按任意粒度计数
Count Anything at Any Granularity
AI总结：
本文提出多粒度计数框架，通过显式定义计数粒度解决开放世界计数问题，构建了最大的标注数据集KubriCount，并训练了HieraCount模型提升计数精度与泛化能力。
摘要：
开放世界物体计数仍存在脆弱性：尽管视觉-语言模型（VLMs）迅速发展，但可靠计数用户意图仍难解决。我们指出核心原因是计数粒度未被显式定义；用户可能指特定身份、属性、实例类型、类别或抽象概念，但大多数方法将'计数什么'视为单一类别匹配问题。本文将开放世界计数重新定义为多粒度计数，其中视觉示例指定目标外观，细粒度文本（可选负提示）指定意图的语义粒度，涵盖五个显式层级。显式定义粒度，然而，暴露了一个关键数据瓶颈：现有计数数据集缺乏多类别场景、可控干扰因素和实例级标注，无法验证细粒度提示语义。为此，我们提出首个全自动数据扩展流程，整合可控3D合成、一致图像编辑和VLM基于过滤，构建了最大的标注计数数据集KubriCount，支持训练和多粒度评估。系统评估揭示，多模态大语言模型和专门计数模型在细粒度区分下存在严重提示跟随失败。受此启发，我们训练HieraCount，一个联合利用文本和视觉示例作为互补目标规范的多粒度计数模型。HieraCount显著提升多粒度计数精度，并稳健泛化到挑战性现实场景。项目页面见：https://verg-avesta.github.io/KubriCount/.
英文摘要：
Open-world object counting remains brittle: despite rapid advances in vision-language models (VLMs), reliably counting the objects a user intends is far from solved. We argue that a central reason is that counting granularity is left implicit; users may refer to a specific identity, an attribute, an instance type, a category, or an abstract concept, yet most methods treat "what to count" as a single, category-level matching problem. In this work, we redefine open-world counting as multi-grained counting, where visual exemplars specify target appearance and fine-grained text, with optional negative prompts, specifies the intended semantic granularity across five explicit levels. Making granularity explicit, however, exposes a critical data bottleneck: existing counting datasets lack the multi-category scenes, controlled distractors, and instance-level annotations needed to verify fine-grained prompt semantics. To address this, we propose the first fully automatic data-scaling pipeline that integrates controllable 3D synthesis with consistent image editing and VLM-based filtering, and use it to construct KubriCount, the largest and most comprehensively annotated counting dataset to date, supporting both training and multi-grained evaluation. Systematic benchmarking reveals that both multimodal large language models and specialist counting models exhibit severe prompt-following failures under fine-grained distinctions. Motivated by these findings, we train HieraCount, a multi-grained counting model that jointly leverages text and visual exemplars as complementary target specifications. HieraCount substantially improves multi-grained counting accuracy and generalizes robustly to challenging real-world scenarios. The project page is available here: https://verg-avesta.github.io/KubriCount/.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
