CogniMap3D: Cognitive 3D Mapping and Rapid Retrieval
This addresses the problem of efficient spatial knowledge storage and rapid retrieval for robotics or AR/VR applications, representing an incremental/hybrid advancement.
The paper tackled dynamic 3D scene understanding and reconstruction by introducing CogniMap3D, a bioinspired framework that integrates motion cues, cognitive mapping, and optimization, achieving state-of-the-art performance in video depth estimation, camera pose reconstruction, and 3D mapping tasks.
We present CogniMap3D, a bioinspired framework for dynamic 3D scene understanding and reconstruction that emulates human cognitive processes. Our approach maintains a persistent memory bank of static scenes, enabling efficient spatial knowledge storage and rapid retrieval. CogniMap3D integrates three core capabilities: a multi-stage motion cue framework for identifying dynamic objects, a cognitive mapping system for storing, recalling, and updating static scenes across multiple visits, and a factor graph optimization strategy for refining camera poses. Given an image stream, our model identifies dynamic regions through motion cues with depth and camera pose priors, then matches static elements against its memory bank. When revisiting familiar locations, CogniMap3D retrieves stored scenes, relocates cameras, and updates memory with new observations. Evaluations on video depth estimation, camera pose reconstruction, and 3D mapping tasks demonstrate its state-of-the-art performance, while effectively supporting continuous scene understanding across extended sequences and multiple visits.