Bidirectional Recurrent Convolutional Networks for Multi-Frame Super-Resolution
Authors: Yan Huang, Wei Wang, Liang Wang
NeurIPS 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | To verify the effectiveness, we apply the proposed model to the task of video SR, and present both quantitative and qualitative results as follows. |
| Researcher Affiliation | Academia | 1Center for Research on Intelligent Perception and Computing National Laboratory of Pattern Recognition 2Center for Excellence in Brain Science and Intelligence Technology Institute of Automation, Chinese Academy of Sciences |
| Pseudocode | No | The paper describes the network architecture and mathematical formulations (Equations 1, 2, 3), but it does not include any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper states: 'The publicly available codes of compared methods are all in MATLAB while SR-CNN and ours are in Python.' However, it does not provide any specific link or explicit statement about the availability of their own source code. |
| Open Datasets | Yes | We use 25 YUV format video sequences2 as our training set, which have been widely used in many video SR methods [13, 16, 21]. (...) 2http://www.codersvoice.com/a/webbase/video/08/152014/130.html. We test our model on a variety of challenging videos, including Dancing, Flag, Fan, Treadmill and Turbine [19], |
| Dataset Splits | No | The paper describes how training volumes are generated ('cropping multiple overlapped volumes from training videos and then regarding each volume as a training sample'), but it does not provide specific details on training/validation/test dataset splits such as percentages, sample counts, or a dedicated validation set. |
| Hardware Specification | Yes | all the methods are implemented on the same machine (Intel CPU 3.10 GHz and 32 GB memory) |
| Software Dependencies | No | The paper mentions that 'SR-CNN and ours are in Python' and 'publicly available codes of compared methods are all in MATLAB', but it does not specify any version numbers for Python, MATLAB, or any required libraries or software packages. |
| Experiment Setup | Yes | Some important parameters of our network are illustrated as follows: fv1=9, fv3=5, n1=64, n2=32 and c=14. |