CVOct 16, 2025

ChangingGrounding: 3D Visual Grounding in Changing Scenes

arXiv:2510.14965v11 citationsh-index: 21
Originality Incremental advance
AI Analysis

This addresses the challenge for real-world robots to localize objects from language in dynamic environments, representing an incremental step by proposing a new benchmark and method.

The paper tackles the problem of 3D visual grounding in changing scenes, where existing methods rely on costly re-scans, and introduces ChangingGrounding, a benchmark for memory-driven agents, with Mem-ChangingGrounder achieving the highest localization accuracy while reducing exploration cost.

Real-world robots localize objects from natural-language instructions while scenes around them keep changing. Yet most of the existing 3D visual grounding (3DVG) method still assumes a reconstructed and up-to-date point cloud, an assumption that forces costly re-scans and hinders deployment. We argue that 3DVG should be formulated as an active, memory-driven problem, and we introduce ChangingGrounding, the first benchmark that explicitly measures how well an agent can exploit past observations, explore only where needed, and still deliver precise 3D boxes in changing scenes. To set a strong reference point, we also propose Mem-ChangingGrounder, a zero-shot method for this task that marries cross-modal retrieval with lightweight multi-view fusion: it identifies the object type implied by the query, retrieves relevant memories to guide actions, then explores the target efficiently in the scene, falls back when previous operations are invalid, performs multi-view scanning of the target, and projects the fused evidence from multi-view scans to get accurate object bounding boxes. We evaluate different baselines on ChangingGrounding, and our Mem-ChangingGrounder achieves the highest localization accuracy while greatly reducing exploration cost. We hope this benchmark and method catalyze a shift toward practical, memory-centric 3DVG research for real-world applications. Project page: https://hm123450.github.io/CGB/ .

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes