Grounding Acoustic Echoes in Single View Geometry Estimation
Authors: Muhammad Wajahat Hussain, Javier Civera, Luis Montano
AAAI 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Our audio-visual 3D geometry descriptor improves over the state of the art in passive perception models as we show in our experiments. |
| Researcher Affiliation | Academia | Wajahat Hussain, Javier Civera, Luis Montano Robotics, Perception and Real Time Group, I3A University of Zaragoza, Spain {hussain, jcivera, montano}@unizar.es |
| Pseudocode | Yes | Algorithm 1 Acoustic Penalty Algorithm |
| Open Source Code | No | The paper mentions using the 'publicly available GSound system', but does not state that the code for their own methodology is open-source or provided. |
| Open Datasets | No | The paper states, 'In order to generate the test data, we used the publicly available GSound system (Schissler and Manocha 2011).' This refers to the system used for data generation, not that the specific dataset generated for their experiments is publicly available or provides access information. |
| Dataset Splits | No | The paper mentions 'Our test set contains 17 scene renderings' but does not provide specific details on training, validation, or test dataset splits needed for reproduction. |
| Hardware Specification | No | The paper does not provide specific details about the hardware (e.g., CPU, GPU models, memory) used to run its experiments. |
| Software Dependencies | No | The paper mentions using the 'publicly available GSound system', but does not provide specific version numbers for any software dependencies, libraries, or frameworks used for their implementation. |
| Experiment Setup | Yes | The value of the acoustic weight is set αe = 10. Figure 3 shows the insensitivity of geometric labelling error to this parameter. Notice the logarithmic scale in the αe axis and the wide range where the fusion improves over the image-only understanding. (...) Starting with the intial room orientation R, we generate multiple particles for room orientation within 5 along each axis. |