统一长视频修复与外扩：基于重叠高阶协同去噪
Unified Long Video Inpainting and Outpainting via Overlapping High-Order Co-Denoising
AI总结：
提出重叠高阶协同去噪框架，利用LoRA和双区域损失将预训练文本到视频模型统一用于长视频修复与外扩，在InpaintBench上优于现有方法并支持800帧。
摘要：
基于扩散的文本到视频模型能力日益增强，但基于掩码的数百帧编辑仍然具有挑战性：朴素的长视频生成存在内存爆炸、窗口接缝和时间漂移问题，而现有编辑器通常需要专门的模块或大量微调。我们提出重叠高阶协同去噪（Overlapping High-Order Co-Denoising），这是一个轻量级框架，可将单个预训练的文本到视频模型转变为统一的修复-外扩编辑器。我们仅使用混合内部和边界掩码训练LoRA适配器，并采用双区域损失，在改善掩码内部合成的同时显式保留已知内容。在推理时，我们使用重叠窗口对长潜在序列进行去噪，在每个窗口内应用二阶Heun采样，并使用汉明加权混合融合重叠区域，以减少边界伪影并提高时间一致性。在InpaintBench（30个真实世界视频，81-300帧）上，我们的方法在背景保真度（SSIM/LPIPS）、时间一致性（tLPIPS）和文本对齐（CLIP）方面优于Wan 2.1变体和VACE，并可扩展到长序列，展示至800帧，内存受所选窗口大小限制。
英文摘要：
Diffusion-based text-to-video models are increasingly capable, but mask-based editing over hundreds of frames remains challenging: naïve long-video generation suffers from memory blow-up, window seams, and temporal drift, while existing editors often require specialized modules or heavy fine-tuning. We present Overlapping High-Order Co-Denoising, a lightweight framework that turns a single pre-trained text-to-video model into a unified inpainting-outpainting editor. We train only LoRA adapters using mixed interior and border masks together with a dual-region loss that improves synthesis inside the mask while explicitly preserving known content. At inference, we denoise long latent sequences using overlapping windows, apply second-order Heun sampling within each window, and fuse overlaps with Hamming-weighted blending to reduce boundary artifacts and improve temporal coherence. On InpaintBench (30 real-world videos, 81--300 frames), our method outperforms Wan 2.1 variants and VACE in background faithfulness (SSIM/LPIPS), temporal consistency (tLPIPS), and text alignment (CLIP), and scales to long horizons, demonstrated up to 800 frames, with memory bounded by the chosen window size.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
