Journal of Visual Computing logo

Articles

Vol. 1 No. 4 (2026)

High-Order Co-Denoising for Temporally Consistent Long-Video Inpainting and Outpainting Generation

Submitted
September 24, 2026
Published
October 8, 2026

Abstract

The rapid advancement of generative artificial intelligence has significantly enhanced the capabilities of image synthesis, yet the extension of these techniques to the temporal domain, specifically in long-video generation, remains profoundly challenging. Video inpainting and outpainting require not only spatial fidelity but also rigorous temporal consistency across hundreds of frames. Conventional diffusion-based video editing methods typically struggle with temporal flickering, structural degradation over time, and a lack of long-range coherence, primarily because they rely on low-order temporal attention mechanisms or autoregressive sliding windows that suffer from error accumulation. To address these critical limitations, this paper introduces a novel high-order co-denoising framework explicitly designed for temporally consistent long-video inpainting and outpainting generation. By formulating the reverse diffusion process as a joint optimization problem across multiple distant frames, the proposed methodology captures high-order temporal dynamics and implicitly enforces long-range kinematic consistency. We integrate a latent temporal alignment strategy that synchronizes the noise trajectories of visible and masked regions, thereby preventing contextual divergence during the generation sequence. Extensive quantitative and qualitative evaluations on benchmark datasets demonstrate that our approach significantly outperforms existing state-of-the-art models in metrics evaluating both perceptual quality and temporal coherence. The proposed framework sets a new standard for long-video synthesis, offering robust solutions for complex editing tasks in dynamic scenes.

