Update to 2026-09-17 pipeline snapshot; add weights, L20 assets and recording via Git LFS

Source: RGB-D -> Dyn-HaMR -> L20 retargeting -> FoundationPose -> reference repair -> SPIDER, documented in docs/PIPELINE_LATEST.md and docs/SETUP_AND_WEIGHTS.md. Adds FoundationPose and nvdiffrast upstream snapshots, requirements/pipeline_venv.txt and the FoundationPose weight manifest/downloader. Assets (Git LFS): weights/ (WiLoR detector, HandFlow denoiser, UniDepth-L), FoundationPose checkpoints, HaMeR checkpoint, Dyn-HaMR HMP model and BMC constraints, L20 URDF/meshes, the 20260915_171525 D405 recording and the two box CADs. MANO models are not redistributed (third_party/hamer/_DATA/data/mano/README.txt). Environments, caches and run outputs excluded. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-17 11:27:46 +08:00
parent 7e4ef6f98b
commit ae28d55f81
761 changed files with 55598 additions and 59 deletions
@@ -0,0 +1,120 @@
+# Copyright (c) 2020, NVIDIA CORPORATION.  All rights reserved.
+#
+# NVIDIA CORPORATION and its licensors retain all intellectual property
+# and proprietary rights in and to this software, related documentation
+# and any modifications thereto.  Any use, reproduction, disclosure or
+# distribution of this software and related documentation without an express
+# license agreement from NVIDIA CORPORATION is strictly prohibited.
+
+import numpy as np
+import torch
+
+#----------------------------------------------------------------------------
+# Projection and transformation matrix helpers.
+#----------------------------------------------------------------------------
+
+def projection(x=0.1, n=1.0, f=50.0):
+    return np.array([[n/x,    0,            0,              0],
+                     [  0,  n/x,            0,              0],
+                     [  0,    0, -(f+n)/(f-n), -(2*f*n)/(f-n)],
+                     [  0,    0,           -1,              0]]).astype(np.float32)
+
+def translate(x, y, z):
+    return np.array([[1, 0, 0, x],
+                     [0, 1, 0, y],
+                     [0, 0, 1, z],
+                     [0, 0, 0, 1]]).astype(np.float32)
+
+def rotate_x(a):
+    s, c = np.sin(a), np.cos(a)
+    return np.array([[1, 0,  0, 0],
+                     [0, c, -s, 0],
+                     [0, s,  c, 0],
+                     [0, 0,  0, 1]]).astype(np.float32)
+
+def rotate_y(a):
+    s, c = np.sin(a), np.cos(a)
+    return np.array([[ c, 0, s, 0],
+                     [ 0, 1, 0, 0],
+                     [-s, 0, c, 0],
+                     [ 0, 0, 0, 1]]).astype(np.float32)
+
+def random_rotation_translation(t):
+    m = np.random.normal(size=[3, 3])
+    m[1] = np.cross(m[0], m[2])
+    m[2] = np.cross(m[0], m[1])
+    m = m / np.linalg.norm(m, axis=1, keepdims=True)
+    m = np.pad(m, [[0, 1], [0, 1]], mode='constant')
+    m[3, 3] = 1.0
+    m[:3, 3] = np.random.uniform(-t, t, size=[3])
+    return m
+
+#----------------------------------------------------------------------------
+# Bilinear downsample by 2x.
+#----------------------------------------------------------------------------
+
+def bilinear_downsample(x):
+    w = torch.tensor([[1, 3, 3, 1], [3, 9, 9, 3], [3, 9, 9, 3], [1, 3, 3, 1]], dtype=torch.float32, device=x.device) / 64.0
+    w = w.expand(x.shape[-1], 1, 4, 4) 
+    x = torch.nn.functional.conv2d(x.permute(0, 3, 1, 2), w, padding=1, stride=2, groups=x.shape[-1])
+    return x.permute(0, 2, 3, 1)
+
+#----------------------------------------------------------------------------
+# Image display function using OpenGL.
+#----------------------------------------------------------------------------
+
+_glfw_window = None
+def display_image(image, zoom=None, size=None, title=None): # HWC
+    # Import OpenGL and glfw.
+    import OpenGL.GL as gl
+    import glfw
+
+    # Zoom image if requested.
+    image = np.asarray(image)
+    if size is not None:
+        assert zoom is None
+        zoom = max(1, size // image.shape[0])
+    if zoom is not None:
+        image = image.repeat(zoom, axis=0).repeat(zoom, axis=1)
+    height, width, channels = image.shape
+
+    # Initialize window.
+    if title is None:
+        title = 'Debug window'
+    global _glfw_window
+    if _glfw_window is None:
+        glfw.init()
+        _glfw_window = glfw.create_window(width, height, title, None, None)
+        glfw.make_context_current(_glfw_window)
+        glfw.show_window(_glfw_window)
+        glfw.swap_interval(0)
+    else:
+        glfw.make_context_current(_glfw_window)
+        glfw.set_window_title(_glfw_window, title)
+        glfw.set_window_size(_glfw_window, width, height)
+
+    # Update window.
+    glfw.poll_events()
+    gl.glClearColor(0, 0, 0, 1)
+    gl.glClear(gl.GL_COLOR_BUFFER_BIT)
+    gl.glWindowPos2f(0, 0)
+    gl.glPixelStorei(gl.GL_UNPACK_ALIGNMENT, 1)
+    gl_format = {3: gl.GL_RGB, 2: gl.GL_RG, 1: gl.GL_LUMINANCE}[channels]
+    gl_dtype = {'uint8': gl.GL_UNSIGNED_BYTE, 'float32': gl.GL_FLOAT}[image.dtype.name]
+    gl.glDrawPixels(width, height, gl_format, gl_dtype, image[::-1])
+    glfw.swap_buffers(_glfw_window)
+    if glfw.window_should_close(_glfw_window):
+        return False
+    return True
+
+#----------------------------------------------------------------------------
+# Image save helper.
+#----------------------------------------------------------------------------
+
+def save_image(fn, x):
+    import imageio
+    x = np.rint(x * 255.0)
+    x = np.clip(x, 0, 255).astype(np.uint8)
+    imageio.imsave(fn, x)
+
+#----------------------------------------------------------------------------