Object-Aware Video Matting with Cross-Frame Guidance
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913715227459584 |
|---|---|
| author | Zhang, Huayu Wu, Dongyue Shao, Yuanjie Sang, Nong Gao, Changxin |
| author_facet | Zhang, Huayu Wu, Dongyue Shao, Yuanjie Sang, Nong Gao, Changxin |
| contents | Recently, trimap-free methods have drawn increasing attention in human video matting due to their promising performance. Nevertheless, these methods still suffer from the lack of deterministic foreground-background cues, which impairs their ability to consistently identify and locate foreground targets over time and mine fine-grained details. In this paper, we present a trimap-free Object-Aware Video Matting (OAVM) framework, which can perceive different objects, enabling joint recognition of foreground objects and refinement of edge details. Specifically, we propose an Object-Guided Correction and Refinement (OGCR) module, which employs cross-frame guidance to aggregate object-level instance information into pixel-level detail features, thereby promoting their synergy. Furthermore, we design a Sequential Foreground Merging augmentation strategy to diversify sequential scenarios and enhance capacity of the network for object discrimination. Extensive experiments on recent widely used synthetic and real-world benchmarks demonstrate the state-of-the-art performance of our OAVM with only an initial coarse mask. The code and model will be available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_01262 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Object-Aware Video Matting with Cross-Frame Guidance Zhang, Huayu Wu, Dongyue Shao, Yuanjie Sang, Nong Gao, Changxin Computer Vision and Pattern Recognition Recently, trimap-free methods have drawn increasing attention in human video matting due to their promising performance. Nevertheless, these methods still suffer from the lack of deterministic foreground-background cues, which impairs their ability to consistently identify and locate foreground targets over time and mine fine-grained details. In this paper, we present a trimap-free Object-Aware Video Matting (OAVM) framework, which can perceive different objects, enabling joint recognition of foreground objects and refinement of edge details. Specifically, we propose an Object-Guided Correction and Refinement (OGCR) module, which employs cross-frame guidance to aggregate object-level instance information into pixel-level detail features, thereby promoting their synergy. Furthermore, we design a Sequential Foreground Merging augmentation strategy to diversify sequential scenarios and enhance capacity of the network for object discrimination. Extensive experiments on recent widely used synthetic and real-world benchmarks demonstrate the state-of-the-art performance of our OAVM with only an initial coarse mask. The code and model will be available. |
| title | Object-Aware Video Matting with Cross-Frame Guidance |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.01262 |