AI 终于学会说“它不见了”
现在的视频分割模型有个毛病：物体离开画面，它不会告诉你“没了”，而是硬找一个长得像的东西继续框；物体怼到镜头前，它只切出一块纹理而不是整个物体；雕像、画、倒影这些“长得像但根本不是”的东西，它分不清。这篇把两件事合进一个方法：一是靠时间记忆把目标跟住，消失就承认消失，不漂移；二是加了一层“语义验证”，先用高速视觉匹配筛一遍，只对模糊的候选才动用大模型做推理，既滤掉视觉上像但本体不对的东西，又保持低延迟。它做 3D 重建时特别有用——一个误分类的干扰物就能毁掉整个资产。代码已开源。
📄 原文摘要(英文)
We present ENEAS, a unified, text-promptable method for instance tracking and semantic discovery. Text-promptable segmentation models, including the latest foundation models such as SAM 3, still suffer from temporal hallucinations, spatial fragmentation, and semantic misclassification: they fail to report target absence when an object leaves the field of view, segment local textures instead of the complete object during extreme close-ups, and prioritize visual features over ontological reality, so that visually similar artifacts such as statues, paintings, or reflections are segmented as target entities. ENEAS works two ways from a single method: precise tracking and high-quality segmentation of a unique instance, and open-concept discovery of every instance a text query names, resolved by a semantic verification layer. For tracking, we extend the geometrically robust SeC architecture, previously limited to point interactions, with a text-prompting adapter and leverage its temporal memory, so that the target is held through disappearance without drifting to distractors and kept whole even when it fills the entire view. For discovery, the verification layer combines high-speed visual embedding matching with conditional VLM refinement, invoking semantic reasoning only for ambiguous candidates, which filters out the ontological errors that visual-only models cannot distinguish while keeping latency low. Designed with 3D reconstruction in mind, where a single misclassified distractor corrupts the asset, ENEAS unlocks high-quality semantic tracking and segmentation of video, of broad libraries, and of collections of temporally or spatially unordered data, together with the discrimination to tell true instances from their doppelgangers: things that look alike but are not the same. The code and models are available at https://github.com/speridlabs/eneas