---
library_name: onnxruntime
license: bsd-3-clause
tags:
  - foundation
  - amd
  - rocm
  - stereo-depth-estimation
pipeline_tag: depth-estimation
---

![](https://huggingface.co/AMD-PAVS-AI/raft-stereo/resolve/main/RAFT-Stereo.png)

# RAFT-Stereo: Optimized for AMD ROCm

RAFT-Stereo ([Princeton VL](https://github.com/princeton-vl/RAFT-Stereo)) estimates dense per-pixel disparity from a rectified stereo image pair using multilevel recurrent field transforms. This repository packages evaluation/inference for stereo disparity estimation using ONNX Runtime, exported and validated for **AMD ROCm** so it runs efficiently on AMD GPUs and CPUs, as well as AMD Ryzen AI NPUs.

This is based on the implementation of RAFT-Stereo found [here](https://github.com/princeton-vl/RAFT-Stereo).
This repository contains configurations and scripts optimized for **AMD® ROCm™** platforms. You can use the [RAFT-Stereo AMD scripts](https://github.com/AMD-PAVS/physical_ai_sdk/blob/main/models/RAFT-Stereo) to reproduce results or export with custom configurations.

---

## Task Overview

**Task:** Stereo disparity estimation

**Dataset:** Middlebury MiddEval3 (F/H/Q splits), ETH3D two-view training set, KITTI 2012/2015 stereo, and FlyingThings3D (SceneFlow)

**Output metrics:** EPE (End-Point Error, px), D1-error (%)

> **ONNX Runtime note:** CPU runs FP32 only. GPU supports FP32/FP16/INT8 individually or all at once via the MIGraphX execution provider. NPU has no precision knob (Vitis AI compiles the graph as-is); instead it offers a **smoke** graph (few unrolled GRU iterations, compiles in minutes) vs. the **full** graph (32 iterations, Vitis AI compilation can take hours).

---

## AMD ROCm Optimization

This model export has been adapted and validated for **AMD Instinct™ / Radeon™ GPUs** running **ROCm**, as well as AMD CPUs and AMD Ryzen AI NPUs. Key points:

- Exported/tested with ROCm `7.x` for the MIGraphX execution provider.
- Validated backends: **ONNX Runtime CPU EP**, **ONNX Runtime MIGraphX EP** (ROCm GPU), and **Vitis AI EP** (Ryzen AI NPU).
- No code changes required versus the upstream RAFT-Stereo implementation — only environment/runtime configuration differs.
- CPU fallback path supported for environments without a ROCm-capable GPU.

| Runtime | Precision | Backend | Hardware | Notes |
|---|---|---|---|---|
| ONNX Runtime | FP32 | CPU EP | AMD CPU | Only precision supported on CPU |
| ONNX Runtime | FP32 / FP16 / INT8 | MIGraphX EP | AMD GPU (e.g. gfx11xx) | Precisions run individually or all at once |
| ONNX Runtime | N/A (compiled as-is) | Vitis AI EP | AMD Ryzen AI NPU | Smoke graph (fast compile) vs. full graph (32 iterations, long compile) |

---

## Getting Started

For setup instructions, evaluation scripts, and custom configuration options, see the [RAFT-Stereo on GitHub](https://github.com/AMD-PAVS/physical_ai_sdk/blob/main/models/RAFT-Stereo).

---

## Model Details

**Model Type:** Stereo disparity estimation (multilevel recurrent field transform network)

**Model Stats:**
- No `MODEL_SIZE` variants — single architecture
- Static ONNX export by default: `[1, 3, 384, 512]` input resolution (configurable via `--height`/`--width`, or `--dynamic` for variable axes)
- Precision tested: FP32 (CPU); FP32, FP16, INT8 (GPU); Vitis AI-compiled (NPU)

---

## Accuracy Pipeline

Accuracy evaluation is not yet implemented for this model.

---

## Dig Deeper

Want to explore the full evaluation scripts, config options, and other AMD-optimized model examples?

📂 **[View the full project on GitHub](https://github.com/AMD-PAVS/physical_ai_sdk/blob/main/models/RAFT-Stereo)**

The GitHub repository includes:
- Setup and prerequisites for ROCm environments
- Scripts for the supported runners
- Additional model variants and datasets
- Benchmarking and reproduction instructions