Online 3D Gaussian Splatting Modeling with Novel View Selection

Authors: Byeonggwon Lee, Junkyu Park, Khang Truong Giang, Soohwan Song

IJCAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results demonstrate that our method outperforms state-of-the-art methods, delivering exceptional performance in complex outdoor scenes.
Researcher Affiliation Collaboration 1Department of Computer Science and Artificial Intelligence, Dongguk University, Seoul, Korea 242dot, Seongnam-si, Gyeonggi-do, Korea EMAIL, EMAIL, EMAIL
Pseudocode No The paper describes methods in paragraph text and equations but does not include any clearly labeled pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any explicit statement about releasing source code, nor does it include a link to a code repository.
Open Datasets Yes The proposed method was evaluated using two benchmarks for indoor scenes [Sturm et al., 2012] [Straub et al., 2019]. To highlight its generalization capability, we also extended the evaluation to include challenging outdoor scenarios [Song et al., 2021] [Knapitsch et al., 2017].
Dataset Splits No The paper mentions using datasets for indoor and outdoor scenes and states "following the same experimental setups as other methods" but does not explicitly provide specific training/test/validation split information within the paper.
Hardware Specification Yes All experiments were carried out on a desktop equipped with an AMD Ryzen9 7900X 12core processor and an NVIDIA Ge Force RTX 4090 GPU.
Software Dependencies No The paper mentions "Training and evaluation were performed in Py Torch with CUDA" but does not specify version numbers for PyTorch or CUDA.
Experiment Setup Yes While most hyperparameters follow the original 3DGS setting [Kerbl et al., 2023], we empirically set ̘L1, ̘SSIM, ̘depth and ̘smooth to 0.95, 0.2, 0.2, and 0.1, respectively, for the loss function of Gaussian training.