Haojie Liu

Liu Haojie, Gao Suixiang

We present HumanCM, a one-step human motion prediction framework built upon consistency models. Instead of relying on multi-step denoising as in diffusion-based methods, HumanCM performs efficient single-step generation by learning a self-consistent mapping between noisy and clean motion states. The framework adopts a Transformer-based spatiotemporal architecture with temporal embeddings to model long-range dependencies and preserve motion coherence. Experiments on Human3.6M and HumanEva-I demonstrate that HumanCM achieves comparable or superior accuracy to state-of-the-art diffusion models while reducing inference steps by up to two orders of magnitude.

Xudong Huang, Chunyu Lin, Haojie Liu et al.

LiDAR sensors are widely used in autonomous driving due to the reliable 3D spatial information. However, the data of LiDAR is sparse and the frequency of LiDAR is lower than that of cameras. To generate denser point clouds spatially and temporally, we propose the first future pseudo-LiDAR frame prediction network. Given the consecutive sparse depth maps and RGB images, we first predict a future dense depth map based on dynamic motion information coarsely. To eliminate the errors of optical flow estimation, an inter-frame aggregation module is proposed to fuse the warped depth maps with adaptive weights. Then, we refine the predicted dense depth map using static contextual information. The future pseudo-LiDAR frame can be obtained by converting the predicted dense depth map into corresponding 3D point clouds. Experimental results show that our method outperforms the existing solutions on the popular KITTI benchmark.

Haojie Liu, Ming Lu, Zhiqi Chen et al.

Recent years have witnessed rapid advances in learnt video coding. Most algorithms have solely relied on the vector-based motion representation and resampling (e.g., optical flow based bilinear sampling) for exploiting the inter frame redundancy. In spite of the great success of adaptive kernel-based resampling (e.g., adaptive convolutions and deformable convolutions) in video prediction for uncompressed videos, integrating such approaches with rate-distortion optimization for inter frame coding has been less successful. Recognizing that each resampling solution offers unique advantages in regions with different motion and texture characteristics, we propose a hybrid motion compensation (HMC) method that adaptively combines the predictions generated by these two approaches. Specifically, we generate a compound spatiotemporal representation (CSTR) through a recurrent information aggregation (RIA) module using information from the current and multiple past frames. We further design a one-to-many decoder pipeline to generate multiple predictions from the CSTR, including vector-based resampling, adaptive kernel-based resampling, compensation mode selection maps and texture enhancements, and combines them adaptively to achieve more accurate inter prediction. Experiments show that our proposed inter coding system can provide better motion-compensated prediction and is more robust to occlusions and complex motions. Together with jointly trained intra coder and residual coder, the overall learnt hybrid coder yields the state-of-the-art coding efficiency in low-delay scenario, compared to the traditional H.264/AVC and H.265/HEVC, as well as recently published learning-based methods, in terms of both PSNR and MS-SSIM metrics.

Zhiqi Chen, Ran Wang, Haojie Liu et al.

Video interpolation aims to generate a non-existent intermediate frame given the past and future frames. Many state-of-the-art methods achieve promising results by estimating the optical flow between the known frames and then generating the backward flows between the middle frame and the known frames. However, these methods usually suffer from the inaccuracy of estimated optical flows and require additional models or information to compensate for flow estimation errors. Following the recent development in using deformable convolution (DConv) for video interpolation, we propose a light but effective model, called Pyramid Deformable Warping Network (PDWN). PDWN uses a pyramid structure to generate DConv offsets of the unknown middle frame with respect to the known frames through coarse-to-fine successive refinements. Cost volumes between warped features are calculated at every pyramid level to help the offset inference. At the finest scale, the two warped frames are adaptively blended to generate the middle frame. Lastly, a context enhancement network further enhances the contextual detail of the final output. Ablation studies demonstrate the effectiveness of the coarse-to-fine offset refinement, cost volumes, and DConv. Our method achieves better or on-par accuracy compared to state-of-the-art models on multiple datasets while the number of model parameters and the inference time are substantially less than previous models. Moreover, we present an extension of the proposed framework to use four input frames, which can achieve significant improvement over using only two input frames, with only a slight increase in the model size and inference time.

Haojie Liu, Ming Lu, Zhan Ma et al.

