Query Quantized Neural SLAM
Authors: Sijia Jiang, Jing Hua, Zhizhong Han
AAAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We evaluate our methods on widely used benchmarks containing synthetic data and real scans. Our numerical and visual comparisons justify the effectiveness of our modules, and show superiorities over the latest methods in terms of accuracy in scene reconstruction and camera tracking. The paper includes sections like "Experiments and Analysis" and "Ablation Studies", which involve empirical data analysis and performance metrics. |
| Researcher Affiliation | Academia | All authors are affiliated with "Wayne State University", and their email addresses use the "@wayne.edu" domain, indicating an academic affiliation. |
| Pseudocode | No | The paper describes methods and processes verbally and through mathematical equations, but does not include any clearly labeled pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not contain an unambiguous statement indicating the release of source code, nor does it provide a specific repository link for the methodology described. |
| Open Datasets | Yes | We evaluate our method on real-world indoor scenes from 4 datasets and 8 synthetic Replica (Straub et al. 2019) scenes following Co-SLAM. Additionally, we assess reconstruction quality on 7 noisy scenes from Synthetic RGBD (Rajpal et al. 2023) and compare our reconstruction and camera tracking accuracy to SOTAs on 6 scenes from NICE-SLAM (Zhu et al. 2022) with Bundle Fusion ground truth poses. Camera tracking is also reported on 3 scenes from TUM RGB-D (Sturm et al. 2012). |
| Dataset Splits | No | The paper mentions evaluating on specific scenes from various datasets (e.g., 8 Replica scenes, 7 Synthetic RGBD scenes, 6 NICE-SLAM scenes, 3 TUM RGB-D scenes) but does not provide specific training, validation, or test dataset splits (e.g., percentages, sample counts, or citations to predefined splits) for the main SLAM experiments. While it refers to a multi-view reconstruction application using Go-Surf on ScanNet scenes, it does not detail the splits for its own method's evaluation. |
| Hardware Specification | No | The paper does not provide specific hardware details such as GPU models, CPU types, or memory amounts used for running the experiments. |
| Software Dependencies | No | The paper does not provide specific software dependencies with version numbers (e.g., Python, PyTorch, CUDA versions) that are needed to replicate the experiment. |
| Experiment Setup | Yes | For query sampling, we sample N = 43 queries per ray, including 32 uniformly sampled and 11 near-surface sampled. We use B = 128 codes for vector quantization and a 2563 TSDF resolution with a truncated threshold tr = 10 voxel size near surfaces. Loss parameters are set as t = 0.1, α = 0.02, β = 0.06, γ = 0.0001, ζ = 200, η = 2. The paper also mentions a bundle adjustment procedure every 5 frames and selecting a key frame every 5 frames, along with incrementally fusing input depth images into a TSDF grid with a resolution of 256. |