F2HDR: Two-Stage HDR Video Reconstruction via Flow Adapter and Physical Motion Modeling

• URL: http://arxiv.org/abs/2603.14920v2
• Date: Wed, 18 Mar 2026 04:08:07 GMT
• Title: F2HDR: Two-Stage HDR Video Reconstruction via Flow Adapter and Physical Motion Modeling
• Abstract summary: Cross-exposure inconsistencies and complex motion make inter-frame alignment difficult, leading to ghosting and detail loss.<n>Existing methods often suffer from inaccurate alignment, suboptimal feature aggregation, and degraded reconstruction quality in motion-dominated regions.<n>We propose F2, a two-stage HDR video reconstruction framework that robustly perceives inter-frame motion and restores fine details in complex dynamic scenarios.
• Score: 21.989561243459363
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Reconstructing High Dynamic Range (HDR) videos from sequences of alternating-exposure Low Dynamic Range (LDR) frames remains highly challenging, especially under dynamic scenes where cross-exposure inconsistencies and complex motion make inter-frame alignment difficult, leading to ghosting and detail loss. Existing methods often suffer from inaccurate alignment, suboptimal feature aggregation, and degraded reconstruction quality in motion-dominated regions. To address these challenges, we propose F2HDR, a two-stage HDR video reconstruction framework that robustly perceives inter-frame motion and restores fine details in complex dynamic scenarios. The proposed framework integrates a flow adapter that adapts generic optical flow for robust cross-exposure alignment, a physical motion modeling to identify salient motion regions, and a motion-aware refinement network that aggregates complementary information while removing ghosting and noise. Extensive experiments demonstrate that F2HDR achieves state-of-the-art performance on real-world HDR video benchmarks, producing ghost-free and high-fidelity results under large motion and exposure variations.

