OmnimatteZero: Training-free Real-time Omnimatte with Pre-trained Video Diffusion Models

• URL: http://arxiv.org/abs/2503.18033v1
• Date: Sun, 23 Mar 2025 11:26:48 GMT
• Title: OmnimatteZero: Training-free Real-time Omnimatte with Pre-trained Video Diffusion Models
• Authors: Dvir Samuel, Matan Levy, Nir Darshan, Gal Chechik, Rami Ben-Ari,
• Abstract summary: We present OmnimatteZero, a training-free approach that leverages off-the-shelf pre-trained video diffusion models for omnimatte.<n>It can remove objects from videos, extract individual object layers along with their effects, and composite those objects onto new videos.<n>We show that self-attention maps capture information about the object and its footprints and use them to inpaint the object's effects, leaving a clean background.
• Score: 31.48981364573974
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Omnimatte aims to decompose a given video into semantically meaningful layers, including the background and individual objects along with their associated effects, such as shadows and reflections. Existing methods often require extensive training or costly self-supervised optimization. In this paper, we present OmnimatteZero, a training-free approach that leverages off-the-shelf pre-trained video diffusion models for omnimatte. It can remove objects from videos, extract individual object layers along with their effects, and composite those objects onto new videos. We accomplish this by adapting zero-shot image inpainting techniques for video object removal, a task they fail to handle effectively out-of-the-box. We then show that self-attention maps capture information about the object and its footprints and use them to inpaint the object's effects, leaving a clean background. Additionally, through simple latent arithmetic, object layers can be isolated and recombined seamlessly with new video layers to produce new videos. Evaluations show that OmnimatteZero not only achieves superior performance in terms of background reconstruction but also sets a new record for the fastest Omnimatte approach, achieving real-time performance with minimal frame runtime.

Related papers

• OmniEraser: Remove Objects and Their Effects in Images with Paired Video-Frame Data [21.469971783624402]
  In this paper, we propose Video4Removal, a large-scale dataset comprising over 100,000 high-quality samples with realistic object shadows and reflections.<n>By constructing object-background pairs from video frames with off-the-shelf vision models, the labor costs of data acquisition can be significantly reduced.<n>To avoid generating shape-like artifacts and unintended content, we propose Object-Background Guidance.<n>We present OmniEraser, a novel method that seamlessly removes objects and their visual effects using only object masks as input.
  arXiv  Detail & Related papers  (2025-01-13T15:12:40Z)
• Generative Omnimatte: Learning to Decompose Video into Layers [29.098471541412113]
  We present a novel generative layered video decomposition framework to address the omnimatte problem.<n>Our core idea is to train a video diffusion model to identify and remove scene effects caused by a specific object.<n>We show that this model can be finetuned from an existing video inpainting model with a small, carefully curated dataset.
  arXiv  Detail & Related papers  (2024-11-25T18:59:57Z)
• Puppet-Master: Scaling Interactive Video Generation as a Motion Prior for Part-Level Dynamics [67.97235923372035]
  We present Puppet-Master, an interactive video generative model that can serve as a motion prior for part-level dynamics. At test time, given a single image and a sparse set of motion trajectories, Puppet-Master can synthesize a video depicting realistic part-level motion faithful to the given drag interactions.
  arXiv  Detail & Related papers  (2024-08-08T17:59:38Z)
• Rethinking Image-to-Video Adaptation: An Object-centric Perspective [61.833533295978484]
  We propose a novel and efficient image-to-video adaptation strategy from the object-centric perspective. Inspired by human perception, we integrate a proxy task of object discovery into image-to-video transfer learning.
  arXiv  Detail & Related papers  (2024-07-09T13:58:10Z)
• OmnimatteRF: Robust Omnimatte with 3D Background Modeling [42.844343885602214]
  We propose a novel video matting method, OmnimatteRF, that combines dynamic 2D foreground layers and a 3D background model. The 2D layers preserve the details of the subjects, while the 3D background robustly reconstructs scenes in real-world videos.
  arXiv  Detail & Related papers  (2023-09-14T14:36:22Z)
• WALDO: Future Video Synthesis using Object Layer Decomposition and Parametric Flow Prediction [82.79642869586587]
  WALDO is a novel approach to the prediction of future video frames from past ones. Individual images are decomposed into multiple layers combining object masks and a small set of control points. The layer structure is shared across all frames in each video to build dense inter-frame connections.
  arXiv  Detail & Related papers  (2022-11-25T18:59:46Z)
• Occlusion-Aware Video Object Inpainting [72.38919601150175]
  This paper presents occlusion-aware video object inpainting, which recovers both the complete shape and appearance for occluded objects in videos. Our technical contribution VOIN jointly performs video object shape completion and occluded texture generation. For more realistic results, VOIN is optimized using both T-PatchGAN and a newoc-temporal YouTube attention-based multi-class discriminator.
  arXiv  Detail & Related papers  (2021-08-15T15:46:57Z)
• Attention-guided Temporal Coherent Video Object Matting [78.82835351423383]
  We propose a novel deep learning-based object matting method that can achieve temporally coherent matting results. Its key component is an attention-based temporal aggregation module that maximizes image matting networks' strength. We show how to effectively solve the trimap generation problem by fine-tuning a state-of-the-art video object segmentation network.
  arXiv  Detail & Related papers  (2021-05-24T17:34:57Z)
• Omnimatte: Associating Objects and Their Effects in Video [100.66205249649131]
  Scene effects related to objects in video are typically overlooked by computer vision. In this work, we take a step towards solving this novel problem of automatically associating objects with their effects in video. Our model is trained only on the input video in a self-supervised manner, without any manual labels, and is generic---it produces omnimattes automatically for arbitrary objects and a variety of effects.
  arXiv  Detail & Related papers  (2021-05-14T17:57:08Z)

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.