# SHARP 3D Gaussian Splat Generator

> Use this tool when you need to generate 3D Gaussian Splat representations from single photographs for applications like virtual reality, game development, and architectural visualization. It solves problems related to parallax effects and 3D scene visualization, taking a single image as input and producing a 3D representation as output. This tool is ideal for use cases requiring small-range view synthesis, such as creating immersive experiences or simulating real-world environments.

Canonical page: https://skillsregistry.net/skills/neosun100-sharp  
JSON: https://api.skillsregistry.net/v1/skills/neosun100-sharp

## Description

Wraps Apple's SHARP monocular view synthesis model to generate 3D Gaussian Splat representations from single photographs. Runs as a Docker container with GPU acceleration, providing tools for image prediction, batch processing, GPU memory management, and format conversion. Generates small-range view synthesis suitable for parallax effects and 3D scene visualization in virtual reality, game development, and architectural applications.

## Trust

- **Trust score (0–1):** 0.77
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** cloud-infra
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/neosun100-sharp)
- **Repository:** <https://github.com/neosun100/sharp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "neosun100-sharp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/neosun100-sharp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/neosun100-sharp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt