Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo
Authors: Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang
AAAI 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive evaluations on ETH3D and Tanks & Temples benchmarks demonstrate that our method can achieve state-of-the-art performance with excellent robustness and generalization. |
| Researcher Affiliation | Academia | 1Institute of Computing Technology, Chinese Academy of Sciences 2Harbin Institute of Technology, Shenzhen 3Nanjing University of Science and Technology, Nanjing 4Agricultural Information Institute, Chinese Academy of Agricultural Sciences 5Key Laboratory of Agricultural Big Data, Ministry of Agriculture and Rural Affairs EMAIL, EMAIL, EMAIL, EMAIL, EMAIL, EMAIL |
| Pseudocode | No | The paper describes methods in prose and mathematical formulations but does not contain any explicitly labeled pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any explicit statement about open-sourcing the code or a link to a code repository. |
| Open Datasets | Yes | Extensive evaluations on ETH3D and Tanks & Temples benchmarks demonstrate that our method can achieve state-of-the-art performance with excellent robustness and generalization. |
| Dataset Splits | Yes | We evaluate our work on both ETH3D (Schops et al. 2017) and Tanks & Temples (TNT) (Knapitsch et al. 2017) datasets and upload our results to their websites for reference. ... Our method achieves the highest F1 scores and completeness on both training and testing datasets, validating its excellent effectiveness. |
| Hardware Specification | Yes | Our method is implemented on a machine with an Intel(R) Xeon(R) Silver 4210 CPU and eight NVIDIA Ge Force RTX 3090 GPUs. |
| Software Dependencies | No | The paper does not specify any software dependencies with version numbers (e.g., Python, PyTorch, CUDA versions). |
| Experiment Setup | Yes | Concerning parameter setting, {η, σ, γ, κ, δ, ε, α, β, µ} = {3 102, 0.5, 1.2, 0.7, 0.8, 2, 1, 4, 3}. Our method is implemented on a machine with an Intel(R) Xeon(R) Silver 4210 CPU and eight NVIDIA Ge Force RTX 3090 GPUs. We take APD-MVS (Wang et al. 2023) as our baseline. Experiments are performed on original images in both ETH3D and TNT datasets. In cost calculation, we adopt the matching strategy of every other row and column. |