Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
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.
Gaussian Process Priors for View-Aware Inference
Authors: Yuxin Hou, Ari Heljakka, Arno Solin7762-7770
AAAI 2021 | Venue PDF | LLM Run Details | Input Tokens: 17,092 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 5,091 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In the experiments, we show examples of real-world applications of the view kernel in probabilistic view synthesis. Our quantitative experiments showed that the view prior can encode authentic movement and provide a soft-prior for view synthesis. |
| Researcher Affiliation | Collaboration | Yuxin Hou1, , Ari Heljakka1,2,*, Arno Solin1 1Aalto University, Espoo, Finland, 2Gen Mind Ltd., Finland |
| Pseudocode | No | No pseudocode or algorithm blocks were found in the paper. |
| Open Source Code | Yes | Code and material related to this paper is available at https: //aaltoml.github.io/view-aware-inference. |
| Open Datasets | Yes | We carried out an experiment with Shape Net (Chang et al. 2015) 3D chair models at 128 128 resolution. |
| Dataset Splits | Yes | We randomly selected 80% images for training (81,312 images), 10% for validation (10,164 images) and 10% for testing (10,164 images). |
| Hardware Specification | No | The paper mentions 'computational resources provided by the Aalto Science-IT project' but does not specify any particular hardware details such as GPU models, CPU types, or memory amounts used for the experiments. |
| Software Dependencies | No | The paper mentions software libraries like GPflow (Matthews et al. 2017) and GPy Torch (Gardner et al. 2018), and Style GAN (Karras, Laine, and Aila 2019), but does not provide specific version numbers for these or other software dependencies. |
| Experiment Setup | Yes | The values for the three hyperparameters were chosen to σ2 = 0.1, ℓ= 1.098, and σ2 n = 0.0001 (pre-trained on an independent task w.r.t. marginal likelihood). |