Video imaging is often affected by complex degradations such as blur, noise, and compression artifacts. Traditional restoration methods follow a "single-task single-model" paradigm, resulting in poor generalization and high computational cost, limiting their applicability in real-world scenarios with diverse degradation types. We propose UniFlowRestore, a general video restoration framework that models restoration as a time-continuous evolution under a prompt-guided and physics-informed vector field. A physics-aware backbone PhysicsUNet encodes degradation priors as potential energy, while PromptGenerator produces task-relevant prompts as momentum. These components define a Hamiltonian system whose vector field integrates inertial dynamics, decaying physical gradients, and prompt-based guidance. The system is optimized via a fixed-step ODE solver to achieve efficient and unified restoration across tasks. Experiments show that UniFlowRestore delivers stateof-the-art performance with strong generalization and efficiency. Quantitative results demonstrate that UniFlowRestore achieves state-of-the-art performance, attaining the highest PSNR (33.89 dB) and SSIM (0.97) on the video denoising task, while maintaining top or second-best scores across all evaluated tasks.
While deep neural network (DNN)-based video denoising has demonstrated significant performance, deploying state-of-the-art models on edge devices remains challenging due to stringent real-time and energy efficiency requirements. Computing-in-Memory (CIM) chips offer a promising solution by integrating computation within memory cells, enabling rapid matrix-vector multiplication (MVM). However, existing DNN models are often designed without considering CIM architectural constraints, thus limiting their acceleration potential during inference. To address this, we propose a hardware-algorithm co-design framework incorporating two innovations: (1) a CIM-Aware Architecture, CIM-NET, optimized for large receptive field operation and CIM's crossbar-based MVM acceleration; and (2) a pseudo-convolutional operator, CIM-CONV, used within CIM-NET to integrate slide-based processing with fully connected transformations for high-quality feature extraction and reconstruction. This framework significantly reduces the number of MVM operations, improving inference speed on CIM chips while maintaining competitive performance. Experimental results indicate that, compared to the conventional lightweight model FastDVDnet, CIM-NET substantially reduces MVM operations with a slight decrease in denoising performance. With a stride value of 8, CIM-NET reduces MVM operations to 1/77th of the original, while maintaining competitive PSNR (35.11 dB vs. 35.56 dB
Animating images with interactive motion control has garnered popularity for image-to-video (I2V) generation. Modern approaches typically rely on large Gaussian kernels to extend motion trajectories as condition without explicitly defining movement region, leading to coarse motion control and failing to disentangle object and camera moving. To alleviate these, we present MotionPro, a precise motion controller that novelly leverages region-wise trajectory and motion mask to regulate fine-grained motion synthesis and identify target motion category (i.e., object or camera moving), respectively. Technically, MotionPro first estimates the flow maps on each training video via a tracking model, and then samples the region-wise trajectories to simulate inference scenario. Instead of extending flow through large Gaussian kernels, our region-wise trajectory approach enables more precise control by directly utilizing trajectories within local regions, thereby effectively characterizing fine-grained movements. A motion mask is simultaneously derived from the predicted flow maps to capture the holistic motion dynamics of the movement regions. To pursue natural motion control, MotionPro further strengthens video denoising by incorporating both region-wise trajectories and motion mask through feature modulation. More remarkably, we meticulously construct a benchmark, i.e., MC-Bench, with 1.1K user-annotated image-trajectory pairs, for the evaluation of both fine-grained and object-level I2V motion control. Extensive experiments conducted on WebVid-10M and MC-Bench demonstrate the effectiveness of MotionPro. Please refer to our project page for more results: https://zhw-zhang.github.io/MotionPro-page/.
Denoising is a crucial step in many video processing pipelines such as in interactive editing, where high quality, speed, and user control are essential. While recent approaches achieve significant improvements in denoising quality by leveraging deep learning, they are prone to unexpected failures due to discrepancies between training data distributions and the wide variety of noise patterns found in real-world videos. These methods also tend to be slow and lack user control. In contrast, traditional denoising methods perform reliably on in-the-wild videos and run relatively quickly on modern hardware. However, they require manually tuning parameters for each input video, which is not only tedious but also requires skill. We bridge the gap between these two paradigms by proposing a differentiable denoising pipeline based on traditional methods. A neural network is then trained to predict the optimal denoising parameters for each specific input, resulting in a robust and efficient approach that also supports user control.
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/.
