While video generation models excel at producing high-quality monocular videos, generating 3D stereoscopic and spatial videos for immersive applications remains an underexplored challenge. We present a pose-free and training-free method that leverages an off-the-shelf monocular video generation model to produce immersive 3D videos. Our approach first warps the generated monocular video into pre-defined camera viewpoints using estimated depth information, then applies a novel \textit{frame matrix} inpainting framework. This framework utilizes the original video generation model to synthesize missing content across different viewpoints and timestamps, ensuring spatial and temporal consistency without requiring additional model fine-tuning. Moreover, we develop a \dualupdate~scheme that further improves the quality of video inpainting by alleviating the negative effects propagated from disoccluded areas in the latent space. The resulting multi-view videos are then adapted into stereoscopic pairs or optimized into 4D Gaussians for spatial video synthesis. We validate the efficacy of our proposed method by conducting experiments on videos from various generative models, such as Sora, Lumiere, WALT, and Zeroscope. The experiments demonstrate that our method has a significant improvement over previous methods. Project page at: https://daipengwa.github.io/S-2VG_ProjectPage/
Mannheim University of Applied Sciences（曼海姆应用科学大学）；Magdeburg University（马格德堡大学）；Heidelberg University Hospital（海德堡大学医院）
Phantoms for surgical training are able to mimic cutting and suturing properties and patient-individual shape of organs, but lack a realistic visual appearance that captures the heterogeneity of surgical scenes. In order to overcome this in endoscopic approaches, hyperrealistic concepts have been proposed to be used in an augmented reality-setting, which are based on deep image-to-image transformation methods. Such concepts are able to generate realistic representations of phantoms learned from real intraoperative endoscopic sequences. Conditioned on frames from the surgical training process, …
Less Cybersickness, Please: Demystifying and Detecting Stereoscopic Visual Inconsistencies in Virtual Reality Apps
The Chinese University of Hong Kong（香港中文大学）；Harbin Institute of Technology（哈尔滨工业大学）；Research Institute of Trustworthy Autonomous Systems（可信自主系统研究院）；Southern University of Science and Technology（南方科技大学）
Magnetic resonance imaging (MRI) is a common and life-saving medical imaging technique. However, acquiring high signal-to-noise ratio MRI scans requires long scan times, resulting in increased costs and patient discomfort, and decreased throughput. Thus, there is great interest in denoising MRI scans, especially for the subtype of diffusion MRI scans that are severely SNR-limited. While most prior MRI denoising methods are supervised in nature, acquiring supervised training datasets for the multitude of anatomies, MRI scanners, and scan parameters proves impractical. Here, we propose Denoising…
Bahcesehir University（巴赫切谢希尔大学）；American University of Malta（马耳他美国大学）；Multimedia University（多媒体大学）
Stereo video super-resolution (SVSR) aims to enhance the spatial resolution of the low-resolution video by reconstructing the high-resolution video. The key challenges in SVSR are preserving the stereo-consistency and temporal-consistency, without which viewers may experience 3D fatigue. There are several notable works on stereoscopic image super-resolution, but there is little research on stereo video super-resolution. In this paper, we propose a novel Transformer-based model for SVSR, namely Trans-SVSR. Trans-SVSR comprises two key novel components: a spatio-temporal convolutional self-atten…
Shanghai Jiao Tong University（上海交通大学）；Cooperative Medianet Innovation Center（未来媒体网络协同创新中心）；University of California at Riverside（加州大学河滨分校）；Nanjing University（南京大学）
High-speed, high-resolution stereoscopic (H2-Stereo) video allows us to perceive dynamic 3D content at fine granularity. The acquisition of H2-Stereo video, however, remains challenging with commodity cameras. Existing spatial super-resolution or temporal frame interpolation methods provide compromised solutions that lack temporal or spatial details, respectively. To alleviate this problem, we propose a dual camera system, in which one camera captures high-spatial-resolution low-frame-rate (HSR-LFR) videos with rich spatial details, and the other captures low-spatial-resolution high-frame-rate…
Indian Institute of Technology Hyderabad（印度理工学院海得拉巴分校）
We present a no reference (NR) quality assessment algorithm for assessing the perceptual quality of natural stereoscopic 3D (S3D) videos. This work is inspired by our finding that the joint statistics of the subband coefficients of motion (optical flow or motion vector magnitude) and depth (disparity map) of natural S3D videos possess a unique signature. Specifically, we empirically show that the joint statistics of the motion and depth subband coefficients of S3D video frames can be modeled accurately using a Bivariate Generalized Gaussian Distribution (BGGD). We then demonstrate that the par…