References

  1. Ye, Z., Ma, S., Yang, J., Yang, X., Yang, Y., Gong, Z., ... & Wang, H. (2026, April). Object fidelity diffusion for remote sensing image generation. In International Conference on Learning Representations (Vol. 2026, pp. 3258-3278).
  2. Fang, S., Shen, I., Wang, Y., Tsai, Y. H., Yang, Y., Zhou, S., ... & Yang, M. H. (2025). Meshllm: Empowering large language models to progressively understand and generate 3d mesh. In Proceedings of the IEEE/CVF international conference on computer vision (pp. 14061-14072).
  3. Yang, J., Wang, Q., Jin, Y., Ma, S., Xu, M., & Pang, S. (2026). Knowledge-Refined Dual Context-Aware Network for Partially Relevant Video Retrieval. arXiv preprint arXiv:2603.23902.
  4. Yang, Z., Ji, W., Guo, Q., & Wang, Z. (2023, October). Javp: Joint-aware video processing with edge-cloud collaboration for dnn inference. In Proceedings of the 31st ACM International Conference on Multimedia (pp. 9152-9160).
  5. Yu, Y., Zhang, L., Wang, B., Zhao, J., Han, K., Qi, Y., ... & Wang, W. (2025). Synergistic π-Tunnel Clamps in β-Sheets for Long-Range Dry-State Conduction: Toward Neural Restoration. Journal of the American Chemical Society, 147(13), 11049-11061.
  6. Yang, Y., & Zhang, S. (2025). Pixel-wise calibration for a multi-focus microscopic 3D imaging system.Optics and Lasers in Engineering,194, 109127.
  7. Fan, Y., Tang, Z., Miyazaki, T., Huang, Y., & Omachi, S. (2026). A real-driven image synthesis framework for adapting pre-trained scene text detectors. Image and Vision Computing, 106027.
  8. Li, Y., Wang, S., & Tan, G. (2025). ID-NeRF: Indirect diffusion-guided neural radiance fields for generalizable view synthesis. Expert Systems with Applications, 266, 126068.
  9. Li, Y., Wang, S., Guo, M., Huang, J., Ding, T., Hu, M., ... & Tan, G. (2025). ReCamDriving: LiDAR-Free Camera-Controlled Novel Trajectory Video Generation. arXiv preprint arXiv:2512.03621.
  10. Jiaxing, Z., & Hao, T. (2025). Sam2 for image and video segmentation: A comprehensive survey.
  11. Liu, R., Zhang, R., & Wang, S. (2025, December). Transformer-based modeling of user interaction sequences for dwell time prediction in human-computer interfaces. In 2025 7th International Academic Exchange Conference on Science and Technology Innovation (IAECST) (pp. 352-356). IEEE.
  12. H. Wang et al., “Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation,” arXiv preprint arXiv:2607.05382, 2026.
  13. He, H., Sun, Z., Fan, J., & Mok, P. Y. (2025). TiPGAN: High-quality tileable textures synthesis with intrinsic priors for cloth digitization applications. Computer-Aided Design, 183, 103866.
  14. Hao, Y., Xu, M., Ye, C., Qin, J., Lu, S., Qin, Y., & Han, X. (2026). LoFA: Learning to Predict Personalized Prior for Fast Adaptation of Visual Generative Models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 21986-21996).
  15. Qu, W., Shao, Y., Meng, L., Huang, X., & Xiao, L. (2024, June). A conditional denoising diffusion probabilistic model for point cloud upsampling. In 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 20786-20795). IEEE.
  16. Zhang, B., Wang, S., Jiang, Y., Sui, D., Tu, Z., & Chu, D. (2025, July). Ask and Retrieve Knowledge: Towards Proactive Asking with Imperfect Information in Medical Multi-turn Dialogues. In Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 1055-1065).
  17. Lyu, S., Mao, S., & Ma, Y. (2025). Unified Long Video Inpainting and Outpainting via Overlapping High-Order Co-Denoising. arXiv preprint arXiv:2511.03272.
  18. Z. Wang, R. Yuan, Z. Geng, H. Li, X. Qu, X. Li, S. Chen, H. Fu, R. B. Dannenberg, and K. Zhang, ‘‘Singing timbre popularity assessment based on multimodal large foundation model,’’ in Proc. 33rd ACM Int. Conf. Multimedia, Oct. 2025, pp. 12227–12236, doi: 10.1145/3746027.3758148.
  19. Jing, G., Gao, P., Lee, Y., Hu, Y., & Zhang, H. (2025). 3D-aided pedestrian representation learning for video-based person re-identification. IEEE Transactions on Circuits and Systems for Video Technology, 35 (12), 12830-12845.
  20. Chang Liu, Tianjiao Jing, Chengcheng Ma, XuanQi Zhou, Zhengxuan Lian, Qin Jin, Hongliang Yuan, and Shi-Sheng Huang. 2025. EmoDiffTalk:Emotion-aware Diffusion for Editable 3D Gaussian Talking Head. CoRR abs/2512.05991 (2025). arXiv:2512.05991 doi:10.48550/ARXIV.2512.05991