The first-in-first-out (FIFO) video diffusion, built on a pre-trained text-to-video model, has recently emerged as an effective approach for tuning-free long video generation. This technique maintains a queue of video frames with progressively increasing noise, continuously producing clean frames at the queue's head while Gaussian noise is enqueued at the tail. However, FIFO-Diffusion often struggles to keep long-range temporal consistency in the generated videos due to the lack of correspondence modeling across frames. In this paper, we propose Ouroboros-Diffusion, a novel video denoising framework designed to enhance structural and content (subject) consistency, enabling the generation of consistent videos of arbitrary length. Specifically, we introduce a new latent sampling technique at the queue tail to improve structural consistency, ensuring perceptually smooth transitions among frames. To enhance subject consistency, we devise a Subject-Aware Cross-Frame Attention (SACFA) mechanism, which aligns subjects across frames within short segments to achieve better visual coherence. Furthermore, we introduce self-recurrent guidance. This technique leverages information from all previous cleaner frames at the front of the queue to guide the denoising of noisier frames at the end, fostering rich and contextual global information interaction. Extensive experiments of long video generation on the VBench benchmark demonstrate the superiority of our Ouroboros-Diffusion, particularly in terms of subject consistency, motion smoothness, and temporal consistency.
Video restoration plays a pivotal role in revitalizing degraded video content by rectifying imperfections caused by various degradations introduced during capturing (sensor noise, motion blur, etc.), saving/sharing (compression, resizing, etc.) and editing. This paper introduces a novel algorithm designed for scenarios where noise is introduced during video capture, aiming to enhance the visual quality of videos by reducing unwanted noise artifacts. We propose the Latent space LSTM Video Denoiser (LLVD), an end-to-end blind denoising model. LLVD uniquely combines spatial and temporal feature extraction, employing Long Short Term Memory (LSTM) within the encoded feature domain. This integration of LSTM layers is crucial for maintaining continuity and minimizing flicker in the restored video. Moreover, processing frames in the encoded feature domain significantly reduces computations, resulting in a very lightweight architecture. LLVD's blind nature makes it versatile for real, in-the-wild denoising scenarios where prior information about noise characteristics is not available. Experiments reveal that LLVD demonstrates excellent performance for both synthetic and captured noise. Specifically, LLVD surpasses the current State-Of-The-Art (SOTA) in RAW denoising by 0.3dB, while also achieving a 59\% reduction in computational complexity.
Creating high-fidelity, coherent long videos is a sought-after aspiration. While recent video diffusion models have shown promising potential, they still grapple with spatiotemporal inconsistencies and high computational resource demands. We propose GLC-Diffusion, a tuning-free method for long video generation. It models the long video denoising process by establishing denoising trajectories through Global-Local Collaborative Denoising to ensure overall content consistency and temporal coherence between frames. Additionally, we introduce a Noise Reinitialization strategy which combines local noise shuffling with frequency fusion to improve global content consistency and visual diversity. Further, we propose a Video Motion Consistency Refinement (VMCR) module that computes the gradient of pixel-wise and frequency-wise losses to enhance visual consistency and temporal smoothness. Extensive experiments, including quantitative and qualitative evaluations on videos of varying lengths (\textit{e.g.}, 3\times and 6\times longer), demonstrate that our method effectively integrates with existing video diffusion models, producing coherent, high-fidelity long videos superior to previous approaches.
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.
$360^\circ$ videos offer a hyper-immersive experience that allows the viewers to explore a dynamic scene from full 360 degrees. To achieve more user-friendly and personalized content creation in $360^\circ$ video format, we seek to lift standard perspective videos into $360^\circ$ equirectangular videos. To this end, we introduce Imagine360, the first perspective-to-$360^\circ$ video generation framework that creates high-quality $360^\circ$ videos with rich and diverse motion patterns from video anchors. Imagine360 learns fine-grained spherical visual and motion patterns from limited $360^\circ$ video data with several key designs. 1) Firstly we adopt the dual-branch design, including a perspective and a panorama video denoising branch to provide local and global constraints for $360^\circ$ video generation, with motion module and spatial LoRA layers fine-tuned on extended web $360^\circ$ videos. 2) Additionally, an antipodal mask is devised to capture long-range motion dependencies, enhancing the reversed camera motion between antipodal pixels across hemispheres. 3) To handle diverse perspective video inputs, we propose elevation-aware designs that adapt to varying video masking due to changing elevations across frames. Extensive experiments show Imagine360 achieves superior graphics quality and motion coherence among state-of-the-art $360^\circ$ video generation methods. We believe Imagine360 holds promise for advancing personalized, immersive $360^\circ$ video creation.
Fluorescence guided surgery (FGS) is a promising surgical technique that gives surgeons a unique view of tissue that is used to guide their practice by delineating tissue types and diseased areas. As new fluorescent contrast agents are developed that have low fluorescent photon yields, it becomes increasingly important to develop computational models to allow FGS systems to maintain good video quality in real time environments. To further complicate this task, FGS has a difficult bias noise term from laser leakage light (LLL) that represents unfiltered excitation light that can be on the order of the fluorescent signal. Most conventional video denoising methods focus on zero mean noise, and non-causal processing, both of which are violated in FGS. Luckily in FGS, often a co-located reference video is also captured which we use to simulate the LLL and assist in the denoising processes. In this work, we propose an accurate noise simulation pipeline that includes LLL and propose three baseline deep learning based algorithms for FGS video denoising.
