DC4GS: Directional Consistency-Driven Adaptive Density Control for 3D Gaussian Splatting (NeurIPS 2025)
_{Official Implementation}

This repository contains the official dateset and code in the following paper:

DC4GS: Directional Consistency-Driven Adaptive Density Control for 3D Gaussian Splatting

Moonsoo Jeong¹, Dongbeen Kim¹, Minseong Kim¹, Sungkil Lee^1,*

¹Sungkyunkwan University

^*Corresponding author

Conference on Advances in Neural Information Processing Systems (NeurIPS) 2025

We present a Directional Consistency (DC)-driven Adaptive Density Control (ADC) for 3D Gaussian Splatting (DC4GS). Whereas the conventional ADC bases its primitive splitting on the magnitudes of positional gradients, we further incorporate the DC of the gradients into ADC, and realize it through the angular coherence of the gradients. Our DC better captures local structural complexities in ADC, avoiding redundant splitting. When splitting is required, we again utilize the DC to define optimal split positions so that sub-primitives best align with the local structures than the conventional random placement. As a consequence, our DC4GS greatly reduces the number of primitives (up to 30% in our experiments) than the existing ADC, and also enhances reconstruction fidelity greatly.

Use the provided environment.yml file to create and install the conda environment:

conda env create -f environment.yml
conda activate DC4GS

Replace items in braces {} with your actual values when running the commands.

OMP_NUM_THREADS=4 \
CUDA_VISIBLE_DEVICES={gpu_idx} \
python train-dcc.py \
  -s {dataset_dir} \
  -m {output_dir} \
  -i images or images_{scale} \
  --eval \
  --without_bound

• {gpu_idx}: GPU index to use
• {dataset_dir}: Path to your dataset
• {output_dir}: Directory to save checkpoints and logs
• images or images_{scale}: Folder of original images or scaled images

OMP_NUM_THREADS=4 \
CUDA_VISIBLE_DEVICES={gpu_idx} \
python metrics.py \
  -m {output_dir} \
  --skip_train

If you find this work useful, please cite:

@inproceedings{jeong25dc4gs,
    title       = {{DC4GS: Directional Consistency-Driven Adaptive Density Control for 3D Gaussian Splatting}},
    author      = {Jeong, Moonsoo and Kim, Dongbeen and Kim, Minseong and Lee, Sungkil},
    booktitle   = {Advances in Neural Information Processing Systems (NeurIPS)},
    year        = {2025}
}

This repository is based on the 3DGS and AbsGS. Thanks for their awesome work.