Implicit-PDF: Non-Parametric Representation of Probability Distributions on the Rotation Manifold
Authors: Kieran A Murphy, Carlos Esteves, Varun Jampani, Srikumar Ramalingam, Ameesh Makadia
ICML 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Our IPDF method is extensively evaluated on the new SYMSOL dataset as well as traditional pose estimation benchmarks. Nonetheless, our implicit model is highly expressive to handle complex distributions over 3D poses, while still obtaining accurate pose estimation on standard non-ambiguous environments, achieving state-of-the-art performance on Pascal3D+ and Model Net10-SO(3) benchmarks. |
| Researcher Affiliation | Industry | Kieran Murphy * 1 Carlos Esteves * 1 Varun Jampani 1 Srikumar Ramalingam 1 Ameesh Makadia 1 1Google Research, New York, NY, USA. Correspondence to: <implicitpdf@gmail.com>. |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | Code, data, and visualizations may be found at implicit-pdf.github.io. |
| Open Datasets | Yes | Code, data, and visualizations may be found at implicit-pdf.github.io. ... Pascal3D+ (Xiang et al., 2014), Object Net3D (Xiang et al., 2016), Model Net10-SO(3) (Liao et al., 2019), Model Net10 (Wu et al., 2015), T-LESS (Hodaˇn et al., 2017). |
| Dataset Splits | No | The paper mentions 'training' and 'test set' but does not explicitly provide details on train/validation/test splits, such as percentages or sample counts for reproduction. |
| Hardware Specification | No | No specific hardware details (e.g., GPU/CPU models, memory) used for experiments are mentioned in the paper. |
| Software Dependencies | No | The paper mentions using a 'pre-trained Res Net' but does not provide specific version numbers for any software dependencies or libraries. |
| Experiment Setup | No | The paper discusses some model architecture and training principles, but does not provide specific experimental setup details such as concrete hyperparameter values (learning rate, batch size, epochs, optimizer settings) in the main text. |