cs.CVNov 10, 2026

Is It Still There? Place-Registered Verification Makes VLMs Reliable Scene-Change Detectors

Authors: Jinjie Xie, Baihua Li, Qinggang Meng

Organizations: Department of Computer Science, Loughborough University, United Kingdom

Abstract

A robot that returns to a space must tell which objects were added, removed or moved since its last visit, while its trajectory, viewpoints and lighting differ between the two visits. We find that multi-image vision-language models (VLMs) fail at this task mainly because they cannot find the place where an object was. A VLM recognises what each frame shows but cannot check whether an object is still at its place in the other capture. It therefore reports objects that only one capture shows and misses most removed and moved objects. We propose STILL, which reformulates change detection as object verification at a registered place. 3D geometry registers the place of each change hypothesis in the other capture, and one VLM answers, from a scene view and a local place view, whether the object is still at that place, trained with supervision of the same form. Under the official SceneDiff protocol, STILL raises the main metric obj/sc AP from 24.0 to 37.8, and from 11.6 to 20.6 on the egocentric kitchen subset without any kitchen training data. It improves F1 by more than 21 points over a VLM fine-tuned on the same annotations and adds only about 11% to the runtime.

Figures & tables

Appendix figures & tables15 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. VLMs Can Describe, But Not Measure: Object-Centric Scene Understanding for Robotic Manipulation

    Sep 23, 2026Enrico Saccon, Tommaso Faraci, Iñigo De La Ossa Zarzuelo +3Robotic ManipulationVLMs for Robotics

  2. MissingBench-Verified: Probing Vision-Language Models' Inability to Detect Missing Object Parts

    Jul 21, 2026Wenqi Marshall Guo, Qingyun Qian, Shiyu Zhou +2VLM EvaluationObject Hallucination in VLMs