ComfyUI Node
Gaussian Merge to Target
A ComfyUI node in viewer with 6 inputs and 1 output.
Gaussian Merge to Target
- ply_path
◄ply_path—►
◄target_count200000►
◄output_filenamemerged►
◄opacity_threshold0.10►
◄k16►
◄backendtorch_gpu►
Categoryviewer
Inputs (6)
| Name | Type | Default | Description |
|---|---|---|---|
| ply_path | STRING | Path to a Gaussian Splatting PLY file | |
| target_count | INT | 2000001000–10000000 | Approximate output Gaussian count. NanoGS works in ratio terms - target / input_count is passed as `--ratio`. If target >= input count, the input is passed through unchanged. |
| output_filename | STRING | merged | Basename for the output PLY (no extension). |
| opacity_threshold | FLOAT | 0.100–1 | Splats with opacity below min(threshold, median(opacity)) are pruned before merging. |
| k | INT | 164–64 | k nearest neighbors per splat that the merge graph considers as candidate pairs. Higher k -> slightly better quality (more options for the greedy selector) but more RAM + slower (O(N*k) edges). 16 is the upstream sweet spot. 8 = fast draft. 24-32 helps on specular-heavy scenes; 32+ rarely pays off. |
| backend | COMBO | torch_gpu | torch_gpu - MPMM on GPU via PyTorch (CUDA / ROCm / MPS, falls back to CPU torch). ~5-10x faster than nanogs_cpu. nanogs_cpu - original NanoGS NumPy/SciPy backend. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| ply_path | STRING | — |