area metric calculation error corrected

app.py

@@ -181,7 +181,44 @@ dpt_processor = None
 # ============================================================================
 
 def process_image(image, model_choice="GLPN (Recommended)", visualization_type="mesh"):
-    """Main processing pipeline"""
+    """Main processing pipeline - simplified from first version"""
+    
+    def _generate_quality_assessment(metrics):
+        """Generate quality assessment based on metrics"""
+        assessment = []
+        
+        # Check outlier removal
+        outlier_pct = (metrics['outliers_removed'] / metrics['initial_points']) * 100
+        if outlier_pct < 5:
+            assessment.append("✅ Very clean depth estimation (low noise)")
+        elif outlier_pct < 15:
+            assessment.append("✅ Good depth quality (normal noise level)")
+        else:
+            assessment.append("⚠️ High noise in depth estimation")
+        
+        # Check manifold properties
+        if metrics['is_edge_manifold'] and metrics['is_vertex_manifold']:
+            assessment.append("✅ Excellent topology - mesh is well-formed")
+        elif metrics['is_vertex_manifold']:
+            assessment.append("⚠️ Good local topology but has some edge issues")
+        else:
+            assessment.append("⚠️ Topology issues present - may need cleanup")
+        
+        # Check watertight
+        if metrics['is_watertight']:
+            assessment.append("✅ Watertight mesh - ready for 3D printing!")
+        else:
+            assessment.append("ℹ️ Not watertight - use MeshLab's 'Close Holes' for 3D printing")
+        
+        # Check complexity
+        if metrics['triangles'] > 1000000:
+            assessment.append("ℹ️ Very detailed mesh - may be slow in some software")
+        elif metrics['triangles'] > 500000:
+            assessment.append("✅ High detail mesh - good quality")
+        else:
+            assessment.append("✅ Moderate detail - good balance of quality and performance")
+        
+        return "\n".join(f"- {item}" for item in assessment)
     
     if image is None:
         return None, None, None, "Please upload an image first.", None
@@ -347,16 +384,31 @@ def process_image(image, model_choice="GLPN (Recommended)", visualization_type="
             'is_edge_manifold': mesh.is_edge_manifold(),
             'is_vertex_manifold': mesh.is_vertex_manifold(),
             'is_watertight': mesh.is_watertight(),
-            'surface_area': float(mesh.get_surface_area()),
         }
         
+        # Compute surface area safely
+        try:
+            surface_area = mesh.get_surface_area()
+            metrics['surface_area'] = float(surface_area) if surface_area > 0 else "Unable to compute"
+        except Exception as e:
+            print(f"Could not compute surface area: {e}")
+            metrics['surface_area'] = "Unable to compute"
+        
+        # Compute volume only if watertight
         try:
             if mesh.is_watertight():
-                metrics['volume'] = float(mesh.get_volume())
-        except:
+                volume = mesh.get_volume()
+                metrics['volume'] = float(volume)
+            else:
+                metrics['volume'] = None
+        except Exception as e:
+            print(f"Could not compute volume: {e}")
             metrics['volume'] = None
         
         print("Metrics computed!")
+        print(f"Surface area: {metrics['surface_area']}")
+        print(f"Edge manifold: {metrics['is_edge_manifold']}")
+        print(f"Watertight: {metrics['is_watertight']}")
         
         # STEP 9: Create 3D visualization
         print("Step 9: Creating 3D visualization...")
@@ -473,17 +525,20 @@ def process_image(image, model_choice="GLPN (Recommended)", visualization_type="
 
 ### Point Cloud Statistics
 - **Initial Points**: {metrics['initial_points']:,}
-- **Outliers Removed**: {metrics['outliers_removed']:,}
+- **Outliers Removed**: {metrics['outliers_removed']:,} ({(metrics['outliers_removed']/metrics['initial_points']*100):.1f}%)
 - **Final Points**: {metrics['final_points']:,}
 