Related papers

• HDR-NSFF: High Dynamic Range Neural Scene Flow Fields [25.023351117641358]
  We present HDR-NSFF, a paradigm shift from 2D-based merging to 4D-temporal modeling.<n>Experiments demonstrate that HDR-NSFF recovers fine details radiance coherent dynamics even under challenging exposure variations.<n>We present the first real-world HDR-GoPro dataset specifically designed for dynamic HDR scenes.
  arXiv  Detail & Related papers  (2026-03-09T12:36:46Z)
• Wavelet-Domain Masked Image Modeling for Color-Consistent HDR Video Reconstruction [69.35623794013152]
  High Dynamic Range (LDR) video reconstruction aims to recover fine brightness, color, and details from LDR videos.<n>Existing methods often suffer from color inaccuracies and temporal inconsistencies.<n>We propose WMNet, a novel HDR video reconstruction network that leverages Wavelet domain Masked Image Modeling.
  arXiv  Detail & Related papers  (2026-02-07T06:19:23Z)
• Dynamic Novel View Synthesis in High Dynamic Range [78.72910306733607]
  Current methods primarily focus on static scenes, implicitly assuming all scene elements remain stationary and non-living.<n>We introduce HDR-4DGS, a Gaussian Splatting-based architecture featured with an innovative dynamic tone-mapping module.<n>Experiments demonstrate that HDR-4DGS surpasses existing state-of-the-art methods in both quantitative performance and visual fidelity.
  arXiv  Detail & Related papers  (2025-09-26T04:29:22Z)
• MIORe & VAR-MIORe: Benchmarks to Push the Boundaries of Restoration [53.180212987726556]
  We introduce MIORe and VAR-MIORe, two novel multi-task datasets that address critical limitations in current motion restoration benchmarks.<n>Our datasets capture a broad spectrum of motion scenarios, which include complex ego-camera movements, dynamic multi-subject interactions, and depth-dependent blur effects.
  arXiv  Detail & Related papers  (2025-09-08T15:34:31Z)
• Event-Enhanced Blurry Video Super-Resolution [52.894824081586776]
  We tackle the task of blurry video super-resolution (BVSR), aiming to generate high-resolution (HR) videos from low-resolution (LR) and blurry inputs.<n>Current BVSR methods often fail to restore sharp details at high resolutions, resulting in noticeable artifacts and jitter.<n>We introduce event signals into BVSR and propose a novel event-enhanced network, Ev-DeVSR.
  arXiv  Detail & Related papers  (2025-04-17T15:55:41Z)
• BARD-GS: Blur-Aware Reconstruction of Dynamic Scenes via Gaussian Splatting [8.480548767680894]
  We introduce BARD-GS, a novel approach for robust dynamic scene reconstruction that effectively handles blurry inputs and imprecise camera poses.<n>By explicitly decomposing motion blur into camera motion blur and object motion blur, we achieve significantly improved rendering results in dynamic regions.
  arXiv  Detail & Related papers  (2025-03-20T04:23:52Z)
• Event-assisted 12-stop HDR Imaging of Dynamic Scene [20.064191181938533]
  We propose a novel 12-stop HDR imaging approach for dynamic scenes, leveraging a dual-camera system with an event camera and an RGB camera.<n>The event camera provides temporally dense, high dynamic range signals that improve alignment between LDR frames with large exposure differences, reducing ghosting artifacts caused by motion.<n>Our method achieves state-of-the-art performance, successfully extending HDR imaging to 12 stops in dynamic scenes.
  arXiv  Detail & Related papers  (2024-12-19T10:17:50Z)
• Event-boosted Deformable 3D Gaussians for Dynamic Scene Reconstruction [50.873820265165975]
  We introduce the first approach combining event cameras, which capture high-temporal-resolution, continuous motion data, with deformable 3D-GS for dynamic scene reconstruction.<n>We propose a GS-Threshold Joint Modeling strategy, creating a mutually reinforcing process that greatly improves both 3D reconstruction and threshold modeling.<n>We contribute the first event-inclusive 4D benchmark with synthetic and real-world dynamic scenes, on which our method achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-11-25T08:23:38Z)
• HDRTransDC: High Dynamic Range Image Reconstruction with Transformer Deformation Convolution [21.870772317331447]
  High Dynamic Range (CAM) imaging aims to generate an artifact-free HDR image with realistic details by fusing multi-exposure Low Dynamic Range (LDR) images. For the purpose of eliminating fusion distortions, we propose DWFB to spatially adaptively select useful information across frames.
  arXiv  Detail & Related papers  (2024-03-11T15:48:17Z)
• Towards High-quality HDR Deghosting with Conditional Diffusion Models [88.83729417524823]
  High Dynamic Range (LDR) images can be recovered from several Low Dynamic Range (LDR) images by existing Deep Neural Networks (DNNs) techniques. DNNs still generate ghosting artifacts when LDR images have saturation and large motion. We formulate the HDR deghosting problem as an image generation that leverages LDR features as the diffusion model's condition.
  arXiv  Detail & Related papers  (2023-11-02T01:53:55Z)
• LAN-HDR: Luminance-based Alignment Network for High Dynamic Range Video Reconstruction [20.911738532410766]
  We propose an end-to-end HDR video composition framework, which aligns LDR frames in feature space and then merges aligned features into an HDR frame. In training, we adopt a temporal loss, in addition to frame reconstruction losses, to enhance temporal consistency and thus reduce flickering.
  arXiv  Detail & Related papers  (2023-08-22T01:43:00Z)
• Alignment-free HDR Deghosting with Semantics Consistent Transformer [76.91669741684173]
  High dynamic range imaging aims to retrieve information from multiple low-dynamic range inputs to generate realistic output. Existing methods often focus on the spatial misalignment across input frames caused by the foreground and/or camera motion. We propose a novel alignment-free network with a Semantics Consistent Transformer (SCTNet) with both spatial and channel attention modules.
  arXiv  Detail & Related papers  (2023-05-29T15:03:23Z)
• DeepHS-HDRVideo: Deep High Speed High Dynamic Range Video Reconstruction [23.341594337637545]
  We propose to align the input LDR frames using a pre-trained video frame network. This results in better alignment of LDR frames, since we circumvent the error-prone exposure matching step. We also present the first method to generate high FPS HDR videos.
  arXiv  Detail & Related papers  (2022-10-10T04:27:45Z)
• Deep Progressive Feature Aggregation Network for High Dynamic Range Imaging [24.94466716276423]
  We propose a deep progressive feature aggregation network for improving HDR imaging quality in dynamic scenes. Our method implicitly samples high-correspondence features and aggregates them in a coarse-to-fine manner for alignment. Experiments show that our proposed method can achieve state-of-the-art performance under different scenes.
  arXiv  Detail & Related papers  (2022-08-04T04:37:35Z)

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.