PointSplat

PointSplat: Compact Gaussian Splatting via Human-Centric Prediction

ECCV 2026

Yujie Guo1, Yudong Jin1, Lingteng Qiu3, Zehong Shen1, Zhen Xu1, Jing Zhang2, Xianchao Shen2, Hujun Bao1, Sida Peng1, Xiaowei Zhou1†

1Zhejiang University    2ByteDance    3CUHK, Shenzhen

†Corresponding author

⚙️ Installation

Create a conda environment and install the dependencies:

conda create -n pointsplat python=3.10 -y
conda activate pointsplat
pip install -r requirements.txt

📦 Checkpoint

Download the pretrained checkpoint with:

hf download Yujie0012/PointSplat_pretrained_weights pointsplat_mixed.pt \
  --local-dir pretrained

You can also download the checkpoint manually. Either way, the final layout should be:

pretrained/
└── pointsplat_mixed.pt

🚀 Inference

Inference on DNA-Rendering

Step 1: Download example data.

Download the DNA-Rendering example package from PointSplat_example_data with:

hf download Yujie0012/PointSplat_example_data DNA_Rendering_example.zip \
  --repo-type dataset \
  --local-dir datasets
unzip datasets/DNA_Rendering_example.zip -d datasets

Expected data layout:

datasets/DNA_Rendering_example/
├── validation_index.json
├── scenes/
│   └── /
│       ├── transforms.json
│       └── images/
│           └── /
│               └── 000030.webp
└── masks/
    └── /
        └── fmasks/
            └── /
                └── 000030.png

[!TIP] To test the model on more DNA-Rendering scenes, follow the processed DNA-Rendering dataset instructions in Diffuman4D.

Step 2: Run the inference script.

CUDA_VISIBLE_DEVICES=0 python -m src.main \
  +experiment=pointsplat_renbody \
  output_dir=experiments/eval_pointsplat_dna_rendering \
  dataset.roots='[datasets/DNA_Rendering_example]' \
  checkpointing.pretrained_