With diffusion transformer (DiT) excelling in video generation, its use in specific tasks has drawn increasing attention. However, adapting DiT for pose-guided human image animation faces two core challenges: (a) existing U-Net-based pose control methods may be suboptimal for the DiT backbone; and (b) removing text guidance, as in previous approaches, often leads to semantic loss and model degradation. To address these issues, we propose DynamiCtrl, a novel framework for human animation in video DiT architecture. Specifically, we use a shared VAE encoder for human images and driving poses, unifying them into a common latent space, maintaining pose fidelity, and eliminating the need for an expert pose encoder during video denoising. To integrate pose control into the DiT backbone effectively, we propose a novel Pose-adaptive Layer Norm model. It injects normalized pose features into the denoising process via conditioning on visual tokens, enabling seamless and scalable pose control across DiT blocks. Furthermore, to overcome the shortcomings of text removal, we introduce the "Joint-text" paradigm, which preserves the role of text embeddings to provide global semantic context. Through full-attention blocks, image and pose features are aligned with text features, enhancing semantic consistency, leveraging pretrained knowledge, and enabling multi-level control. Experiments verify the superiority of DynamiCtrl on benchmark and self-collected data (e.g., achieving the best LPIPS of 0.166), demonstrating strong character control and high-quality synthesis. The project page is available at https://gulucaptain.github.io/DynamiCtrl/.
Self-supervised video denoising aims to remove noise from videos without relying on ground truth data, leveraging the video itself to recover clean frames. Existing methods often rely on simplistic feature stacking or apply optical flow without thorough analysis. This results in suboptimal utilization of both inter-frame and intra-frame information, and it also neglects the potential of optical flow alignment under self-supervised conditions, leading to biased and insufficient denoising outcomes. To this end, we first explore the practicality of optical flow in the self-supervised setting and introduce a SpatioTemporal Blind-spot Network (STBN) for global frame feature utilization. In the temporal domain, we utilize bidirectional blind-spot feature propagation through the proposed blind-spot alignment block to ensure accurate temporal alignment and effectively capture long-range dependencies. In the spatial domain, we introduce the spatial receptive field expansion module, which enhances the receptive field and improves global perception capabilities. Additionally, to reduce the sensitivity of optical flow estimation to noise, we propose an unsupervised optical flow distillation mechanism that refines fine-grained inter-frame interactions during optical flow alignment. Our method demonstrates superior performance across both synthetic and real-world video denoising datasets. The source code is publicly available at https://github.com/ZKCCZ/STBN.
Current frontier video diffusion models have demonstrated remarkable results at generating high-quality videos. However, they can only generate short video clips, normally around 10 seconds or 240 frames, due to computation limitations during training. Existing methods naively achieve autoregressive long video generation by directly placing the ending of the previous clip at the front of the attention window as conditioning, which leads to abrupt scene changes, unnatural motion, and error accumulation. In this work, we introduce a more natural formulation of autoregressive long video generation by revisiting the noise level assumption in video diffusion models. Our key idea is to 1. assign the frames with per-frame, progressively increasing noise levels rather than a single noise level and 2. denoise and shift the frames in small intervals rather than all at once. This allows for smoother attention correspondence among frames with adjacent noise levels, larger overlaps between the attention windows, and better propagation of information from the earlier to the later frames. Video diffusion models equipped with our progressive noise schedule can autoregressively generate long videos with much improved fidelity compared to the baselines and minimal quality degradation over time. We present the first results on text-conditioned 60-second (1440 frames) long video generation at a quality close to frontier models. Code and video results are available at https://desaixie.github.io/pa-vdm/.
One key challenge to video restoration is to model the transition dynamics of video frames governed by motion. In this work, we propose TURTLE to learn the truncated causal history model for efficient and high-performing video restoration. Unlike traditional methods that process a range of contextual frames in parallel, TURTLE enhances efficiency by storing and summarizing a truncated history of the input frame latent representation into an evolving historical state. This is achieved through a sophisticated similarity-based retrieval mechanism that implicitly accounts for inter-frame motion and alignment. The causal design in TURTLE enables recurrence in inference through state-memorized historical features while allowing parallel training by sampling truncated video clips. We report new state-of-the-art results on a multitude of video restoration benchmark tasks, including video desnowing, nighttime video deraining, video raindrops and rain streak removal, video super-resolution, real-world and synthetic video deblurring, and blind video denoising while reducing the computational cost compared to existing best contextual methods on all these tasks.