Modeling the processing chain that has produced a video is a difficult reverse engineering task, even when the camera is available. This makes model based video processing a still more complex task. In this paper we propose a fully blind video denoising method, with two versions off-line and on-line. This is achieved by fine-tuning a pre-trained AWGN denoising network to the video with a novel frame-to-frame training strategy. Our denoiser can be used without knowledge of the origin of the video or burst and the post processing steps applied from the camera sensor. The on-line process only req…
We propose a self-supervised approach for training multi-frame video denoising networks. These networks predict frame t from a window of frames around t. Our self-supervised approach benefits from the video temporal consistency by penalizing a loss between the predicted frame t and a neighboring target frame, which are aligned using an optical flow. We use the proposed strategy for online internal learning, where a pre-trained network is fine-tuned to denoise a new unknown noise type from a single video. After a few frames, the proposed fine-tuning reaches and sometimes surpasses the performan…
Peking University（北京大学）；National Biomedical Imaging Center, Peking University（北京大学国家生物医学成像中心）
The performance of learning-based denoising largely depends on clean supervision. However, it is difficult to obtain clean images in many scenes. On the contrary, the capture of multiple noisy frames for the same field of view is available and often natural in real life. Therefore, it is necessary to avoid the restriction of clean labels and make full use of noisy data for model training. So we propose an unsupervised learning strategy named one-pot denoising (OPD) for multi-frame images. OPD is the first proposed unsupervised multi-frame denoising (MFD) method. Different from the traditional …
Harbin Institute of Technology（哈尔滨工业大学）；Xidian University（西安电子科技大学）
While significant progress has been made in deep video denoising, it remains very challenging for exploiting historical and future frames. Bidirectional recurrent networks (BiRNN) have exhibited appealing performance in several video restoration tasks. However, BiRNN is intrinsically offline because it uses backward recurrent modules to propagate from the last to current frames, which causes high latency and large memory consumption. To address the offline issue of BiRNN, we present a novel recurrent network consisting of forward and look-ahead recurrent modules for unidirectional video denois…
Sparse representation of images under certain transform domain has been playing a fundamental role in image restoration tasks. One such representative method is the widely used wavelet tight frame systems. Instead of adopting fixed filters for constructing a tight frame to sparsely model any input image, a data-driven tight frame was proposed for the sparse representation of images, and shown to be very efficient for image denoising very recently. However, in this method the number of framelet filters used for constructing a tight frame is the same as the length of filters. In fact, through fu…
TQD-Track: Temporal Query Denoising for 3D Multi-Object Tracking
Mercedes-Benz AG（梅赛德斯-奔驰股份公司）；University of Bonn（波恩大学）；University of Stuttgart（斯图加特大学）；University of Tübingen（蒂宾根大学）；Lamarr Institute for Machine Learning and Artificial Intelligence（拉马尔机器学习与人工智能研究所）
Optical coherence tomography (OCT) is an important interferometric diagnostic technique which provides cross-sectional views of the subsurface microstructure of biological tissues. However, the imaging quality of high-speed OCT is limited due to the large speckle noise. To address this problem, this paper proposes a multi-frame algorithmic method to denoise OCT volume. Mathematically, we build an optimization model which forces the temporally registered frames to be low rank, and the gradient in each frame to be sparse, under logarithmic image formation and noise variance constraints. Besides,…
The non-local self-similarity property of natural images has been exploited extensively for solving various image processing problems. When it comes to video sequences, harnessing this force is even more beneficial due to the temporal redundancy. In the context of image and video denoising, many classically-oriented algorithms employ self-similarity, splitting the data into overlapping patches, gathering groups of similar ones and processing these together somehow. With the emergence of convolutional neural networks (CNN), the patch-based framework has been abandoned. Most CNN denoisers operat…
