Superpoint Transformer for 3D Scene Instance Segmentation

Authors: Jiahao Sun, Chunmei Qing, Junpeng Tan, Xiangmin Xu

AAAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on Scan Netv2 and S3DIS benchmarks verify that our method is concise yet efficient.
Researcher Affiliation Academia 1 School of Electronic and Information Engineering, South China University of Technology, China 2 School of Future Technology, South China University of Technology, China
Pseudocode No The paper describes the model architecture and process in detail but does not include formal pseudocode blocks or algorithms.
Open Source Code Yes Code is available at https://github.com/sunjiahao1999/SPFormer.
Open Datasets Yes Experiments are conducted on Scan Netv2 (Dai et al. 2017) and S3DIS (Armeni et al. 2016) datasets.
Dataset Splits Yes Scan Netv2 has a total of 1613 indoor scenes, of which 1201 are used for training, 312 for validation, and 100 for testing.
Hardware Specification Yes The runtime is measured on the same RTX 3090 GPU.
Software Dependencies Yes For a fair comparison, the SSC and SC layers in all the above methods are implemented by spconv v2.1.
Experiment Setup Yes In our experiments, we set λcls = 0.5, λmask = 1. Empirically, we set τ to 0.5. Empirically, we set βcls = βs = 0.5, βmask = 1. Table 7 presents the selection of the number of query vectors and transformer decoder layers.