Paper Overview
- Field: Computer Vision (CV)
- Authors: Nhan Tran, Hijung Valentina Shin, Abe Davis, Mackenzie Leake
- Published: 2026-10-29
- arXiv: 2610.40653
Abstract (translated from the original)
In film editing, every frame matters. While macro, content-level edits shape the high-level narrative of a film, small local edits often control timing and direct visual attention. For example, editors can adjust the precise timing of clips to control the length of a meaningful silence, or cut to shots that highlight a specific character's reactions to important moments. These small, detailed edits are slow and tedious to make in standard editing tools because users have to map high-level narrative goals to low-level frame-by-frame adjustments. At the same time, these fine-scale adjustments, which the authors call micro-edits, can be nuanced and expressive, with different choices serving different creative goals.
In this work, the authors start by conducting a formative study with professional editors to understand how micro-edits are used in practice, and then develop computational support for making such edits. *(The abstract in the source post is truncated; see the arXiv page for the complete abstract, method, and evaluation.)*
> Note: the Chinese-language abstract attached to this forum post describes a different topic (differential privacy, propose-filter-release) and appears to be a mis-scraped summary; it does not match the paper's official abstract above. Readers should rely on the arXiv original.
---
*Auto-collected on 2026-10-31.*