Toward Dynamic Non-Line-of-Sight Imaging with Mamba Enforced Temporal Consistency

Authors: Yue Li, Yi Sun, Shida Sun, Juntian Ye, Yueyi Zhang, Feihu Xu, Zhiwei Xiong

NeurIPS 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments showcase the superior performance of our method on both synthetic data and realworld data captured by different imaging setups.
Researcher Affiliation Academia University of Science and Technology of China {yueli65,sunyi2017,jt141884,sdsun}@mail.ustc.edu.cn {zhyuey,feihuxu,zwxiong}@ustc.edu.cn
Pseudocode No The paper describes the method procedurally and with architectural diagrams (e.g., Figure 3, Figure 4) but does not include explicit pseudocode or algorithm blocks.
Open Source Code Yes The code and data are available at https://github.com/Depth2World/Dynamic_NLOS.
Open Datasets Yes The code and data are available at https://github.com/Depth2World/Dynamic_NLOS. The dataset is publicly available to propel research in dynamic imaging within this field.
Dataset Splits No We utilize 150 sequences for training and 17 sequences for synthetic testing. Besides, we utilize 4 sequences for real-world evaluation. The paper specifies training and testing sets but does not explicitly mention a separate validation set split.
Hardware Specification Yes All the experiments are conducted on the NVIDIA A100 GPUs, with a batch size of 4.
Software Dependencies No Our method is implemented using Py Torch, trained on the synthetic data, and then directly tested on the real-world data. The paper mentions PyTorch but does not specify a version number or list other software dependencies with version numbers.
Experiment Setup Yes During training, we employ the Adam W [47] as the optimizer with a learning rate of 10^-4 and a weight decay of 0.95. ... All the experiments are conducted on the NVIDIA A100 GPUs, with a batch size of 4. ... The hyper-parameter β and γ are set to 1 and 10^-5. α1, α2, α3 are set to 0.5, 1, and 0.1, respectively.