跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 28 天前AI 評分50

更多記憶能生成更好的影片嗎?長影片生成中視覺記憶的對照研究

More Memory, Better Videos? A Controlled Study of Visual Memory in Long-Video Generation

AI 導讀

這項對照研究發現,長影片生成中的視覺記憶檢索可提升歷史外觀相似度,卻可能因沿用過時外觀而降低故事當前狀態的準確性。VMem-Bench 顯示,檢索令實體召回率由 0.559 升至 0.628-0.693,但精確率由 0.977 降至 0.915-0.938,避免禁用實體的表現亦由 0.968 降至 0.845-0.898。研究指出,檢索相關性或最終影片的一致性本身不足以證明記憶有用。

正文

Published on Oct 26

Authors:

,

,

,

,

,

,

,

Abstract

Visual memory improves historical consistency but can reduce current-story accuracy by reinforcing outdated appearances, showing that retrieval relevance alone does not prove memory utility.

Long-video generators increasingly retrieve past visual observations to prevent identity drift. The intuition is compelling: more access to history should make future video more consistent. But an image can be faithful to the past and wrong for the present. Does visual memory always improve the generated story? We investigate this question through VMem-Bench, a two-track diagnostic study. Track-A measures which references are selected from 92 real films (16,548 segments), before generation and without generator confounds. Track-B compares four retrieval policies with no-memory and gold-informed last-seen controls on 30 causally generated stories (2,824 segments) using a shared generator. Retrieval increases entity recall from 0.559 to 0.628-0.693 and improves similarity to past appearances, but decreases precision from 0.977 to 0.915-0.938 and forbidden-entity avoidance from 0.968 to 0.845-0.898. It can also reinforce obsolete appearances after the story changes them. Conversely, high long-gap recall can arise without memory when the prompt itself supplies the appearance; an appearance-stripping analysis exposes this confound. These results distinguish historical fidelity from current-story correctness and show why retrieval relevance or final-video consistency alone does not establish memory utility.

View arXiv page View PDF Project page GitHub Add to collection

Get this paper in your agent:

hf papers read 2610.35001

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/2610.35001 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/2610.35001 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/2610.35001 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