MDN-Control: Mask-Depth-Noise Guided Region Control for Multi-Subject Video Editing

• URL: http://arxiv.org/abs/2609.16475v1
• Date: Tue, 15 Sep 2026 00:58:55 GMT
• Title: MDN-Control: Mask-Depth-Noise Guided Region Control for Multi-Subject Video Editing
• Abstract summary: Multi subject video editing modifies designated subjects while preserving non target content.<n>Existing approaches rely on masks and struggle to distinguish overlapping subjects or ensure consistent generation.<n>We propose MDN-Control, a training free framework jointly controlling target localization, occlusion geometry, and appearance.<n> Experiments on MSVBench show that MDN-Control achieves the lowest CM-Err and the highest Q-Edit, while maintaining competitive text alignment and temporal consistency.
• Score: 19.25272895567409
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi subject video editing modifies designated subjects while preserving non target content, but faces cross subject attribute leakage, and occlusion ambiguity. Existing approaches rely on masks and struggle to distinguish overlapping subjects or ensure consistent generation. To address these limitations, we propose MDN-Control, a training free framework jointly controlling target localization, occlusion geometry, and appearance initialization. Specifically, mask-guided localization provides consistent target localization, while depth-aware occlusion control resolves ambiguous boundaries between overlapping subjects. We further introduce noise latent prompting, which retrieves Gaussian initializations from a noise library for prompt relevant priors. Experiments on MSVBench show that MDN-Control achieves the lowest CM-Err and the highest Q-Edit, while maintaining competitive text alignment and temporal consistency, demonstrating the effectiveness of combining spatial, geometric, and latent priors for multi subject video editing.

Related papers

• Drag within Prior Distribution: Text-Conditioned Point-Based Image Editing within Distribution Constraints [7.503616785263929]
  Diffusion-based point editing can manipulate image semantics and fine details by applying localized perturbations on the manifold of noise latent perturbations.<n>Traditional point-based editing relies on pairs of handle and target points to define motion trajectories.<n>We introduce a CLIP-based model to evaluate and guide intermediate editing steps, ensuring that the generated results remain both semantically aligned.
  arXiv  Detail & Related papers  (2026-05-13T11:05:31Z)
• CARE-Edit: Condition-Aware Routing of Experts for Contextual Image Editing [17.372230178356357]
  We propose Condition-Aware of Experts (CARE-Edit) that aligns model computation with specific editing competencies.<n>At its core, a lightweight latent-attention router assigns encoded diffusion tokens to four specialized experts.<n>Experiments validate CARE-Edit's strong performance on contextual editing tasks.
  arXiv  Detail & Related papers  (2026-03-09T16:40:47Z)
• AnyMS: Bottom-up Attention Decoupling for Layout-guided and Training-free Multi-subject Customization [55.06425570300248]
  We present AnyMS, a training-free framework for layout-guided multi-subject customization.<n>AnyMS leverages three input conditions: text prompt, subject images, and layout constraints.<n>AnyMS achieves state-of-the-art performance, supporting complex compositions and scaling to a larger number of subjects.
  arXiv  Detail & Related papers  (2025-12-29T15:26:25Z)
• LoVoRA: Text-guided and Mask-free Video Object Removal and Addition with Learnable Object-aware Localization [49.945233586949286]
  LoVoRA is a novel framework for mask-free video object removal and addition.<n>Our approach integrates image-to-video translation, optical flow-based mask propagation, and videopainting, enabling temporally consistent edits.<n>LoVoRA achieves end-to-end video editing without requiring external control signals during inference.
  arXiv  Detail & Related papers  (2025-12-02T17:01:07Z)
• ReMix: Towards a Unified View of Consistent Character Generation and Editing [22.04681457337335]
  ReMix is a unified framework for character-consistent generation and editing.<n>It constitutes two core components: the ReMix Module and IP-ControlNet.<n>ReMix supports a wide range of tasks, including personalized generation, image editing, style transfer, and multi-condition synthesis.
  arXiv  Detail & Related papers  (2025-10-11T10:31:56Z)
• FOCUS: Unified Vision-Language Modeling for Interactive Editing Driven by Referential Segmentation [55.01077993490845]
  Recent Large Vision Language Models (LVLMs) demonstrate promising capabilities in unifying visual understanding and generative modeling.<n>We introduce FOCUS, a unified LVLM that integrates segmentation-aware perception and controllable object-centric generation within an end-to-end framework.
  arXiv  Detail & Related papers  (2025-06-20T07:46:40Z)
• MDE-Edit: Masked Dual-Editing for Multi-Object Image Editing via Diffusion Models [10.798205956644317]
  We propose a training-free, inference-stage optimization approach that enables precise localized image manipulation in complex multi-object scenes, named MDE-Edit.<n>Extensive experiments demonstrate that MDE-Edit outperforms state-of-the-art methods in editing accuracy and visual quality, offering a robust solution for complex multi-object image manipulation tasks.
  arXiv  Detail & Related papers  (2025-05-08T10:01:14Z)
• MAKIMA: Tuning-free Multi-Attribute Open-domain Video Editing via Mask-Guided Attention Modulation [55.101611012677616]
  Diffusion-based text-to-image (T2I) models have demonstrated remarkable results in global video editing tasks.<n>We present MAKIMA, a tuning-free MAE framework built upon pretrained T2I models for open-domain video editing.
  arXiv  Detail & Related papers  (2024-12-28T02:36:51Z)
• Re-Attentional Controllable Video Diffusion Editing [48.052781838711994]
  We propose a Re-Attentional Controllable Video Diffusion Editing (ReAtCo) method.<n>To align the spatial placement of the target objects with the edited text prompt in a training-free manner, we propose a Re-Attentional Diffusion (RAD)<n>RAD refocuses the cross-attention activation responses between the edited text prompt and the target video during the denoising stage, resulting in a spatially location-aligned and semantically high-fidelity manipulated video.
  arXiv  Detail & Related papers  (2024-12-16T12:32:21Z)
• Addressing Text Embedding Leakage in Diffusion-based Image Editing [33.1686050396517]
  We introduce Attribute-Leakage-free Editing (ALE), a framework that tackles attribute leakage at its source.<n>ALE combines Object-Restricted Embeddings (ORE) to disentangle text embeddings, Region-Guided Blending for Cross-Attention Masking (RGB-CAM) for spatially precise attention, and Background Blending (BB) to preserve non-edited content.
  arXiv  Detail & Related papers  (2024-12-06T02:10:07Z)
• When ControlNet Meets Inexplicit Masks: A Case Study of ControlNet on its Contour-following Ability [93.15085958220024]
  ControlNet excels at creating content that closely matches precise contours in user-provided masks. When these masks contain noise, as a frequent occurrence with non-expert users, the output would include unwanted artifacts. This paper first highlights the crucial role of controlling the impact of these inexplicit masks with diverse deterioration levels through in-depth analysis. An advanced Shape-aware ControlNet consisting of a deterioration estimator and a shape-prior modulation block is devised.
  arXiv  Detail & Related papers  (2024-03-01T11:45:29Z)

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.