Any-to-Bokeh: Arbitrary-Subject Video Refocusing with Video Diffusion Model

• URL: http://arxiv.org/abs/2505.21593v3
• Date: Fri, 10 Oct 2025 07:15:41 GMT
• Title: Any-to-Bokeh: Arbitrary-Subject Video Refocusing with Video Diffusion Model
• Abstract summary: We propose a one-step diffusion framework for generating temporally coherent, depth-aware video bokeh rendering.<n>Experiments on synthetic and real-world benchmarks demonstrate superior temporal coherence, spatial accuracy, and controllability, outperforming prior baselines.<n>This work represents the first dedicated diffusion framework for video bokeh generation, establishing a new baseline for temporally coherent and controllable depth-of-field effects.
• Score: 38.625590142415405
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Diffusion models have recently emerged as powerful tools for camera simulation, enabling both geometric transformations and realistic optical effects. Among these, image-based bokeh rendering has shown promising results, but diffusion for video bokeh remains unexplored. Existing image-based methods are plagued by temporal flickering and inconsistent blur transitions, while current video editing methods lack explicit control over the focus plane and bokeh intensity. These issues limit their applicability for controllable video bokeh. In this work, we propose a one-step diffusion framework for generating temporally coherent, depth-aware video bokeh rendering. The framework employs a multi-plane image (MPI) representation adapted to the focal plane to condition the video diffusion model, thereby enabling it to exploit strong 3D priors from pretrained backbones. To further enhance temporal stability, depth robustness, and detail preservation, we introduce a progressive training strategy. Experiments on synthetic and real-world benchmarks demonstrate superior temporal coherence, spatial accuracy, and controllability, outperforming prior baselines. This work represents the first dedicated diffusion framework for video bokeh generation, establishing a new baseline for temporally coherent and controllable depth-of-field effects.

