PDF: Point Diffusion Implicit Function for Large-scale Scene Neural Representation

Authors: Yuhan Ding, Fukun Yin, Jiayuan Fan, Hui Li, Xin Chen, Wen Liu, Chongshan Lu, Gang Yu, Tao Chen

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

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments have demonstrated the effectiveness of our method for large-scale scene novel view synthesis, which outperforms relevant state-of-the-art baselines.
Researcher Affiliation Collaboration 1 School of Information Science and Technology, Fudan University, China 2 Academy for Engineering and Technology, Fudan University, China 3 Tencent PCG, Shanghai, China
Pseudocode No The paper describes methods and processes in text but does not include structured pseudocode or algorithm blocks.
Open Source Code No Our code and models will be available.
Open Datasets Yes We use two outdoor large-scale scene datasets, OMMO [15] and Blended MVS [35], to evaluate our model.
Dataset Splits No The paper mentions 'training views' and 'training data' but does not specify explicit percentages or sample counts for training, validation, and test dataset splits.
Hardware Specification Yes train on 4 A100 GPUs for around one day" and "20 hours on a single A100 GPU
Software Dependencies No The paper mentions software like COLMAP and Adam optimizer but does not provide specific version numbers for any software dependencies.
Experiment Setup Yes For point super-resolution diffusion, we set T = 1000, β0 = 10 4, βT = 0.01 and linearly interpolate other β s for all experiments. We use Adam optimizer with learning rate 2 10 4 and train on 4 A100 GPUs for around one day. We train this stage using Adam optimizer with an initial learning rate 5 10 4 for 2 106 iterations about 20 hours on a single A100 GPU.