DiffSQL: Leveraging Diffusion Model for Zero-Shot Self-Supervised Monocular Depth Estimation
Authors: Heyuan Zheng, Yunji Liang, Lei Liu, Zhiwen Yu
IJCAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results on the KITTI dataset show that Diff SQL outperforms SQLdepth by 1.03% in terms of Abs Rel and 2.79% in terms of Sq Rel. Furthermore, our experiments demonstrate that Diff SQL is superior in zero-shot generalization. |
| Researcher Affiliation | Academia | Heyuan Zheng , Yunji Liang , Lei Liu and Zhiwen Yu School of Computer Science, Northwestern Polytechnical University EMAIL, EMAIL, EMAIL, EMAIL |
| Pseudocode | No | The paper describes the methodology using textual explanations and mathematical formulations (Eq. 1-15) but does not include any explicit pseudocode blocks or algorithm listings. |
| Open Source Code | No | The paper does not provide any explicit statement about releasing open-source code or a link to a code repository for the described methodology. |
| Open Datasets | Yes | Experimental results on the KITTI dataset show that Diff SQL outperforms SQLdepth by 1.03% in terms of Abs Rel and 2.79% in terms of Sq Rel. Furthermore, our experiments demonstrate that Diff SQL is superior in zero-shot generalization. The Make3D dataset [Saxena et al., 2008] validates Diff SQL s cross-dataset generalization capability by employing zero-shot evaluation with KITTI-pre-trained weights. |
| Dataset Splits | Yes | Adopting Eigen s benchmark split [Eigen et al., 2014], we utilize 39,810 monocular triplets for training and 4,424 for validation. The test set contains raw Li DAR measurements (697 frames) and sparsity-corrected ground truth [Uhrig et al., 2017] (652 frames). |
| Hardware Specification | No | The paper does not provide specific details about the hardware (e.g., GPU models, CPU types) used for running the experiments. |
| Software Dependencies | No | The paper does not provide specific software dependency details, such as library names with version numbers (e.g., Python, PyTorch, TensorFlow versions), that would be needed for replication. |
| Experiment Setup | No | The paper describes the loss functions used (photometric error, smoothness loss, auto-masking strategy) and some general training methodologies. However, it does not explicitly provide concrete hyperparameter values such as learning rate, batch size, or number of epochs, or specific optimizer settings in the main text. |