Recent advancements in deep learning have shown impressive results in image and video denoising, leveraging extensive pairs of noisy and noise-free data for supervision. However, the challenge of acquiring paired videos for dynamic scenes hampers the practical deployment of deep video denoising techniques. In contrast, this obstacle is less pronounced in image denoising, where paired data is more readily available. Thus, a well-trained image denoiser could serve as a reliable spatial prior for video denoising. In this paper, we propose a novel unsupervised video denoising framework, named ``Temporal As a Plugin'' (TAP), which integrates tunable temporal modules into a pre-trained image denoiser. By incorporating temporal modules, our method can harness temporal information across noisy frames, complementing its power of spatial denoising. Furthermore, we introduce a progressive fine-tuning strategy that refines each temporal module using the generated pseudo clean video frames, progressively enhancing the network's denoising performance. Compared to other unsupervised video denoising methods, our framework demonstrates superior performance on both sRGB and raw video denoising datasets.
Image denoising is an appealing and challenging task, in that noise statistics of real-world observations may vary with local image contents and different image channels. Specifically, the green channel usually has twice the sampling rate in raw data. To handle noise variances and leverage such channel-wise prior information, we propose a simple and effective green channel prior-based image denoising (GCP-ID) method, which integrates GCP into the classic patch-based denoising framework. Briefly, we exploit the green channel to guide the search for similar patches, which aims to improve the patch grouping quality and encourage sparsity in the transform domain. The grouped image patches are then reformulated into RGGB arrays to explicitly characterize the density of green samples. Furthermore, to enhance the adaptivity of GCP-ID to various image contents, we cast the noise estimation problem into a classification task and train an effective estimator based on convolutional neural networks (CNNs). Experiments on real-world datasets demonstrate the competitive performance of the proposed GCP-ID method for image and video denoising applications in both raw and sRGB spaces. Our code is available at https://github.com/ZhaomingKong/GCP-ID.
Significant advances have been made in human-centric video generation, yet the joint video-depth generation problem remains underexplored. Most existing monocular depth estimation methods may not generalize well to synthesized images or videos, and multi-view-based methods have difficulty controlling the human appearance and motion. In this work, we present IDOL (unIfied Dual-mOdal Latent diffusion) for high-quality human-centric joint video-depth generation. Our IDOL consists of two novel designs. First, to enable dual-modal generation and maximize the information exchange between video and depth generation, we propose a unified dual-modal U-Net, a parameter-sharing framework for joint video and depth denoising, wherein a modality label guides the denoising target, and cross-modal attention enables the mutual information flow. Second, to ensure a precise video-depth spatial alignment, we propose a motion consistency loss that enforces consistency between the video and depth feature motion fields, leading to harmonized outputs. Additionally, a cross-attention map consistency loss is applied to align the cross-attention map of the video denoising with that of the depth denoising, further facilitating spatial alignment. Extensive experiments on the TikTok and NTU120 datasets show our superior performance, significantly surpassing existing methods in terms of video FVD and depth accuracy.
This paper introduces a method for zero-shot video restoration using pre-trained image restoration diffusion models. Traditional video restoration methods often need retraining for different settings and struggle with limited generalization across various degradation types and datasets. Our approach uses a hierarchical token merging strategy for keyframes and local frames, combined with a hybrid correspondence mechanism that blends optical flow and feature-based nearest neighbor matching (latent merging). We show that our method not only achieves top performance in zero-shot video restoration but also significantly surpasses trained models in generalization across diverse datasets and extreme degradations (8$\times$ super-resolution and high-standard deviation video denoising). We present evidence through quantitative metrics and visual comparisons on various challenging datasets. Additionally, our technique works with any 2D restoration diffusion model, offering a versatile and powerful tool for video enhancement tasks without extensive retraining. This research leads to more efficient and widely applicable video restoration technologies, supporting advancements in fields that require high-quality video output. See our project page for video results and source code at https://jimmycv07.github.io/DiffIR2VR_web/.
Noise removal in the standard RGB (sRGB) space remains a challenging task, in that the noise statistics of real-world images can be different in R, G and B channels. In fact, the green channel usually has twice the sampling rate in raw data and a higher signal-to-noise ratio than red/blue ones. However, the green channel prior (GCP) is often understated or ignored in color image denoising since many existing approaches mainly focus on modeling the relationship among image patches. In this paper, we propose a simple and effective one step GCP-based image denoising (GCP-ID) method, which aims to exploit the GCP for denoising in the sRGB space by integrating it into the classic nonlocal transform domain denoising framework. Briefly, we first take advantage of the green channel to guide the search of similar patches, which improves the patch search quality and encourages sparsity in the transform domain. Then we reformulate RGB patches into RGGB arrays to explicitly characterize the density of green samples. The block circulant representation is utilized to capture the cross-channel correlation and the channel redundancy. Experiments on both synthetic and real-world datasets demonstrate the competitive performance of the proposed GCP-ID method for the color image and video denoising tasks. The code is available at github.com/ZhaomingKong/GCP-ID.
