paper-with-me

Papers

Generative Omnimatte: Learning to Decompose Video into Layers

2024-11-25 · CVPR 2025 1 · Yao-Chih Lee, Erika Lu, Sarah Rumbley, Michal Geyer, Jia-Bin Huang, Tali Dekel, Forrester Cole

Given a video and a set of input object masks, an omnimatte method aims to decompose the video into semantically meaningful layers containing individual objects along with their associated effects, such as shadows and reflections. Existing omnimatte methods assume a static background or accurate pose and depth estimation and produce poor decompositions when these assumptions are violated. Furthermore, due to the lack of generative prior on natural videos, existing methods cannot complete dynamic occluded regions. We present a novel generative layered video decomposition framework to address the omnimatte problem. Our method does not assume a stationary scene or require camera pose or depth information and produces clean, complete layers, including convincing completions of occluded dynamic regions. Our core idea is to train a video diffusion model to identify and remove scene effects caused by a specific object. We show that this model can be finetuned from an existing video inpainting model with a small, carefully curated dataset, and demonstrate high-quality decompositions and editing results for a wide range of casually captured videos containing soft shadows, glossy reflections, splashing water, and more.

📄 PDF Abstract BibTeX arXiv:2411.16683

Code (0)

등록된 구현이 없습니다.

Tasks

Depth EstimationVideo Inpainting

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
Inpainting Train a convolutional neural network to generate the contents of an arbitrary image region conditioned on its surroundings.

Similar Papers 제목 키워드 기반

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

2025-03-23 · Dvir Samuel, Matan Levy, Nir Darshan, Gal Chechik 외

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 …

Image InpaintingObject

OmnimatteRF: Robust Omnimatte with 3D Background Modeling

2023-09-14 · ICCV 2023 1 · Geng Lin, Chen Gao, Jia-Bin Huang, Changil Kim 외

Video matting has broad applications, from adding interesting effects to casually captured movies to assisting video production professionals. Matting with associated effects such as shadows and reflections has also attr…

Image MattingVideo Matting

Omnimatte3D: Associating Objects and Their Effects in Unconstrained Monocular Video

2023-01-01 · CVPR 2023 1 · Mohammed Suhail, Erika Lu, Zhengqi Li, Noah Snavely 외

We propose a method to decompose a video into a background and a set of foreground layers, where the background captures stationary elements while the foreground layers capture moving objects along with their associa…

Depth Estimation

EasyOmnimatte: Taming Pretrained Inpainting Diffusion Models for End-to-End Video Layered Decomposition

2025-12-26 · Yihan Hu, Xuelin Chen, Xiaodong Cun arxiv

Existing video omnimatte methods typically rely on slow, multi-stage, or inference-time optimization pipelines that fail to fully exploit powerful generative priors, producing suboptimal decompositions. Our key insight i…

Video Inpainting

Omnimatte: Associating Objects and Their Effects in Video

2021-05-14 · CVPR 2021 1 · Erika Lu, Forrester Cole, Tali Dekel, Andrew Zisserman 외

Computer vision is increasingly effective at segmenting objects in images and videos; however, scene effects related to the objects -- shadows, reflections, generated smoke, etc -- are typically overlooked. Identifying s…