  21. Zhang, J., Shi, Y., Ma, Y., Xu, L., Yu, J., & Wang, J. (2023, June). Ikol: Inverse kinematics optimization layer for 3d human pose and shape estimation via gauss-newton differentiation. In Proceedings of the AAAI conference on artificial intelligence (Vol. 37, No. 3, pp. 3454-3462).
  22. Qu, W., Wang, J., Gong, Y., Huang, X., & Xiao, L. (2025, June). An end-to-end robust point cloud semantic segmentation network with single-step conditional diffusion models. In 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 27325-27335). IEEE.
  23. Liu, Y., Cai, Q., Wang, C., Yang, J., Fan, H., Dong, J., & Chen, S. (2024). Geometry-enhanced attentive multi-view stereo for challenging matching scenarios. IEEE Transactions on Circuits and Systems for Video Technology, 34(8), 7401-7416.
  24. Chen, Z., Gao, P., Lee, Y., Barthelemy, J., Zhou, L., & Wang, L. (2025, June). Optimizing Efficiency and Visual-Textual Alignment for LLM-Based Radiology Report Generation. In 2025 IEEE International Conference on Multimedia and Expo (ICME) (pp. 1-6). IEEE.
  25. Li, Q., Liu, Z., Luo, W., Luo, T., & Hou, C. (2026). Correcting Visual Blur Induced by Attention Distraction to Reduce Hallucinations: Algorithm and Theory. arXiv preprint arXiv:2605.24602.
  26. Fan, J., Liang, Y., Liu, L., Huang, S., & Zhang, L. (2023). RCA-NOC: Relative contrastive alignment for novel object captioning. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (pp. 15510–15520). IEEE. https://doi.org/10.1109/ICCV51070.2023.01422
  27. Cong, P., Xu, Y., Ren, Y., Zhang, J., Xu, L., Wang, J., ... & Ma, Y. (2023, June). Weakly supervised 3d multi-person pose estimation for large-scale scenes based on monocular camera and single lidar. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 37, No. 1, pp. 461-469).
  28. Wang, Y., Li, F. W., & Wang, J. (2026, May). Motion-Guided Semantic Alignment with Negative Prompts for Zero-Shot Video Action Recognition. In ICASSP 2026-2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 10712-10716). IEEE.
  29. Li, Y., Gou, C., & Tan, G. (2024). Taming uncertainty in sparse-view generalizable nerf via indirect diffusion guidance. arXiv preprint arXiv:2402.01217, 3, 2.
  30. Wang, Y., Yu, H., Tang, J., Gao, Y., Wang, X., Yue, Y., & Yang, Y. (2026). FilterGS: Traversal-Free Parallel Filtering and Adaptive Shrinking for Large-Scale LoD 3D Gaussian Splatting. arXiv preprint arXiv:2603.23891.
  31. Du, J., Gao, S., & Chen, C. H. (2024). A contextual ranking and selection method for personalized medicine. Manufacturing & Service Operations Management, 26(1), 167-181.
  32. Wang, G., Zhou, Y., Deng, K., Cheah, W. P., Qu, R., Ren, J., & Shen, L. (2026). SurgCoT: Advancing Spatiotemporal Reasoning in Surgical Videos through a Chain-of-Thought Benchmark. arXiv preprint arXiv:2604.20319.
  33. Johnson, J., Alahi, A., & Fei-Fei, L. (2016). Perceptual losses for real-time style transfer and super-resolution. In Proceedings of ECCV.
  34. Sun, J., Lin, Y., Xue, Y., Wang, Y., Yao, Z., Qian, R., ... & Zhou, H. (2026). Pmmc: Prospective multimodal memory compilation for long-term lvlm agents. arXiv preprint arXiv:2608.00962.
  35. Wang, J., Xu, Y., Li, Y., Khargonekar, P., & Faruque, M. A. A. (2026). CRUISE: Vision-Language Model-Guided Uncertainty-Aware Cross-Modal Sensor Fusion for Robust Autonomous Driving. arXiv preprint arXiv:2608.09202.
  36. Zhang, W., Huang, M., Zhou, Y., Zhang, J., Yu, J., Wang, J., & Xu, L. (2024). Both2hands: Inferring 3d hands from both text prompts and body dynamics. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 2393-2404).
  37. Meng, X., & Lin, J. (2026). CARTN: Counterfactual Audit and Repair for Trust-Aware Multi-Signal Streaming LiDAR Segmentation. Information Fusion, 104809.
  38. Kabra M, Shahi P K, Wang Y, et al. Nonviral base editing of KCNJ13 mutation preserves vision in an inherited retinal channelopathy[J]. bioRxiv, 2022: 2022.07. 12.499808.
  39. Su, Z., Wei, H., Cen, K., Wang, Y., Chen, G., Yuan, C., & Chu, X. (2026). Generation enhances understanding in unified multimodal models via multi-representation generation. arXiv preprint arXiv:2601.21406.
  40. Wang, J., Malawade, A. V., Zhou, J., Yu, S. Y., & Al Faruque, M. A. (2024, January). Rs2g: Data-driven scene-graph extraction and embedding for robust autonomous perception and scenario understanding. In 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) (pp. 7478-7487). IEEE.