Cross-Spectral Gaussian Splatting with Spatial Occupancy Consistency
Authors: Haipeng Guo, Huanyu Liu, Jiazheng Wen, Junbao Li
AAAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Comprehensive experiments demonstrate that SOC-GS achieves superior performance in novel view synthesis and real-time cross-spectral rendering. We evaluate the performance of SOC-GS using the X-Ne RF and Real Sense datasets, which involve bi-modality and tri-modality cross-spectral scene representation, and provide a comprehensive comparison with several advanced methods based on Ne RF and 3DGS. |
| Researcher Affiliation | Academia | Faculty of Computing, Harbin Institute of Technology, Harbin, China EMAIL, EMAIL, EMAIL, EMAIL |
| Pseudocode | No | The paper describes the method in a 'Method' section and uses Figure 2 to illustrate a pipeline, but it does not contain a clearly labeled 'Pseudocode' or 'Algorithm' block, nor does it present structured steps in a code-like format. |
| Open Source Code | Yes | Code https://github.com/Guo HP-HIT/SOC-GS. |
| Open Datasets | Yes | We evaluated the performance of our method using the publicly X-Ne RF dataset and our self-collected Real Sense dataset. (1) X-Ne RF dataset. X-Ne RF consists of 16 indoor forward-facing scenes... (Poggi et al. 2022) |
| Dataset Splits | Yes | X-Ne RF consists of 16 indoor forward-facing scenes, each containing about 30 images from RGB, Multi-spectral and Infrared cameras, 5 images reserved for testing, and the rest for training. |
| Hardware Specification | Yes | We implemented our method using Py Torch framework on one single RTX3090 by taichi (Hu et al. 2019, 2020, 2021) to accelerate optimization and rasterisation. |
| Software Dependencies | No | We implemented our method using Py Torch framework on one single RTX3090 by taichi (Hu et al. 2019, 2020, 2021) to accelerate optimization and rasterisation. |
| Experiment Setup | Yes | We start from the point cloud output from Sf M to pre-train Gaussians for 5000 iterations using only RGB images, then initialize the camera poses of the remaining spectral images. ... We set the confidence threshold for Lo FTR matcher to 0.5. ... We use λ = 0.2 for all experiments, consistent with 3DGS. |