Related papers

• Bridging Event Streams and DiT: Event-Guided Video Frame Interpolation [75.95737622994548]
  Event cameras provide high-resolution motion cues that are well suited for bridging temporal gaps.<n>We propose an adapter-based framework that incorporates event-derived cues into a pre-trained image-to-video diffusion model.
  arXiv  Detail & Related papers  (2026-08-11T04:47:44Z)
• Towards Photorealistic and Efficient Bokeh Rendering via Diffusion Framework [29.580886518291518]
  Existing mobile devices are constrained by compact optical designs, such as small apertures.<n>We propose MagicBokeh, a unified diffusion-based framework designed for high-quality and efficient bokeh rendering.
  arXiv  Detail & Related papers  (2026-05-08T08:31:10Z)
• Light-X: Generative 4D Video Rendering with Camera and Illumination Control [52.87059646145144]
  Light-X is a video generation framework that enables controllable rendering from monocular videos with both viewpoint and illumination control.<n>To address the lack of paired multi-view and multi-illumination videos, we introduce Light-Syn, a degradation-based pipeline with inverse-mapping.
  arXiv  Detail & Related papers  (2025-12-04T18:59:57Z)
• ReLumix: Extending Image Relighting to Video via Video Diffusion Models [5.890782804843724]
  Controlling illumination during video post-production is a crucial yet elusive goal in computational photography.<n>This paper introduces ReLumix, a novel framework that decouples the relighting from temporal synthesis.<n>Although trained on synthetic data, ReLumix shows competitive generalization to real-world videos.
  arXiv  Detail & Related papers  (2025-09-28T09:35:33Z)
• Stable Video-Driven Portraits [52.008400639227034]
  Animation aims to generate photo-realistic videos from a single source image by reenacting the expression and pose from a driving video.<n>Recent advances using diffusion models have demonstrated improved quality but remain constrained by weak control signals and architectural limitations.<n>We propose a novel diffusion based framework that leverages masked facial regions specifically the eyes, nose, and mouth from the driving video as strong motion control cues.
  arXiv  Detail & Related papers  (2025-09-22T08:11:08Z)
• BokehDiff: Neural Lens Blur with One-Step Diffusion [53.11429878683807]
  We introduce BokehDiff, a lens blur rendering method that achieves physically accurate and visually appealing outcomes.<n>Our method employs a physics-inspired self-attention module that aligns with the image formation process.<n>We adapt the diffusion model to the one-step inference scheme without introducing additional noise, and achieve results of high quality and fidelity.
  arXiv  Detail & Related papers  (2025-07-24T03:23:19Z)
• Bokeh Diffusion: Defocus Blur Control in Text-to-Image Diffusion Models [26.79219274697864]
  Current diffusion models typically rely on prompt engineering to mimic such effects.<n>We propose Bokeh Diffusion, a scene-consistent bokeh control framework.<n>Our approach achieves flexible, lens-like blur control and supports applications such as real image editing via inversion.
  arXiv  Detail & Related papers  (2025-03-11T13:49:12Z)
• DiffusionRenderer: Neural Inverse and Forward Rendering with Video Diffusion Models [83.28670336340608]
  We introduce DiffusionRenderer, a neural approach that addresses the dual problem of inverse and forward rendering.<n>Our model enables practical applications from a single video input--including relighting, material editing, and realistic object insertion.
  arXiv  Detail & Related papers  (2025-01-30T18:59:11Z)
• Video Depth Anything: Consistent Depth Estimation for Super-Long Videos [60.857723250653976]
  We propose Video Depth Anything for high-quality, consistent depth estimation in super-long videos.<n>Our model is trained on a joint dataset of video depth and unlabeled images, similar to Depth Anything V2.<n>Our approach sets a new state-of-the-art in zero-shot video depth estimation.
  arXiv  Detail & Related papers  (2025-01-21T18:53:30Z)
• DiffuEraser: A Diffusion Model for Video Inpainting [13.292164408616257]
  We introduce DiffuEraser, a video inpainting model based on stable diffusion, to fill masked regions with greater details and more coherent structures.<n>We also expand the temporal receptive fields of both the prior model and DiffuEraser, and further enhance consistency by leveraging the temporal smoothing property of Video Diffusion Models.
  arXiv  Detail & Related papers  (2025-01-17T08:03:02Z)
• Optical-Flow Guided Prompt Optimization for Coherent Video Generation [51.430833518070145]
  We propose a framework called MotionPrompt that guides the video generation process via optical flow.<n>We optimize learnable token embeddings during reverse sampling steps by using gradients from a trained discriminator applied to random frame pairs.<n>This approach allows our method to generate visually coherent video sequences that closely reflect natural motion dynamics, without compromising the fidelity of the generated content.
  arXiv  Detail & Related papers  (2024-11-23T12:26:52Z)
• Variable Aperture Bokeh Rendering via Customized Focal Plane Guidance [18.390543681127976]
  The proposed method has achieved competitive state-of-the-art performance with only 4.4M parameters, which is much lighter than mainstream computational bokeh models. The proposed method has achieved competitive state-of-the-art performance with only 4.4M parameters, which is much lighter than mainstream computational bokeh models.
  arXiv  Detail & Related papers  (2024-10-18T12:04:23Z)
• DaBiT: Depth and Blur informed Transformer for Video Focal Deblurring [4.332534893042983]
  In many real-world scenarios, recorded videos suffer from accidental focus blur.<n>This paper introduces a framework optimized for the as yet unattempted task of video focal deblurring (refocusing)<n>We achieve state-of-the-art results with an average PSNR performance over 1.9dB greater than comparable existing video restoration methods.
  arXiv  Detail & Related papers  (2024-07-01T12:22:16Z)
• GBSD: Generative Bokeh with Stage Diffusion [16.189787907983106]
  The bokeh effect is an artistic technique that blurs out-of-focus areas in a photograph. We present GBSD, the first generative text-to-image model that synthesizes photorealistic images with a bokeh style.
  arXiv  Detail & Related papers  (2023-06-14T05:34:02Z)
• BokehOrNot: Transforming Bokeh Effect with Image Transformer and Lens Metadata Embedding [2.3784282912975345]
  Bokeh effect is an optical phenomenon that offers a pleasant visual experience, typically generated by high-end cameras with wide aperture lenses. We propose a novel universal method for embedding lens metadata into the model and introducing a loss calculation method using alpha masks. Based on the above techniques, we propose the BokehOrNot model, which is capable of producing both blur-to-sharp and sharp-to-blur bokeh effect.
  arXiv  Detail & Related papers  (2023-06-06T21:49:56Z)
• Joint Video Multi-Frame Interpolation and Deblurring under Unknown Exposure Time [101.91824315554682]
  In this work, we aim ambitiously for a more realistic and challenging task - joint video multi-frame and deblurring under unknown exposure time. We first adopt a variant of supervised contrastive learning to construct an exposure-aware representation from input blurred frames. We then build our video reconstruction network upon the exposure and motion representation by progressive exposure-adaptive convolution and motion refinement.
  arXiv  Detail & Related papers  (2023-03-27T09:43:42Z)
• MC-Blur: A Comprehensive Benchmark for Image Deblurring [127.6301230023318]
  In most real-world images, blur is caused by different factors, e.g., motion and defocus. We construct a new large-scale multi-cause image deblurring dataset (called MC-Blur) Based on the MC-Blur dataset, we conduct extensive benchmarking studies to compare SOTA methods in different scenarios.
  arXiv  Detail & Related papers  (2021-12-01T02:10:42Z)
• Motion-blurred Video Interpolation and Extrapolation [72.3254384191509]
  We present a novel framework for deblurring, interpolating and extrapolating sharp frames from a motion-blurred video in an end-to-end manner. To ensure temporal coherence across predicted frames and address potential temporal ambiguity, we propose a simple, yet effective flow-based rule.
  arXiv  Detail & Related papers  (2021-03-04T12:18:25Z)
• AIM 2020 Challenge on Rendering Realistic Bokeh [95.87775182820518]
  This paper reviews the second AIM realistic bokeh effect rendering challenge. The goal was to learn a realistic shallow focus technique using a large-scale EBB! bokeh dataset. The participants had to render bokeh effect based on only one single frame without any additional data from other cameras or sensors.
  arXiv  Detail & Related papers  (2020-11-10T09:15:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.