SD-MVS: Segmentation-Driven Deformation Multi-View Stereo with Spherical Refinement and EM Optimization
Authors: Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang, Zhaoqi Wang
AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Evaluations on the ETH3D high-resolution multi-view stereo benchmark and the Tanks and Temples dataset demonstrate that our method can achieve state-of-the-art results with less time consumption. ... Experiments Datasets and Implementation Details We evaluate our work on both ETH3D high-resolution benchmark (Sch ops et al. 2017) and Tanks and Temples benchmark (TNT) (Knapitsch et al. 2017). |
| Researcher Affiliation | Academia | 1Institute of Computing Technology, Chinese Academy of Sciences 2Agricultural Information Institute, Chinese Academy of Agricultural Sciences 3Key Laboratory of Agricultural Big Data, Ministry of Agriculture and Rural Affairs |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. The methods are described in prose and mathematical formulations. |
| Open Source Code | No | The paper does not provide any explicit statements about releasing source code or links to a code repository for the described methodology. |
| Open Datasets | Yes | We evaluate our work on both ETH3D high-resolution benchmark (Sch ops et al. 2017) and Tanks and Temples benchmark (TNT) (Knapitsch et al. 2017). |
| Dataset Splits | Yes | We evaluate our work on both ETH3D high-resolution benchmark (Sch ops et al. 2017) and Tanks and Temples benchmark (TNT) (Knapitsch et al. 2017). |
| Hardware Specification | Yes | Our method is implemented on a system equipped with an Intel(R) Core(TM) i7-10700 CPU @ 2.90GHz and an NVIDIA Ge Force RTX 3080 graphics card. |
| Software Dependencies | No | The paper mentions 'CUDA operators' and the 'Segment Anything Model (SAM)' but does not provide specific version numbers for any software dependencies, libraries, or frameworks used for reproducibility. |
| Experiment Setup | Yes | Concerning parameter setting, {wms, wrp, wpc, L, k, τ, Nmax, η} = {1, 0.2, 0.2, 11, 3, 2, 3, 0.1}. In cost calculation, we take the matching strategy of every other row and column. |