diff --git a/Dockerfile b/Dockerfile
new file mode 100644
index 0000000..e5efed0
--- /dev/null
+++ b/Dockerfile
@@ -0,0 +1,21 @@
+FROM python:3.11-slim
+
+ENV PYTHONUNBUFFERED=1
+WORKDIR /app
+
+# Install minimal build dependencies for some Python packages
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends gcc git && \
+    rm -rf /var/lib/apt/lists/*
+
+# Copy dependency files first to leverage Docker layer caching
+COPY requirements.txt requirements.in pyproject.toml /app/
+
+RUN pip install --upgrade pip setuptools wheel && \
+    if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+
+# Copy project
+COPY . /app
+
+# Default command prints the CLI help. Users can override with other commands.
+CMD ["python", "-m", "sharp.cli.predict", "--help"]
diff --git a/README.md b/README.md
index 5955753..e44789b 100644
--- a/README.md
+++ b/README.md
@@ -93,3 +93,35 @@ Our codebase is built using multiple opensource contributions, please see [ACKNO
 
 Please check out the repository [LICENSE](LICENSE) before using the provided code and
 [LICENSE_MODEL](LICENSE_MODEL) for the released models.
+
+## Docker
+
+Build the image locally (run from the repository root):
+
+```bash
+docker build -t ml-sharp .
+```
+
+Run the CLI inside the container. Mount the repository and the `data/` directory so outputs persist locally:
+
+```bash
+docker run --rm -it \
+  -v "$PWD":/app \
+  -v "$PWD/data":/app/data \
+  ml-sharp \
+  python -m sharp.cli.predict --help
+```
+
+Example: predict using the mounted `data/` input and write outputs to `data/output`:
+
+```bash
+docker run --rm -it \
+  -v "$PWD":/app \
+  -v "$PWD/data":/app/data \
+  ml-sharp \
+  python -m sharp.cli.predict -i data/input_images -o data/output
+```
+
+Notes:
+- If you need GPU support, use a GPU-enabled base image and the appropriate CUDA toolchain, or prefer running natively with CUDA and PyTorch.
+- The default image is a minimal CPU image intended for convenience and reproduction on typical development machines.