feat: Add surface generation and media handling

- Implemented surface generation functionality in `surface.py`, including geometry estimation and texture writing.
- Introduced media input handling in `input.py`, supporting image and video frame extraction.
- Added model management for geometry adapters in `models/__init__.py`.
- Created BEN2 and DA3 model inference logic in `ben2.py` and `da3.py`, respectively.
- Developed ONNX model inference utilities for BEN2 and DA3 in `onnx_ben2.py` and `onnx_da3.py`.
- Added support for MoGe-2 model inference in `moge2.py` with necessary ONNX utilities.
- Implemented output handling for depth and surface data in `depth.py` and `surface.py`.
- Created debug output utilities for DA3 and MoGe-2 predictions in `debug_da3.py` and `debug_moge2.py`.
- Enhanced ONNX runtime session management in `onnx_runtime.py`.
- Updated `__init__.py` files to include new modules and functions for better organization.

src/snapform/server/jobs/surface.py

@@ -0,0 +1,75 @@
+from ..geometry import foreground_mesh_mask
+from ..models import geometry_adapter, moge2
+from ..geometry import build_surface
+from ..outputs.surface import (
+    write_normal_texture,
+    write_surface_archive,
+    write_surface_texture,
+)
+from .common import input_frames
+from .foreground import write_optional
+
+
+def run(context, parameters):
+    context.progress(0.02, "Preparing surface input")
+    context.directory.mkdir(parents=True, exist_ok=True)
+    model_manager = context.resource("model_manager")
+    adapter = geometry_adapter(parameters["model"])
+    with input_frames(context, parameters) as images:
+        if len(images) != 1:
+            raise ValueError("Convert to Surface currently supports one image")
+        context.progress(0.12, "Estimating surface geometry")
+        if adapter is moge2:
+            prediction = adapter.infer(
+                model_manager,
+                parameters,
+                images,
+                include_points=True,
+                progress_callback=lambda index, total: context.progress(
+                    0.12 + 0.58 * index / total,
+                    f"Estimating MoGe-2 geometry ({index + 1}/{total})",
+                ),
+                cancel_check=context.check_cancelled,
+            )
+        else:
+            prediction = adapter.infer(
+                model_manager,
+                parameters,
+                images,
+                progress_callback=lambda index, total: context.progress(
+                    0.12 + 0.58 * index / total,
+                    f"Estimating DA3 geometry ({index + 1}/{total})",
+                ),
+                cancel_check=context.check_cancelled,
+            )
+        context.check_cancelled()
+        frame = adapter.surface_frame(prediction)
+        foreground_paths = write_optional(
+            context,
+            parameters,
+            images,
+            progress_start=0.72,
+            progress_span=0.08,
+        )
+        foreground_mask = None
+        if foreground_paths:
+            foreground_mask = foreground_mesh_mask(
+                foreground_paths[0],
+                frame.depth.shape,
+            )
+        context.progress(0.82, "Building surface")
+        mesh = build_surface(frame, foreground_mask=foreground_mask)
+        context.progress(0.92, "Writing surface")
+        write_surface_archive(mesh, context.directory / "mesh.npz")
+        write_surface_texture(
+            foreground_paths[0] if foreground_paths else images[0],
+            context.directory / "texture.png",
+        )
+        if adapter is moge2:
+            write_normal_texture(
+                prediction.normal[0],
+                context.directory / "normal.png",
+            )
+    context.check_cancelled()
+    context.progress(1.0, "Surface is ready")
+    return {"surface": "mesh.npz"}