Denoising and demosaicking are two fundamental steps in reconstructing a clean full-color video from raw data, while performing video denoising and demosaicking jointly, namely VJDD, could lead to better video restoration performance than performing them separately. In addition to restoration accuracy, another key challenge to VJDD lies in the temporal consistency of consecutive frames. This issue exacerbates when perceptual regularization terms are introduced to enhance video perceptual quality. To address these challenges, we present a new VJDD framework by consistent and accurate latent space propagation, which leverages the estimation of previous frames as prior knowledge to ensure consistent recovery of the current frame. A data temporal consistency (DTC) loss and a relational perception consistency (RPC) loss are accordingly designed. Compared with the commonly used flow-based losses, the proposed losses can circumvent the error accumulation problem caused by inaccurate flow estimation and effectively handle intensity changes in videos, improving much the temporal consistency of output videos while preserving texture details. Extensive experiments demonstrate the leading VJDD performance of our method in term of restoration accuracy, perceptual quality and temporal consistency. Codes and dataset are available at \url{https://github.com/GuoShi28/VJDD}.
We propose an approach to do learning in Gaussian factor graphs. We treat all relevant quantities (inputs, outputs, parameters, latents) as random variables in a graphical model, and view both training and prediction as inference problems with different observed nodes. Our experiments show that these problems can be efficiently solved with belief propagation (BP), whose updates are inherently local, presenting exciting opportunities for distributed and asynchronous training. Our approach can be scaled to deep networks and provides a natural means to do continual learning: use the BP-estimated parameter marginals of the current task as parameter priors for the next. On a video denoising task we demonstrate the benefit of learnable parameters over a classical factor graph approach and we show encouraging performance of deep factor graphs for continual image classification.
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 this paper, we propose a Bidirectional Streaming Video Denoising (BSVD) framework, to achieve high-fidelity real-time denoising for streaming videos with both past and future temporal receptive fields. The bidirectional temporal fusion for online inference is considered not applicable in the MoViNet. However, we introduce a novel Bidirectional Buffer Block as the core module of our BSVD, which makes it possible during our pipeline-style inference. In addition, our method is concise and flexible to be utilized in both non-blind and blind video denoising. We compare our model with various state-of-the-art video denoising models qualitatively and quantitatively on synthetic and real noise. Our method outperforms previous methods in terms of restoration fidelity and runtime. Our source code is publicly available at https://github.com/ChenyangQiQi/BSVD
Despite the quality improvement brought by the recent methods, video super-resolution (SR) is still very challenging, especially for videos that are low-light and noisy. The current best solution is to subsequently employ best models of video SR, denoising, and illumination enhancement, but doing so often lowers the image quality, due to the inconsistency between the models. This paper presents a new parametric representation called the Deep Parametric 3D Filters (DP3DF), which incorporates local spatiotemporal information to enable simultaneous denoising, illumination enhancement, and SR efficiently in a single encoder-and-decoder network. Also, a dynamic residual frame is jointly learned with the DP3DF via a shared backbone to further boost the SR quality. We performed extensive experiments, including a large-scale user study, to show our method's effectiveness. Our method consistently surpasses the best state-of-the-art methods on all the challenging real datasets with top PSNR and user ratings, yet having a very fast run time.
Video restoration, which aims to restore clear frames from degraded videos, has numerous important applications. The key to video restoration depends on utilizing inter-frame information. However, existing deep learning methods often rely on complicated network architectures, such as optical flow estimation, deformable convolution, and cross-frame self-attention layers, resulting in high computational costs. In this study, we propose a simple yet effective framework for video restoration. Our approach is based on grouped spatial-temporal shift, which is a lightweight and straightforward technique that can implicitly capture inter-frame correspondences for multi-frame aggregation. By introducing grouped spatial shift, we attain expansive effective receptive fields. Combined with basic 2D convolution, this simple framework can effectively aggregate inter-frame information. Extensive experiments demonstrate that our framework outperforms the previous state-of-the-art method, while using less than a quarter of its computational cost, on both video deblurring and video denoising tasks. These results indicate the potential for our approach to significantly reduce computational overhead while maintaining high-quality results. Code is avaliable at https://github.com/dasongli1/Shift-Net.