Video streams are delivered continuously to save the cost of storage and device memory. Real-time denoising algorithms are typically adopted on the user device to remove the noise involved during the shooting and transmission of video streams. However, sliding-window-based methods feed multiple input frames for a single output and lack computation efficiency. Recent multi-output inference works propagate the bidirectional temporal feature with a parallel or recurrent framework, which either suffers from performance drops on the temporal edges of clips or can not achieve online inference. In th…
University of Illinois, Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of Michigan, Ann Arbor（密歇根大学安娜堡分校）
Techniques exploiting the sparsity of images in a transform domain have been effective for various applications in image and video processing. Transform learning methods involve cheap computations and have been demonstrated to perform well in applications such as image denoising and medical image reconstruction. Recently, we proposed methods for online learning of sparsifying transforms from streaming signals, which enjoy good convergence guarantees, and involve lower computational costs than online synthesis dictionary learning. In this work, we apply online transform learning to video denois…
Video denoising aims to recover high-quality frames from the noisy video. While most existing approaches adopt convolutional neural networks~(CNNs) to separate the noise from the original visual content, however, CNNs focus on local information and ignore the interactions between long-range regions in the frame. Furthermore, most related works directly take the output after basic spatio-temporal denoising as the final result, leading to neglect the fine-grained denoising process. In this paper, we propose a Dual-stage Spatial-Channel Transformer for coarse-to-fine video denoising, which inheri…
PPORLD-EDNetLDCT: A Proximal Policy Optimization-Based Reinforcement Learning Framework for Adaptive Low-Dose CT Denoising
Department of Computer Science and Engineering, United International University, Dhaka 1212, Bangladesh（United International University）；Faculty of Science and Technology, Charles Darwin University, Casuarina, NT 0909, Australia（Charles Darwin University）；Faculty of Science and Information Technology, Charles Darwin University, Sydney, NSW, Australia（Charles Darwin University）
The Chinese University of Hong Kong（香港中文大学）；SenseTime Research（商汤科技研究院）；Centre for Perceptual and Interactive Intelligence Limited（感知与交互智能中心有限公司）
With the growing popularity of smartphones, capturing high-quality images is of vital importance to smartphones. The cameras of smartphones have small apertures and small sensor cells, which lead to the noisy images in low light environment. Denoising based on a burst of multiple frames generally outperforms single frame denoising but with the larger compututional cost. In this paper, we propose an efficient yet effective burst denoising system. We adopt a three-stage design: noise prior integration, multi-frame alignment and multi-frame denoising. First, we integrate noise prior by pre-proces…
ZSky Technologies Inc（ZSky科技公司）；NanKai University（南开大学）；Chinese Academy of Sciences(CAS)（中国科学院）；Peng Cheng Laboratory(PCL)（鹏城实验室）
Video denoising is to remove noise from noise-corrupted data, thus recovering true signals via spatiotemporal processing. Existing approaches for spatiotemporal video denoising tend to suffer from motion blur artifacts, that is, the boundary of a moving object tends to appear blurry especially when the object undergoes a fast motion, causing optical flow calculation to break down. In this paper, we address this challenge by designing a first-image-then-video two-stage denoising neural network, consisting of an image denoising module for spatially reducing intra-frame noise followed by a regula…
Subjective and Objective Quality Assessment Methods of Stereoscopic Videos with Visibility Affecting Distortions
Indian Institute of Information Technology, Design and Manufacturing Kancheepuram（印度信息技术、设计与制造坎奇普兰学院）；Indian Institute of Technology Indore（印度印多尔理工学院）；Indian Institute of Technology Hyderabad（印度海得拉巴理工学院）
University of Electronic Science and Technology of China（电子科技大学）；Sichuan University（四川大学）
Deep learning has achieved notable performance in the denoising task of low-quality medical images and the detection task of lesions, respectively. However, existing low-quality medical image denoising approaches are disconnected from the detection task of lesions. Intuitively, the quality of denoised images will influence the lesion detection accuracy that in turn can be used to affect the denoising performance. To this end, we propose a play-and-plug medical image denoising framework, namely Lesion-Inspired Denoising Network (LIDnet), to collaboratively improve both denoising performance and…