Over the past two decades, traditional block-based video coding has made remarkable progress and spawned a series of well-known standards such as MPEG-4, H.264/AVC and H.265/HEVC. On the other hand, deep neural networks (DNNs) have shown their powerful capacity for visual content understanding, feature extraction and compact representation. Some previous works have explored the learnt video coding algorithms in an end-to-end manner, which show the great potential compared with traditional methods. In this paper, we propose an end-to-end deep neural video coding framework (NVC), which uses variational autoencoders (VAEs) with joint spatial and temporal prior aggregation (PA) to exploit the correlations in intra-frame pixels, inter-frame motions and inter-frame compensation residuals, respectively. Novel features of NVC include: 1) To estimate and compensate motion over a large range of magnitudes, we propose an unsupervised multiscale motion compensation network (MS-MCN) together with a pyramid decoder in the VAE for coding motion features that generates multiscale flow fields, 2) we design a novel adaptive spatiotemporal context model for efficient entropy coding for motion information, 3) we adopt nonlocal attention modules (NLAM) at the bottlenecks of the VAEs for implicit adaptive feature extraction and activation, leveraging its high transformation capacity and unequal weighting with joint global and local information, and 4) we introduce multi-module optimization and a multi-frame training strategy to minimize the temporal error propagation among P-frames. NVC is evaluated for the low-delay causal settings and compared with H.265/HEVC, H.264/AVC and the other learnt video compression methods following the common test conditions, demonstrating consistent gains across all popular test sequences for both PSNR and MS-SSIM distortion metrics.

Haojie Liu, Kang Liao, Chunyu Lin et al.

Pseudo-LiDAR point cloud interpolation is a novel and challenging task in the field of autonomous driving, which aims to address the frequency mismatching problem between camera and LiDAR. Previous works represent the 3D spatial motion relationship induced by a coarse 2D optical flow, and the quality of interpolated point clouds only depends on the supervision of depth maps. As a result, the generated point clouds suffer from inferior global distributions and local appearances. To solve the above problems, we propose a Pseudo-LiDAR point cloud interpolation network to generates temporally and spatially high-quality point cloud sequences. By exploiting the scene flow between point clouds, the proposed network is able to learn a more accurate representation of the 3D spatial motion relationship. For the more comprehensive perception of the distribution of point cloud, we design a novel reconstruction loss function that implements the chamfer distance to supervise the generation of Pseudo-LiDAR point clouds in 3D space. In addition, we introduce a multi-modal deep aggregation module to facilitate the efficient fusion of texture and depth features. As the benefits of the improved motion representation, training loss function, and model structure, our approach gains significant improvements on the Pseudo-LiDAR point cloud interpolation task. The experimental results evaluated on KITTI dataset demonstrate the state-of-the-art performance of the proposed network, quantitatively and qualitatively.

Qi Xia, Haojie Liu, Zhan Ma

The Object-Based Image Coding (OBIC) that was extensively studied about two decades ago, promised a vast application perspective for both ultra-low bitrate communication and high-level semantical content understanding, but it had rarely been used due to the inefficient compact representation of object with arbitrary shape. A fundamental issue behind is how to efficiently process the arbitrary-shaped objects at a fine granularity (e.g., feature element or pixel wise). To attack this, we have proposed to apply the element-wise masking and compression by devising an object segmentation network for image layer decomposition, and parallel convolution-based neural image compression networks to process masked foreground objects and background scene separately. All components are optimized in an end-to-end learning framework to intelligently weigh their (e.g., object and background) contributions for visually pleasant reconstruction. We have conducted comprehensive experiments to evaluate the performance on PASCAL VOC dataset at a very low bitrate scenario (e.g., $\lesssim$0.1 bits per pixel - bpp) which have demonstrated noticeable subjective quality improvement compared with JPEG2K, HEVC-based BPG and another learned image compression method. All relevant materials are made publicly accessible at https://njuvision.github.io/Neural-Object-Coding/.

Haojie Liu, Han shen, Lichao Huang et al.

Traditional video compression technologies have been developed over decades in pursuit of higher coding efficiency. Efficient temporal information representation plays a key role in video coding. Thus, in this paper, we propose to exploit the temporal correlation using both first-order optical flow and second-order flow prediction. We suggest an one-stage learning approach to encapsulate flow as quantized features from consecutive frames which is then entropy coded with adaptive contexts conditioned on joint spatial-temporal priors to exploit second-order correlations. Joint priors are embedded in autoregressive spatial neighbors, co-located hyper elements and temporal neighbors using ConvLSTM recurrently. We evaluate our approach for the low-delay scenario with High-Efficiency Video Coding (H.265/HEVC), H.264/AVC and another learned video compression method, following the common test settings. Our work offers the state-of-the-art performance, with consistent gains across all popular test sequences.

Ming Cheng, Zhan Ma, M. Salman Asif et al.

This paper presents a dual camera system for high spatiotemporal resolution (HSTR) video acquisition, where one camera shoots a video with high spatial resolution and low frame rate (HSR-LFR) and another one captures a low spatial resolution and high frame rate (LSR-HFR) video. Our main goal is to combine videos from LSR-HFR and HSR-LFR cameras to create an HSTR video. We propose an end-to-end learning framework, AWnet, mainly consisting of a FlowNet and a FusionNet that learn an adaptive weighting function in pixel domain to combine inputs in a frame recurrent fashion. To improve the reconstruction quality for cameras used in reality, we also introduce noise regularization under the same framework. Our method has demonstrated noticeable performance gains in terms of both objective PSNR measurement in simulation with different publicly available video and light-field datasets and subjective evaluation with real data captured by dual iPhone 7 and Grasshopper3 cameras. Ablation studies are further conducted to investigate and explore various aspects (such as reference structure, camera parallax, exposure time, etc) of our system to fully understand its capability for potential applications.

