跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-14AI 評分44

StreamErase:邁向超高速串流影片物件移除

StreamErase: Towards Ultra-Fast Streaming Video Erasing

AI 導讀

StreamErase 在單張 GPU 上實現串流影片物件移除,延遲低於一秒,生成速度最高達 26 FPS。訓練時結合 self-rollout、attention sinks 和 KV cache rolling,配合滑動視窗因果注意力,令模型可在固定上下文窗口下恆速生成任意長影片。研究亦建立長影片串流物件移除基準 LongErase,並指出模型可泛化至真實影片情境。

正文

Published on Oct 14

Authors:

,

,

,

,

,

Abstract

Current video object removal methods suffer from prohibitive latency (minutes per video) and non-causal processing that prevents real-time interaction. We present StreamErase, enabling sub-second latency with up to 26 FPS streaming generation on a single GPU. Our approach first augments a text-to-video model with mask input to generate high-quality videos that erase target objects and synthesize coherent backgrounds, but does not perform inference on the fly. As such, we progressively transfer the erasing capability from a powerful bidirectional foundation model to an efficient unidirectional streaming eraser, enabling long-horizon erasing without sacrificing visual fidelity. Several key challenges arise when generating videos over long, potentially infinite horizons: (1) bridging the domain gap from training on finite length and extrapolating to long horizons, (2) sustaining high quality by preventing error accumulation, and (3) maintaining fast inference, without increasing computational cost as the context grows. To address these challenges, we carefully designed sliding-window causal attention with attention sinks. By incorporating self-rollout with attention sinks and KV cache rolling during training, we simulate inference-time extrapolations with a fixed context window, enabling constant-speed generation of arbitrarily long videos. Finally, we establish a dedicated benchmark, LongErase, for streaming long-video object removal. Our model achieves strong performance compared to existing video object erasing models and generalizes well to real-world video scenarios, uniquely enabling infinite-length streaming. With StreamErase, users can input a mask and see the erasing results unfold in real-time, delivering a truly interactive experience.

View arXiv page View PDF Project page GitHub 3 Add to collection

Get this paper in your agent:

hf papers read 2610.20137

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.20137 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.20137 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.20137 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co