Effective Rank Analysis and Regularization for Enhanced 3D Gaussian Splatting

Authors: Junha Hyung, Susung Hong, Sungwon Hwang, Jaeseong Lee, Jaegul Choo, Jin-Hwa Kim

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

Reproducibility Variable Result LLM Response
Research Type Experimental We evaluate the effective rank regularization, comparing its performance as an add-on to baseline models. Additionally, we analyze the contributions of different components of the method. ... Table 1 presents the quantitative results of geometry reconstruction on the DTU dataset. We report the Chamfer distance for each scene, along with the mean Chamfer
Researcher Affiliation Collaboration Junha Hyung1 Susung Hong4 Sungwon Hwang1 Jaeseong Lee1 Jaegul Choo1 Jin-Hwa Kim2,3 1KAIST 2NAVER AI Lab 3SNU AIIS 4Korea University
Pseudocode No The paper does not contain a pseudocode block or a clearly labeled algorithm block.
Open Source Code Yes The project page is available at https://junhahyung.github.io/erankgs.github.io/.
Open Datasets Yes We evaluate our model on the DTU [14] and Mip-Ne RF360 [2] datasets.
Dataset Splits No For novel view synthesis, the images are split into training and test sets, while the entire set of images is used for geometry reconstruction.
Hardware Specification Yes All experiments are conducted on a Tesla V100 GPU.
Software Dependencies No The paper does not provide specific version numbers for software dependencies used in the experiments. It only mentions the NSML platform, but no specific libraries or their versions.
Experiment Setup Yes The regularization hyperparameter λerank = 0.01 is used for all training.