Error-aware Sampling in Adaptive Shells for Neural Surface Reconstruction
Authors: Qi Wang, Yuchi Huo, Qi Ye, Rui Wang, Hujun Bao
IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive results in various scenes demonstrate the superiority of our sampling technique, including significantly reducing sample counts and training time, even improving the reconstruction quality. The experiments demonstrate the superiority of our sampling technique, including significantly reducing sample count and improving reconstruction quality within the same training time. |
| Researcher Affiliation | Academia | Qi Wang1 , Yuchi Huo1,2, , Qi Ye1 , Rui Wang1 and Hujun Bao1 1State Key Lab of CAD&CG, Zhejiang University 2Zhejiang Lab |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | The code is available at https://github.com/erernan/ESampling. |
| Open Datasets | Yes | We use 6 scenes from the DTU dataset [Jensen et al., 2014]. |
| Dataset Splits | No | The paper does not explicitly provide training/validation/test dataset splits. It describes experimental setup parameters like sampling points and batch size but not data partitioning for validation. |
| Hardware Specification | Yes | All experiments are deployed on a single Tesla-V100s GPU. |
| Software Dependencies | No | The paper mentions 'SDFStudio [Yu et al., 2022a] framework' but does not provide specific version numbers for any software components or libraries. |
| Experiment Setup | Yes | The radiance network consists of 4 hidden layers with a hidden size of 256 while the geometry network consists of 8 hidden layers with the same hidden size. We also train the network with hash encoding [M uller et al., 2022], in which the geometry and radiance networks are all reduced to 2 hidden layers with a hidden size of 256. We sample 64 points during the double-clipping stage (32 for a single pass), and 16 points during the linear interpolation stage. As for the final volume rendering stage, 32 samples combining uniform samples and importance samples are taken into account. The batch size of all experiments is 1, and the number of sampling rays in each batch is 1024. |