand for efficient brain image compression methods. At present, the most commonly used compression methods are all based on 3-D wavelet transform, such as JP3D. However, traditional 3-D wavelet transforms are designed manually with certain assumptions on the signal, but brain images are not as ideal as assumed. What's more, they are not directly optimized for compression task. In order to solve these problems, we propose a trainable 3-D wavelet transform based on the lifting scheme, in which the predict and update steps are replaced by 3-D convolutional neural networks. Then the proposed transform is embedded into an end-to-end compression scheme called iWave3D, which is trained with a large amount of brain images to directly minimize the rate-distortion loss. Experimental results demonstrate that our method outperforms JP3D significantly by 2.012 dB in terms of average BD-PSNR.

Size Wu, Sheng Jin, Wentao Liu et al.

This paper studies the task of estimating the 3D human poses of multiple persons from multiple calibrated camera views. Following the top-down paradigm, we decompose the task into two stages, i.e. person localization and pose estimation. Both stages are processed in coarse-to-fine manners. And we propose three task-specific graph neural networks for effective message passing. For 3D person localization, we first use Multi-view Matching Graph Module (MMG) to learn the cross-view association and recover coarse human proposals. The Center Refinement Graph Module (CRG) further refines the results via flexible point-based prediction. For 3D pose estimation, the Pose Regression Graph Module (PRG) learns both the multi-view geometry and structural relations between human joints. Our approach achieves state-of-the-art performance on CMU Panoptic and Shelf datasets with significantly lower computation complexity.

Shunxin Xu, Ke Sun, Dong Liu et al.

The capability of image semantic segmentation may be deteriorated due to noisy input image, where image denoising prior to segmentation helps. Both image denoising and semantic segmentation have been developed significantly with the advance of deep learning. Thus, we are interested in the synergy between them by using a holistic deep model. We observe that not only denoising helps combat the drop of segmentation accuracy due to noise, but also pixel-wise semantic information boosts the capability of denoising. We then propose a boosting network to perform denoising and segmentation alternately. The proposed network is composed of multiple segmentation and denoising blocks (SDBs), each of which estimates semantic map then uses the map to regularize denoising. Experimental results show that the denoised image quality is improved substantially and the segmentation accuracy is improved to close to that of clean images. Our code and models will be made publicly available.

Lezi Wang, Dong Liu, Rohit Puri et al.

A movie's key moments stand out of the screenplay to grab an audience's attention and make movie browsing efficient. But a lack of annotations makes the existing approaches not applicable to movie key moment detection. To get rid of human annotations, we leverage the officially-released trailers as the weak supervision to learn a model that can detect the key moments from full-length movies. We introduce a novel ranking network that utilizes the Co-Attention between movies and trailers as guidance to generate the training pairs, where the moments highly corrected with trailers are expected to be scored higher than the uncorrelated moments. Additionally, we propose a Contrastive Attention module to enhance the feature representations such that the comparative contrast between features of the key and non-key moments are maximized. We construct the first movie-trailer dataset, and the proposed Co-Attention assisted ranking network shows superior performance even over the supervised approach. The effectiveness of our Contrastive Attention module is also demonstrated by the performance improvement over the state-of-the-art on the public benchmarks.