 ### Mesh Quality
 - **Vertices**: {metrics['vertices']:,}
 - **Triangles**: {metrics['triangles']:,}
-- **Edge Manifold**: {'✓' if metrics['is_edge_manifold'] else '✗'}
-- **Vertex Manifold**: {'✓' if metrics['is_vertex_manifold'] else '✗'}
-- **Watertight**: {'✓' if metrics['is_watertight'] else '✗'}
-- **Surface Area**: {metrics['surface_area']:.2f}
-- **Volume**: {metrics.get('volume', 'N/A')}
+- **Edge Manifold**: {'✓ Good topology' if metrics['is_edge_manifold'] else '✗ Has non-manifold edges'}
+- **Vertex Manifold**: {'✓ Clean vertices' if metrics['is_vertex_manifold'] else '✗ Has non-manifold vertices'}
+- **Watertight**: {'✓ Closed surface (3D printable)' if metrics['is_watertight'] else '✗ Has boundaries (needs repair for 3D printing)'}
+- **Surface Area**: {metrics['surface_area'] if isinstance(metrics['surface_area'], str) else f"{metrics['surface_area']:.2f}"}
+- **Volume**: {f"{metrics['volume']:.2f}" if metrics.get('volume') else 'N/A (not watertight)'}
+
+### Quality Assessment
+{self._generate_quality_assessment(metrics)}
 
 ### Files Exported
 - Point Cloud: PLY format
@@ -506,11 +561,12 @@ def process_image(image, model_choice="GLPN (Recommended)", visualization_type="
 # GRADIO INTERFACE
 # ============================================================================
 
-with gr.Blocks(title="3D Reconstruction", theme=gr.themes.Soft()) as demo:
+with gr.Blocks(title="Advanced 3D Reconstruction", theme=gr.themes.Soft()) as demo:
     
     gr.Markdown("""
-    # 🏗️  3D Reconstruction from Single Images
+    # 🏗️ Advanced 3D Reconstruction from Single Images
     
+    **Academic-grade pipeline for monocular depth estimation and 3D surface reconstruction**
     
     Upload an image to generate:
     - High-quality depth maps
@@ -523,7 +579,7 @@ with gr.Blocks(title="3D Reconstruction", theme=gr.themes.Soft()) as demo:
     with gr.Tabs():
         
         # ========== RECONSTRUCTION TAB ==========
-        with gr.Tab("Reconstruction"):
+        with gr.Tab("🎯 Reconstruction"):
             with gr.Row():
                 with gr.Column(scale=1):
                     input_image = gr.Image(type="pil", label="Upload Image")
@@ -541,7 +597,7 @@ with gr.Blocks(title="3D Reconstruction", theme=gr.themes.Soft()) as demo:
                         label="3D Visualization Type"
                     )
                     
-                    reconstruct_btn = gr.Button("Start Reconstruction", variant="primary", size="lg")
+                    reconstruct_btn = gr.Button("🚀 Start Reconstruction", variant="primary", size="lg")
                 
                 with gr.Column(scale=2):
                     depth_output = gr.Image(label="Depth Map Comparison")
@@ -659,7 +715,10 @@ with gr.Blocks(title="3D Reconstruction", theme=gr.themes.Soft()) as demo:
             
             **Depth Map Comparison:**
             - Left: Your original image
-            - Right: Estimated depth map (warmer colors = closer)
+            - Right: Estimated depth map
+              - **Yellow/Red colors = CLOSER** objects
+              - **Purple/Blue colors = FARTHER** objects
+              - Color scale shows relative depth (not absolute distance)
             
             **Interactive 3D Viewer:**
             - **Rotate**: Click and drag
@@ -853,13 +912,18 @@ with gr.Blocks(title="3D Reconstruction", theme=gr.themes.Soft()) as demo:
     
     # ========== FOOTER ==========
     gr.Markdown("""
-    ---    
+    ---
+    
+    ### 🎓 PhD Application Demo
+    
     This application demonstrates comprehensive understanding of:
     - Computer vision and deep learning
     - 3D geometry and reconstruction
     - Software engineering best practices
     - Research methodology and evaluation
     
+    **Developed for academic research purposes**
+    
     *Version 1.0*
     """)