Video restoration aims at restoring multiple high-quality frames from multiple low-quality frames. Existing video restoration methods generally fall into two extreme cases, i.e., they either restore all frames in parallel or restore the video frame by frame in a recurrent way, which would result in different merits and drawbacks. Typically, the former has the advantage of temporal information fusion. However, it suffers from large model size and intensive memory consumption; the latter has a relatively small model size as it shares parameters across frames; however, it lacks long-range dependency modeling ability and parallelizability. In this paper, we attempt to integrate the advantages of the two cases by proposing a recurrent video restoration transformer, namely RVRT. RVRT processes local neighboring frames in parallel within a globally recurrent framework which can achieve a good trade-off between model size, effectiveness, and efficiency. Specifically, RVRT divides the video into multiple clips and uses the previously inferred clip feature to estimate the subsequent clip feature. Within each clip, different frame features are jointly updated with implicit feature aggregation. Across different clips, the guided deformable attention is designed for clip-to-clip alignment, which predicts multiple relevant locations from the whole inferred clip and aggregates their features by the attention mechanism. Extensive experiments on video super-resolution, deblurring, and denoising show that the proposed RVRT achieves state-of-the-art performance on benchmark datasets with balanced model size, testing memory and runtime.
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 denoising. Particularly, look-ahead module is an elaborate forward module for leveraging information from near-future frames. When denoising the current frame, the hidden features by forward and look-ahead recurrent modules are combined, thereby making it feasible to exploit both historical and near-future frames. Due to the scene motion between non-neighboring frames, border pixels missing may occur when warping look-ahead feature from near-future frame to current frame, which can be largely alleviated by incorporating forward warping and proposed border enlargement. Experiments show that our method achieves state-of-the-art performance with constant latency and memory consumption. Code is avaliable at https://github.com/nagejacob/FloRNN.
In video denoising, the adjacent frames often provide very useful information, but accurate alignment is needed before such information can be harnassed. In this work, we present a multi-alignment network, which generates multiple flow proposals followed by attention-based averaging. It serves to mimic the non-local mechanism, suppressing noise by averaging multiple observations. Our approach can be applied to various state-of-the-art models that are based on flow estimation. Experiments on a large-scale video dataset demonstrate that our method improves the denoising baseline model by 0.2dB, and further reduces the parameters by 47% with model distillation. Code is available at https://github.com/IndigoPurple/MANet.
Video restoration (e.g., video super-resolution) aims to restore high-quality frames from low-quality frames. Different from single image restoration, video restoration generally requires to utilize temporal information from multiple adjacent but usually misaligned video frames. Existing deep methods generally tackle with this by exploiting a sliding window strategy or a recurrent architecture, which either is restricted by frame-by-frame restoration or lacks long-range modelling ability. In this paper, we propose a Video Restoration Transformer (VRT) with parallel frame prediction and long-range temporal dependency modelling abilities. More specifically, VRT is composed of multiple scales, each of which consists of two kinds of modules: temporal mutual self attention (TMSA) and parallel warping. TMSA divides the video into small clips, on which mutual attention is applied for joint motion estimation, feature alignment and feature fusion, while self attention is used for feature extraction. To enable cross-clip interactions, the video sequence is shifted for every other layer. Besides, parallel warping is used to further fuse information from neighboring frames by parallel feature warping. Experimental results on five tasks, including video super-resolution, video deblurring, video denoising, video frame interpolation and space-time video super-resolution, demonstrate that VRT outperforms the state-of-the-art methods by large margins ($\textbf{up to 2.16dB}$) on fourteen benchmark datasets.
We propose a novel neural representation for videos (NeRV) which encodes videos in neural networks. Unlike conventional representations that treat videos as frame sequences, we represent videos as neural networks taking frame index as input. Given a frame index, NeRV outputs the corresponding RGB image. Video encoding in NeRV is simply fitting a neural network to video frames and decoding process is a simple feedforward operation. As an image-wise implicit representation, NeRV output the whole image and shows great efficiency compared to pixel-wise implicit representation, improving the encoding speed by 25x to 70x, the decoding speed by 38x to 132x, while achieving better video quality. With such a representation, we can treat videos as neural networks, simplifying several video-related tasks. For example, conventional video compression methods are restricted by a long and complex pipeline, specifically designed for the task. In contrast, with NeRV, we can use any neural network compression method as a proxy for video compression, and achieve comparable performance to traditional frame-based video compression approaches (H.264, HEVC \etc). Besides compression, we demonstrate the generalization of NeRV for video denoising. The source code and pre-trained model can be found at https://github.com/haochen-rye/NeRV.git.
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 operate on the whole image, leveraging non-local relations only implicitly by using a large receptive field. This work proposes a novel approach for leveraging self-similarity in the context of video denoising, while still relying on a regular convolutional architecture. We introduce a concept of patch-craft frames - artificial frames that are similar to the real ones, built by tiling matched patches. Our algorithm augments video sequences with patch-craft frames and feeds them to a CNN. We demonstrate the substantial boost in denoising performance obtained with the proposed approach.