Recent advancements utilizing large-scale video data for learning video generation models demonstrate significant potential in understanding complex physical dynamics. It suggests the feasibility of leveraging diverse robot trajectory data to develop a unified, dynamics-aware model to enhance robot manipulation. However, given the relatively small amount of available robot data, directly fitting data without considering the relationship between visual observations and actions could lead to suboptimal data utilization. To this end, we propose VidMan (Video Diffusion for Robot Manipulation), a novel framework that employs a two-stage training mechanism inspired by dual-process theory from neuroscience to enhance stability and improve data utilization efficiency. Specifically, in the first stage, VidMan is pre-trained on the Open X-Embodiment dataset (OXE) for predicting future visual trajectories in a video denoising diffusion manner, enabling the model to develop a long horizontal awareness of the environment's dynamics. In the second stage, a flexible yet effective layer-wise self-attention adapter is introduced to transform VidMan into an efficient inverse dynamics model that predicts action modulated by the implicit dynamics knowledge via parameter sharing. Our VidMan framework outperforms state-of-the-art baseline model GR-1 on the CALVIN benchmark, achieving a 11.7% relative improvement, and demonstrates over 9% precision gains on the OXE small-scale dataset. These results provide compelling evidence that world models can significantly enhance the precision of robot action prediction. Codes and models will be public.
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.
Metamaterials, synthetic materials with customized properties, have emerged as a promising field due to advancements in additive manufacturing. These materials derive unique mechanical properties from their internal lattice structures, which are often composed of multiple materials that repeat geometric patterns. While traditional inverse design approaches have shown potential, they struggle to map nonlinear material behavior to multiple possible structural configurations. This paper presents a novel framework leveraging video diffusion models, a type of generative artificial Intelligence (AI), for inverse multi-material design based on nonlinear stress-strain responses. Our approach consists of two key components: (1) a fields generator using a video diffusion model to create solution fields based on target nonlinear stress-strain responses, and (2) a structure identifier employing two UNet models to determine the corresponding multi-material 2D design. By incorporating multiple materials, plasticity, and large deformation, our innovative design method allows for enhanced control over the highly nonlinear mechanical behavior of metamaterials commonly seen in real-world applications. It offers a promising solution for generating next-generation metamaterials with finely tuned mechanical characteristics.
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.
State-of-the-art (SOTA) video denoising methods employ multi-frame simultaneous denoising mechanisms, resulting in significant delays (e.g., 16 frames), making them impractical for real-time cameras. To overcome this limitation, we propose a multi-fusion gated recurrent Transformer network (GRTN) that achieves SOTA denoising performance with only a single-frame delay. Specifically, the spatial denoising module extracts features from the current frame, while the reset gate selects relevant information from the previous frame and fuses it with current frame features via the temporal denoising module. The update gate then further blends this result with the previous frame features, and the reconstruction module integrates it with the current frame. To robustly compute attention for noisy features, we propose a residual simplified Swin Transformer with Euclidean distance (RSSTE) in the spatial and temporal denoising modules. Comparative objective and subjective results show that our GRTN achieves denoising performance comparable to SOTA multi-frame delay networks, with only a single-frame delay.
MIMO (multiple input, multiple output) approaches are a recent trend in neural network architectures for video restoration problems, where each network evaluation produces multiple output frames. The video is split into non-overlapping stacks of frames that are processed independently, resulting in a very appealing trade-off between output quality and computational cost. In this work we focus on the low-latency setting by limiting the number of available future frames. We find that MIMO architectures suffer from problems that have received little attention so far, namely (1) the performance drops significantly due to the reduced temporal receptive field, particularly for frames at the borders of the stack, (2) there are strong temporal discontinuities at stack transitions which induce a step-wise motion artifact. We propose two simple solutions to alleviate these problems: recurrence across MIMO stacks to boost the output quality by implicitly increasing the temporal receptive field, and overlapping of the output stacks to smooth the temporal discontinuity at stack transitions. These modifications can be applied to any MIMO architecture. We test them on three state-of-the-art video denoising networks with different computational cost. The proposed contributions result in a new state-of-the-art for low-latency networks, both in terms of reconstruction error and temporal consistency. As an additional contribution, we introduce a new benchmark consisting of drone footage that highlights temporal consistency issues that are not apparent in the standard benchmarks.
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.
In recent years, state-of-the-art image and video denoising networks have become increasingly large, requiring millions of trainable parameters to achieve best-in-class performance. Improved denoising quality has come at the cost of denoising speed, where modern transformer networks are far slower to run than smaller denoising networks such as FastDVDnet and classic Bayesian denoisers such as the Wiener filter. In this paper, we implement a hybrid Wiener filter which leverages small ancillary networks to increase the original denoiser performance, while retaining fast denoising speeds. These networks are used to refine the Wiener coring estimate, optimise windowing functions and estimate the unknown noise profile. Using these methods, we outperform several popular denoisers and remain within 0.2 dB, on average, of the popular VRT transformer. Our method was found to be over x10 faster than the transformer method, with a far lower parameter cost.