mlsanityData to 14 Oct 2026

Hybrid Neural Fusion for Full-frame Video Stabilization

arXiv 2102.06205 ↗First posted 11 Feb 2021cs.CVcited by 21

Not on the map. Why?

Abstract (arXiv)

Existing video stabilization methods often generate visible distortion or require aggressive cropping of frame boundaries, resulting in smaller field of views. In this work, we present a frame synthesis algorithm to achieve full-frame video stabilization. We first estimate dense warp fields from neighboring frames and then synthesize the stabilized frame by fusing the warped contents. Our core technical novelty lies in the learning-based hybrid-space fusion that alleviates artifacts caused by optical flow inaccuracy and fast-moving objects. We validate the effectiveness of our method on the NUS, selfie, and DeepStab video datasets. Extensive experiment results demonstrate the merits of our approach over prior video stabilization methods.

Key facts. Cited by 21 papers in the map (data through 14 Oct 2026). Builds on 29 of its 80 references that are in the map. First posted on arXiv 11 Feb 2021.

Builds on

29 of 80 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  5. 2015Spatial Transformer Networkscited by 1,429
  6. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 903
  7. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  8. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  9. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 751
  10. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  11. 2018Free-Form Image Inpainting with Gated Convolutioncited by 594
  12. 2017Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolutioncited by 453
17 more
  1. 2020Space-time Neural Irradiance Fields for Free-Viewpoint Videocited by 414
  2. 2018DeepVoxels: Learning Persistent 3D Feature Embeddingscited by 405
  3. 2019SynSin: End-to-end View Synthesis from a Single Imagecited by 364
  4. 2019Neural Point-Based Graphicscited by 327
  5. 2020Free View Synthesiscited by 231
  6. 20203D Photography using Context-aware Layered Depth Inpaintingcited by 206
  7. 2019Pushing the Boundaries of View Extrapolation with Multiplane Imagescited by 191
  8. 2020Robust Consistent Video Depth Estimationcited by 188
  9. 2019Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wildcited by 180
  10. 2020Stable View Synthesiscited by 165
  11. 20193D Ken Burns Effect from a Single Imagecited by 128
  12. 2020Flow-edge Guided Video Completioncited by 104
  13. 2018Extreme View Synthesiscited by 94
  14. 2020Layered Neural Rendering for Retiming People in Videocited by 51
  15. 2020One Shot 3D Photographycited by 45
  16. 2019Deep Iterative Frame Interpolation for Full-frame Video Stabilizationcited by 23
  17. 2020Semantic View Synthesiscited by 18

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 3; 2023: 5; 2024: 6; 2025: 3; 2026: 3.

21 papers.

Sort:

By area:

  1. 2023Robust Dynamic Radiance Fieldscited by 194
  2. 2023Progressively Optimized Local Radiance Fields for Robust View Synthesiscited by 103
  3. 2024DiffIR2VR-Zero: Zero-Shot Video Restoration with Diffusion-based Image Restoration Modelscited by 34
  4. 2024DeNVeR: Deformable Neural Vessel Representations for Unsupervised Video Vessel Segmentationcited by 13
  5. 2023Learning Continuous Exposure Value Representations for Single-Image HDR Reconstructioncited by 11
  6. 2024D-NPC: Dynamic Neural Point Clouds for Non-Rigid View Synthesis from Monocular Videocited by 11
  7. 2023Fast Full-frame Video Stabilization with Iterative Optimizationcited by 8
  8. 2022GlobalFlowNet: Video Stabilization using Deep Distilled Global Motion Estimatescited by 7
  9. 20243D Multi-frame Fusion for Video Stabilizationcited by 7
  10. 2024NaRCan: Natural Refined Canonical Image with Integration of Diffusion Prior for Video Editingcited by 7
  11. 2024Harnessing Meta-Learning for Improving Full-Frame Video Stabilizationcited by 5
  12. 2025GaVS: 3D-Grounded Video Stabilization via Temporally-Consistent Local Reconstruction and Renderingcited by 5
9 more
  1. 2021Self-Supervised Real-time Video Stabilizationcited by 4
  2. 2022Deep representation learning: Fundamentals, Perspectives, Applications, and Open Challengescited by 3
  3. 2023NeRF-Enhanced Outpainting for Faithful Field-of-View Extrapolationcited by 2
  4. 2025Harnessing Meta-Learning for Controllable Full-Frame Video Stabilizationcited by 2
  5. 2025Splannequin: Freezing Monocular Mannequin-Challenge Footage with Dual-Detection Splattingcited by 2
  6. 2022Leveraging Synthetic Data to Learn Video Stabilization Under Adverse Conditionscited by 1
  7. 2026No Labels, No Look-Ahead: Unsupervised Online Video Stabilization with Classical Priorscited by 0
  8. 2026VS3R: Robust Full-frame Video Stabilization via Deep 3D Reconstructioncited by 0
  9. 2026Accurate Motion Estimation with B'ezier Control Point for Efficient Frame Interpolationcited by 0