README.md

metadata

library_name: onnxruntime
tags:
  - onnx
  - sharp
  - view-synthesis
  - 3d-gaussian-splatting
base_model: apple/Sharp

SHARP (NDC) — ONNX exports (FP32 + INT8)

This repo contains ONNX exports of Apple’s SHARP model predictor that outputs NDC-space 3D Gaussians.

What’s included

• FP32 (opset18, external data): onnx/fp32/sharp_ndc_opset18.onnx (+ .onnx.data)
• INT8 Dynamic (QDQ): onnx/int8_dynamic/sharp_ndc_opset18_int8_dynamic.onnx (+ optional .onnx.data)

External data note: if a model has a .onnx.data file, it must stay in the same folder as its .onnx.

I/O contract (all variants)

Inputs:

• image_resized_pt: float32 [1, 3, 1536, 1536] (NCHW, RGB, normalized to [0,1], resized bilinear with align_corners=True)
• disparity_factor: float32 [1] computed as f_px / width_original

Outputs (float32):

• mean_vectors: [1, 1179648, 3]
• singular_values: [1, 1179648, 3]
• quaternions: [1, 1179648, 4]
• colors: [1, 1179648, 3]
• opacities: [1, 1179648]

Notes

• These ONNX models output NDC Gaussians only. Converting to metric space / writing .ply can be done outside ONNX.
• See metadata/ for manifests and parity metrics.

License

This repository contains model derivatives (ONNX conversions). See LICENSE.