The survey reviews spatial memory methods across 88 references, defines α as peak runtime memory over map size, profiles neural methods showing α from 2.3 to 215 on A100 GPU, and proposes a standardized evaluation protocol plus α-aware budgeting.
arXiv preprint arXiv:2503.14665 (2025) 8
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
A learnable confidence framework in 3D Gaussian Splatting balances photometric and geometric losses while penalizing per-primitive variance to produce state-of-the-art unbounded meshes efficiently.
citing papers explorer
-
A Survey of Spatial Memory Representations for Efficient Robot Navigation
The survey reviews spatial memory methods across 88 references, defines α as peak runtime memory over map size, profiles neural methods showing α from 2.3 to 215 on A100 GPU, and proposes a standardized evaluation protocol plus α-aware budgeting.
-
Confidence-Based Mesh Extraction from 3D Gaussians
A learnable confidence framework in 3D Gaussian Splatting balances photometric and geometric losses while penalizing per-primitive variance to produce state-of-the-art unbounded meshes efficiently.