Saved in:
Bibliographic Details
Main Authors: Wang, Feiran, Wu, Junyi, Cai, Dawen, Hong, Yuan, Yan, Yan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.08175
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918285859094528
author Wang, Feiran
Wu, Junyi
Cai, Dawen
Hong, Yuan
Yan, Yan
author_facet Wang, Feiran
Wu, Junyi
Cai, Dawen
Hong, Yuan
Yan, Yan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_08175
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CogniMap3D: Cognitive 3D Mapping and Rapid Retrieval
Wang, Feiran
Wu, Junyi
Cai, Dawen
Hong, Yuan
Yan, Yan
Computer Vision and Pattern Recognition
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.
title CogniMap3D: Cognitive 3D Mapping and Rapid Retrieval
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.08175