Jianqiang Wang, Hao Zhu, Zhan Ma et al.

This paper presents a novel end-to-end Learned Point Cloud Geometry Compression (a.k.a., Learned-PCGC) framework, to efficiently compress the point cloud geometry (PCG) using deep neural networks (DNN) based variational autoencoders (VAE). In our approach, PCG is first voxelized, scaled and partitioned into non-overlapped 3D cubes, which is then fed into stacked 3D convolutions for compact latent feature and hyperprior generation. Hyperpriors are used to improve the conditional probability modeling of latent features. A weighted binary cross-entropy (WBCE) loss is applied in training while an adaptive thresholding is used in inference to remove unnecessary voxels and reduce the distortion. Objectively, our method exceeds the geometry-based point cloud compression (G-PCC) algorithm standardized by well-known Moving Picture Experts Group (MPEG) with a significant performance margin, e.g., at least 60% BD-Rate (Bjontegaard Delta Rate) gains, using common test datasets. Subjectively, our method has presented better visual quality with smoother surface reconstruction and appealing details, in comparison to all existing MPEG standard compliant PCC methods. Our method requires about 2.5MB parameters in total, which is a fairly small size for practical implementation, even on embedded platform. Additional ablation studies analyze a variety of aspects (e.g., cube size, kernels, etc) to explore the application potentials of our learned-PCGC.

Haojie Liu, Kang Liao, Chunyu Lin et al.

LiDAR sensors can provide dependable 3D spatial information at a low frequency (around 10Hz) and have been widely applied in the field of autonomous driving and UAV. However, the camera with a higher frequency (around 20Hz) has to be decreased so as to match with LiDAR in a multi-sensor system. In this paper, we propose a novel Pseudo-LiDAR interpolation network (PLIN) to increase the frequency of LiDAR sensors. PLIN can generate temporally and spatially high-quality point cloud sequences to match the high frequency of cameras. To achieve this goal, we design a coarse interpolation stage guided by consecutive sparse depth maps and motion relationship. We also propose a refined interpolation stage guided by the realistic scene. Using this coarse-to-fine cascade structure, our method can progressively perceive multi-modal information and generate accurate intermediate point clouds. To the best of our knowledge, this is the first deep framework for Pseudo-LiDAR point cloud interpolation, which shows appealing applications in navigation systems equipped with LiDAR and cameras. Experimental results demonstrate that PLIN achieves promising performance on the KITTI dataset, significantly outperforming the traditional interpolation method and the state-of-the-art video interpolation technique.

Haojie Liu, Tong Chen, Peiyao Guo et al.

This paper proposes a novel Non-Local Attention Optimized Deep Image Compression (NLAIC) framework, which is built on top of the popular variational auto-encoder (VAE) structure. Our NLAIC framework embeds non-local operations in the encoders and decoders for both image and latent feature probability information (known as hyperprior) to capture both local and global correlations, and apply attention mechanism to generate masks that are used to weigh the features for the image and hyperprior, which implicitly adapt bit allocation for different features based on their importance. Furthermore, both hyperpriors and spatial-channel neighbors of the latent features are used to improve entropy coding. The proposed model outperforms the existing methods on Kodak dataset, including learned (e.g., Balle2019, Balle2018) and conventional (e.g., BPG, JPEG2000, JPEG) image compression methods, for both PSNR and MS-SSIM distortion metrics.

Chao Huang, Haojie Liu, Tong Chen et al.

We propose a MultiScale AutoEncoder(MSAE) based extreme image compression framework to offer visually pleasing reconstruction at a very low bitrate. Our method leverages the "priors" at different resolution scale to improve the compression efficiency, and also employs the generative adversarial network(GAN) with multiscale discriminators to perform the end-to-end trainable rate-distortion optimization. We compare the perceptual quality of our reconstructions with traditional compression algorithms using High-Efficiency Video Coding(HEVC) based Intra Profile and JPEG2000 on the public Cityscapes and ADE20K datasets, demonstrating the significant subjective quality improvement.

Haojie Liu, Tong Chen, Qiu Shen et al.

We present a lossy image compression method based on deep convolutional neural networks (CNNs), which outperforms the existing BPG, WebP, JPEG2000 and JPEG as measured via multi-scale structural similarity (MS-SSIM), at the same bit rate. Currently, most of the CNNs based approaches train the network using a L2 loss between the reconstructions and the ground-truths in the pixel domain, which leads to over-smoothing results and visual quality degradation especially at a very low bit rate. Therefore, we improve the subjective quality with the combination of a perception loss and an adversarial loss additionally. To achieve better rate-distortion optimization (RDO), we also introduce an easy-to-hard transfer learning when adding quantization error and rate constraint. Finally, we evaluate our method on public Kodak and the Test Dataset P/M released by the Computer Vision Lab of ETH Zurich, resulting in averaged 7.81% and 19.1% BD-rate reduction over BPG, respectively.