SHREC 2025: Retrieval of Optimal Objects for Multi-modal Enhanced Language and Spatial Assistance (ROOMELSA)
This addresses the need for robust, real-world 3D recognition systems for applications like spatial assistance, though it is incremental as it builds on existing benchmarks and methods.
The paper tackles the problem of retrieving 3D models from cluttered scenes based on vague, free-form natural language descriptions, presenting the ROOMELSA benchmark with over 44,000 queries. The result shows that while coarse object retrieval is largely solved, only one top model consistently ranked the correct match first across nearly all test cases.
Recent 3D retrieval systems are typically designed for simple, controlled scenarios, such as identifying an object from a cropped image or a brief description. However, real-world scenarios are more complex, often requiring the recognition of an object in a cluttered scene based on a vague, free-form description. To this end, we present ROOMELSA, a new benchmark designed to evaluate a system's ability to interpret natural language. Specifically, ROOMELSA attends to a specific region within a panoramic room image and accurately retrieves the corresponding 3D model from a large database. In addition, ROOMELSA includes over 1,600 apartment scenes, nearly 5,200 rooms, and more than 44,000 targeted queries. Empirically, while coarse object retrieval is largely solved, only one top-performing model consistently ranked the correct match first across nearly all test cases. Notably, a lightweight CLIP-based model also performed well, although it struggled with subtle variations in materials, part structures, and contextual cues, resulting in occasional errors. These findings highlight the importance of tightly integrating visual and language understanding. By bridging the gap between scene-level grounding and fine-grained 3D retrieval, ROOMELSA establishes a new benchmark for advancing robust, real-world 3D recognition systems.