MTV-Inpaint: Multi-Task Long Video Inpainting
read the original abstract
Video inpainting involves modifying local regions within a video, ensuring spatial and temporal consistency. Most existing methods focus primarily on scene completion (i.e., filling missing regions) and lack the capability to insert new objects into a scene in a controllable manner. Fortunately, recent advancements in text-to-video (T2V) diffusion models pave the way for text-guided video inpainting. However, directly adapting T2V models for inpainting remains limited in unifying completion and insertion tasks, lacks input controllability, and struggles with long videos, thereby restricting their applicability and flexibility. To address these challenges, we propose MTV-Inpaint, a unified multi-task video inpainting framework capable of handling both traditional scene completion and novel object insertion tasks. To unify these distinct tasks, we design a dual-branch spatial attention mechanism in the T2V diffusion U-Net, enabling seamless integration of scene completion and object insertion within a single framework. In addition to textual guidance, MTV-Inpaint supports multimodal control by integrating various image inpainting models through our proposed image-to-video (I2V) inpainting mode. Additionally, we propose a two-stage pipeline that combines keyframe inpainting with in-between frame propagation, enabling MTV-Inpaint to effectively handle long videos with hundreds of frames. Extensive experiments demonstrate that MTV-Inpaint achieves state-of-the-art performance in both scene completion and object insertion tasks. Furthermore, it demonstrates versatility in derived applications such as multi-modal inpainting, object editing, removal, image object brush, and the ability to handle long videos. Project page: https://mtv-inpaint.github.io/.
This paper has not been read by Pith yet.
Forward citations
Cited by 6 Pith papers
-
Geometry-Instructed Video Editing
GIVE uses paired depth-box and orientation-box geometry streams plus a graphics pipeline to train models for consistent object-level geometric edits like translate, rotate, and scale in videos.
-
Occlusion-Aware Physics-Semantic Keyframe Selection for Robust Video Editing
Occlusion-aware keyframe selection via structural, cycle-consistent tracking, and vision-language criteria improves diffusion video editing robustness without manual annotations.
-
CLEAR: Context-Aware Learning with End-to-End Mask-Free Inference for Adaptive Video Subtitle Removal
CLEAR achieves end-to-end mask-free video subtitle removal via dual-encoder self-supervised orthogonality and LoRA-based generation feedback, delivering +6.77 dB PSNR gains and strong zero-shot multilingual performance.
-
From Ideal to Real: Stable Video Object Removal under Imperfect Conditions
SVOR achieves stable, shadow-free video object removal under real-world imperfections via MUSE mask handling, DA-Seg localization, and curriculum training on real and synthetic data.
-
Occlusion-Aware Physics-Semantic Keyframe Selection for Robust Video Editing
A new keyframe selection framework combines structural, tracking, and semantic criteria to select reliable anchor frames for diffusion-based video editing under occlusion.
-
Controllable Video Object Insertion via Multiview Priors
A multi-view prior-based framework for video object insertion that uses dual-path conditioning and an integration-aware consistency module to improve appearance stability and occlusion handling.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.