Efficient Inference of Continuous Markov Random Fields with Polynomial Potentials
Authors: Shenlong Wang, Alex Schwing, Raquel Urtasun
NeurIPS 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We demonstrate the effectiveness of our approach in the context of 3D reconstruction, shape from shading and image denoising, and show that our method significantly outperforms existing techniques in terms of efficiency as well as quality of the retrieved solution. |
| Researcher Affiliation | Academia | Shenlong Wang University of Toronto slwang@cs.toronto.edu Alexander G. Schwing University of Toronto aschwing@cs.toronto.edu Raquel Urtasun University of Toronto urtasun@cs.toronto.edu |
| Pseudocode | Yes | Algorithm 1 CCCP Inference on Continuous MRFs with Polynomial Potentials |
| Open Source Code | No | The paper does not provide a statement about releasing the source code for the described methodology or a direct link to a code repository. |
| Open Datasets | No | The paper mentions datasets like '100 randomly generated 3x3 meshes of [20]', '9x9 Cardboard sequence [20]', 'Vase, Penny and Mozart datasets', and 'BM3D benchmark 1' but does not provide specific links, DOIs, or formal citations (with author names and year) for directly accessing these datasets. The reference [20] is a method paper, not a dataset source. |
| Dataset Splits | No | The paper describes datasets used (e.g., '100 randomly generated 3x3 meshes', 'Cardboard sequence', 'Vase, Penny and Mozart datasets', 'BM3D benchmark') but does not specify exact training, validation, or test split percentages, sample counts, or mention cross-validation setup. |
| Hardware Specification | No | The paper does not mention any specific hardware components such as GPU models, CPU models, or detailed computer specifications used for running the experiments. |
| Software Dependencies | Yes | SOSTOOLS version 3.00 sum of squares optimization toolbox for matlab. |
| Experiment Setup | Yes | For L-BFGS and our method, we use a flat mesh as initialization with two rotation angles (0, 0, 0) and (π/4, 0, 0). The convergence criteria is an energy decrease of less than 10 5 or a maximum of 500 iterations is reached. |