Generating the Past, Present and Future from a Motion-Blurred Image

• URL: http://arxiv.org/abs/2512.19817v1
• Date: Mon, 22 Dec 2025 19:12:33 GMT
• Title: Generating the Past, Present and Future from a Motion-Blurred Image
• Abstract summary: Motion blur obscures image details and degrades visual quality.<n>It also encodes information about scene and camera motion during an exposure.<n>Previous techniques leverage this information to estimate a sharp image from an input blurry one.<n>We introduce a new technique that repurposes a pre-trained video diffusion model trained on internet-scale datasets.
• Score: 26.99995751817043
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: We seek to answer the question: what can a motion-blurred image reveal about a scene's past, present, and future? Although motion blur obscures image details and degrades visual quality, it also encodes information about scene and camera motion during an exposure. Previous techniques leverage this information to estimate a sharp image from an input blurry one, or to predict a sequence of video frames showing what might have occurred at the moment of image capture. However, they rely on handcrafted priors or network architectures to resolve ambiguities in this inverse problem, and do not incorporate image and video priors on large-scale datasets. As such, existing methods struggle to reproduce complex scene dynamics and do not attempt to recover what occurred before or after an image was taken. Here, we introduce a new technique that repurposes a pre-trained video diffusion model trained on internet-scale datasets to recover videos revealing complex scene dynamics during the moment of capture and what might have occurred immediately into the past or future. Our approach is robust and versatile; it outperforms previous methods for this task, generalizes to challenging in-the-wild images, and supports downstream tasks such as recovering camera trajectories, object motion, and dynamic 3D scene structure. Code and data are available at https://blur2vid.github.io

Related papers

• LaVR: Scene Latent Conditioned Generative Video Trajectory Re-Rendering using Large 4D Reconstruction Models [52.656349227001925]
  Given a monocular video, the goal of video re-rendering is to generate views of the scene from a novel camera trajectory.<n>Existing methods face two distinct challenges.<n>We propose to address these challenges by using the implicit geometric knowledge embedded in the latent space of a large 4D reconstruction model.
  arXiv  Detail & Related papers  (2026-01-21T05:46:03Z)
• DreamJourney: Perpetual View Generation with Video Diffusion Models [91.88716097573206]
  Perpetual view generation aims to synthesize a long-term video corresponding to an arbitrary camera trajectory solely from a single input image.<n>Recent methods commonly utilize a pre-trained text-to-image diffusion model to synthesize new content of previously unseen regions along camera movement.<n>We present DreamJourney, a two-stage framework that leverages the world simulation capacity of video diffusion models to trigger a new perpetual scene view generation task.
  arXiv  Detail & Related papers  (2025-06-21T12:51:34Z)
• AnyCam: Learning to Recover Camera Poses and Intrinsics from Casual Videos [52.726585508669686]
  We propose AnyCam, a fast transformer model that directly estimates camera poses and intrinsics from a dynamic video sequence.<n>We test AnyCam on established datasets, where it delivers accurate camera poses and intrinsics both qualitatively and quantitatively.<n>By combining camera information, uncertainty, and depth, our model can produce high-quality 4D pointclouds.
  arXiv  Detail & Related papers  (2025-03-30T02:22:11Z)
• ReCamMaster: Camera-Controlled Generative Rendering from A Single Video [72.42376733537925]
  ReCamMaster is a camera-controlled generative video re-rendering framework.<n>It reproduces the dynamic scene of an input video at novel camera trajectories.<n>Our method also finds promising applications in video stabilization, super-resolution, and outpainting.
  arXiv  Detail & Related papers  (2025-03-14T17:59:31Z)
• Fillerbuster: Multi-View Scene Completion for Casual Captures [48.12462469832712]
  We present Fillerbuster, a method that completes unknown regions of a 3D scene by utilizing a novel large-scale multi-view latent diffusion transformer.<n>Our solution is to train a generative model that can consume a large context of input frames while generating unknown target views and recovering image poses when desired.
  arXiv  Detail & Related papers  (2025-02-07T18:59:51Z)
• Generative Omnimatte: Learning to Decompose Video into Layers [29.098471541412113]
  We present a novel generative layered video decomposition framework to address the omnimatte problem.<n>Our core idea is to train a video diffusion model to identify and remove scene effects caused by a specific object.<n>We show that this model can be finetuned from an existing video inpainting model with a small, carefully curated dataset.
  arXiv  Detail & Related papers  (2024-11-25T18:59:57Z)
• TimeRewind: Rewinding Time with Image-and-Events Video Diffusion [10.687722181495065]
  This paper addresses the novel challenge of rewinding'' time from a single captured image to recover the fleeting moments missed just before the shutter button is pressed. We overcome this challenge by leveraging the emerging technology of neuromorphic event cameras, which capture motion information with high temporal resolution. Our proposed framework introduces an event motion adaptor conditioned on event camera data, guiding the diffusion model to generate videos that are visually coherent and physically grounded in the captured events.
  arXiv  Detail & Related papers  (2024-03-20T17:57:02Z)
• FlowCam: Training Generalizable 3D Radiance Fields without Camera Poses via Pixel-Aligned Scene Flow [26.528667940013598]
  Reconstruction of 3D neural fields from posed images has emerged as a promising method for self-supervised representation learning. Key challenge preventing the deployment of these 3D scene learners on large-scale video data is their dependence on precise camera poses from structure-from-motion. We propose a method that jointly reconstructs camera poses and 3D neural scene representations online and in a single forward pass.
  arXiv  Detail & Related papers  (2023-05-31T20:58:46Z)
• NeuralDiff: Segmenting 3D objects that move in egocentric videos [92.95176458079047]
  We study the problem of decomposing the observed 3D scene into a static background and a dynamic foreground. This task is reminiscent of the classic background subtraction problem, but is significantly harder because all parts of the scene, static and dynamic, generate a large apparent motion. In particular, we consider egocentric videos and further separate the dynamic component into objects and the actor that observes and moves them.
  arXiv  Detail & Related papers  (2021-10-19T12:51:35Z)
• Future Video Synthesis with Object Motion Prediction [54.31508711871764]
  Instead of synthesizing images directly, our approach is designed to understand the complex scene dynamics. The appearance of the scene components in the future is predicted by non-rigid deformation of the background and affine transformation of moving objects. Experimental results on the Cityscapes and KITTI datasets show that our model outperforms the state-of-the-art in terms of visual quality and accuracy.
  arXiv  Detail & Related papers  (2020-04-01T16:09:54Z)

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.