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 Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Depth-Supervised Fusion Network for Seamless-Free Image Stitching
Authors: Zhiying Jiang, Ruhao Yan, Zengxi Zhang, Bowei Zhang, Jinyuan Liu
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments demonstrate the superior performance of the proposed method against the existing methods. Code is available at https://github.com/DLUT-YRH/DSFN. |
| Researcher Affiliation | Academia | 1 College of Information Science and Technology, Dalian Maritime University 2 School of Software Technology, Dalian University of Technology |
| Pseudocode | No | The paper describes methods and processes using equations and descriptive text, but no explicit pseudocode or algorithm blocks are present. |
| Open Source Code | Yes | Code is available at https://github.com/DLUT-YRH/DSFN. |
| Open Datasets | Yes | The UDIS-D training set [32] is employed as the training data. To enhance the reliability of the experimental results, we evaluate the model on the UDIS-D testing set and further validate it using real-world data from the IVSD dataset [40]. |
| Dataset Splits | No | The UDIS-D training set [32] is employed as the training data. To enhance the reliability of the experimental results, we evaluate the model on the UDIS-D testing set and further validate it using real-world data from the IVSD dataset [40]. The test sets of UDIS-D are categorized into three levels based on their complexity |
| Hardware Specification | Yes | Our method is implemented using the PyTorch framework and executed on an NVIDIA RTX 3090 GPU. |
| Software Dependencies | No | Our method is implemented using the PyTorch framework and executed on an NVIDIA RTX 3090 GPU. |
| Experiment Setup | Yes | For training both the depth-aware transformation estimation and soft-seam based multi-view fusion models, we employ the Adam optimizer [47], and the learning rate decays exponentially, with an initial value of 10^-4. The transformation model is trained for 100 epochs, with the hyperparameters λ, γ, and η set to 3, 3, and 1, respectively. The values of λ', γ', η' are identical to those of λ, γ, and η. µ, ζ, ξ are set to 10, 10 and 0.3. For the multi-view fusion model, we initially train the model for 50 epochs on the training set, with the hyperparameters ρ, τ, ι, σ set to 10000, 1000, 1000, 10. |