Current video denoising methods perform temporal fusion by designing convolutional neural networks (CNN) or combine spatial denoising with temporal fusion into basic recurrent neural networks (RNNs). However, there have not yet been works which adapt gated recurrent unit (GRU) mechanisms for video denoising. In this letter, we propose a new video denoising model based on GRU, namely GRU-VD. First, the reset gate is employed to mark the content related to the current frame in the previous frame output. Then the hidden activation works as an initial spatial-temporal denoising with the help from …
Image denoising is of great importance for medical imaging system, since it can improve image quality for disease diagnosis and downstream image analyses. In a variety of applications, dynamic imaging techniques are utilized to capture the time-varying features of the subject, where multiple images are acquired for the same subject at different time points. Although signal-to-noise ratio of each time frame is usually limited by the short acquisition time, the correlation among different time frames can be exploited to improve denoising results with shared information across time frames. With t…
This paper considers the problem of signal denoising using a sparse tight-frame analysis prior. The L1 norm has been extensively used as a regularizer to promote sparsity; however, it tends to under-estimate non-zero values of the underlying signal. To more accurately estimate non-zero values, we propose the use of a non-convex regularizer, chosen so as to ensure convexity of the objective function. The convexity of the objective function is ensured by constraining the parameter of the non-convex penalty. We use ADMM to obtain a solution and show how to guarantee that ADMM converges to the glo…
The prevalence of accessible depth sensing and 3D laser scanning techniques has enabled the convenient acquisition of 3D dynamic point clouds, which provide efficient representation of arbitrarily-shaped objects in motion. Nevertheless, dynamic point clouds are often perturbed by noise due to hardware, software or other causes. While a plethora of methods have been proposed for static point cloud denoising, few efforts are made for the denoising of dynamic point clouds with varying number of irregularly-sampled points in each frame. In this paper, we represent dynamic point clouds naturally on…
Video Denoising is one of the fundamental tasks of any videoprocessing pipeline. It is different from image denoising due to the tem-poral aspects of video frames, and any image denoising approach appliedto videos will result in flickering. The proposed method makes use oftemporal as well as spatial dimensions of video frames as part of a two-stage pipeline. Each stage in the architecture named as Spatio-TemporalNetwork uses a channel-wise attention mechanism to forward the encodersignal to the decoder side. The Attention Block used in this paper usessoft attention to ranks the filters for bet…
In this paper, we propose a learning-based approach for denoising raw videos captured under low lighting conditions. We propose to do this by first explicitly aligning the neighboring frames to the current frame using a convolutional neural network (CNN). We then fuse the registered frames using another CNN to obtain the final denoised frame. To avoid directly aligning the temporally distant frames, we perform the two processes of alignment and fusion in multiple stages. Specifically, at each stage, we perform the denoising process on three consecutive input frames to generate the intermediate…
In this paper, we propose a pipeline for real-time video denoising with low runtime cost and high perceptual quality. The vast majority of denoising studies focus on image denoising. However, a minority of research works focusing on video denoising do so with higher performance costs to obtain higher quality while maintaining temporal coherence. The approach we introduce in this paper leverages the advantages of both image and video-denoising architectures. Our pipeline first denoises the keyframes or one-fifth of the frames using HI-GAN blind image denoising architecture. Then, the remaining …
Computer Vision Lab, ETH Zurich（苏黎世联邦理工学院计算机视觉实验室）
We propose a deep reparametrization of the maximum a posteriori formulation commonly employed in multi-frame image restoration tasks. Our approach is derived by introducing a learned error metric and a latent representation of the target image, which transforms the MAP objective to a deep feature space. The deep reparametrization allows us to directly model the image formation process in the latent space, and to integrate learned image priors into the prediction. Our approach thereby leverages the advantages of deep learning, while also benefiting from the principled multi-frame fusion provide…
