Submitted anonymously.

Submission data

Full name	Temporal-AwareDepthFusion
Description	A temporal depth fusion approach that combines stereo-derived depth maps across consecutive frames to improve scene reconstruction and localization. The system uses motion-compensated depth aggregation, confidence-based filtering, and inertial guidance to produce stable depth estimates in dynamic and low-light environments. Global optimization is applied to reduce drift and maintain long-term consistency.
Parameters	Depth fusion window: 12 frames Depth confidence threshold: 0.70 Motion compensation iterations: 8 Keyframe overlap ratio: 0.65 Global optimization interval: 50 frames IMU influence factor: 0.30
Programming language(s)	C++, Python, CUDA
Hardware	A100
Submission creation date	24 Jun, 2026
Last edited	24 Jun, 2026

High-res multi-view results

Low-res many-view results

Low-res two-view results

SLAM results