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 [1].
Equivariant Neural Rendering
Authors: Emilien Dupont, Miguel Bautista Martin, Alex Colburn, Aditya Sankar, Josh Susskind, Qi Shan
ICML 2020 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We perform experiments on Shape Net benchmarks (Chang et al., 2015) as well as on two new datasets designed to challenge the model on more complex scenes. |
| Researcher Affiliation | Collaboration | 1University of Oxford, UK 2Apple Inc, USA. Correspondence to: Emilien Dupont <EMAIL>, Qi Shan <EMAIL>. |
| Pseudocode | No | The paper describes the model architecture and training process in text and diagrams (e.g., Figure 4, Figure 5) but does not include structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | The code and datasets are available at https://github.com/ apple/ml-equivariant-neural-rendering. |
| Open Datasets | Yes | We perform experiments on Shape Net benchmarks (Chang et al., 2015) as well as on two new datasets designed to challenge the model on more complex scenes... The code and datasets are available at https://github.com/ apple/ml-equivariant-neural-rendering. |
| Dataset Splits | Yes | We evaluate our model on the Shape Net chairs class by following the experimental setup given in Sitzmann et al., using the same train/validation/test splits. |
| Hardware Specification | Yes | At inference time, SRNs require solving an optimization problem in order to fit a scene to the model. As such, inferring a scene representation from a single input image (on a Tesla V100 GPU) takes 2 minutes with SRNs but only 22ms for our model (three orders of magnitude faster). |
| Software Dependencies | No | The paper mentions using "Pytorch and Tensorflow" frameworks and the "Mitsuba renderer (Jakob, 2010)" but does not specify version numbers for these software dependencies. |
| Experiment Setup | Yes | For all experiments, the images are of size 128 128 and the scene representations are of size 64 32 32 32. For both the 2D and 3D parts of the network we use residual layers for convolutions that preserve the dimension of the input and strided convolutions for downsampling layers. We use the Leaky Re LU nonlinearity (Maas et al.) and Group Norm (Wu & He, 2018) for normalization. |