Update app.py

app.py

@@ -676,52 +676,56 @@ def convert_image_to_3d():
                 return
             
             try:
- def estimate_depth():
-    with torch.no_grad():
-        # Make sure image is in RGB format for the models
-        rgb_image = image
-        if rgb_image.mode == 'RGBA':
-            # Convert RGBA to RGB for model processing
-            rgb_image = Image.new('RGB', image.size, (255, 255, 255))
-            rgb_image.paste(image, mask=image.split()[3])  # Use alpha channel as mask
-        
-        # DPT-Large
-        dpt_result = dpt_model(rgb_image)
-        dpt_depth = dpt_result["depth"]
-        processing_jobs[job_id]['progress'] = 40
-        
-        # Depth Anything (if loaded)
-        if da_model and da_processor:
-            inputs = da_processor(images=rgb_image, return_tensors="pt")  # Use RGB image here
-            inputs = {k: v.to("cpu") for k, v in inputs.items()}
-            outputs = da_model(**inputs)
-            da_depth = outputs.predicted_depth.squeeze()
-            da_depth = torch.nn.functional.interpolate(
-                da_depth.unsqueeze(0).unsqueeze(0),
-                size=(image.height, image.width),
-                mode='bicubic',
-                align_corners=False
-            ).squeeze()
-            processing_jobs[job_id]['progress'] = 50
+                def estimate_depth():
+                    with torch.no_grad():
+                        # Make sure image is in RGB format for the models
+                        rgb_image = image
+                        if rgb_image.mode == 'RGBA':
+                            # Convert RGBA to RGB for model processing
+                             rgb_image = Image.new('RGB', image.size, (255, 255, 255))
+                             rgb_image.paste(image, mask=image.split()[3])  # Use alpha channel as mask
+        
+                        # DPT-Large
+                        dpt_result = dpt_model(rgb_image)
+                        dpt_depth = dpt_result["depth"]
+                        processing_jobs[job_id]['progress'] = 40
+        
+        
+    
+        
+                        # Depth Anything (if loaded)
+                        if da_model and da_processor:
+                            inputs = da_processor(images=rgb_image, return_tensors="pt")  # Use RGB image here
+                            inputs = {k: v.to("cpu") for k, v in inputs.items()}
+                            outputs = da_model(**inputs)
+                            da_depth = outputs.predicted_depth.squeeze()
+                            da_depth = torch.nn.functional.interpolate(
+                                da_depth.unsqueeze(0).unsqueeze(0),
+                                size=(image.height, image.width),
+                                mode='bicubic',
+                                align_corners=False
+                            ).squeeze()
+                            processing_jobs[job_id]['progress'] = 50
             
-            # Improved fusion of depth maps
-            fused_depth = fuse_depth_maps(dpt_depth, da_depth, detail_level)
-        else:
-            # Just use DPT with enhanced processing if Depth Anything is not available
-            fused_depth = np.array(dpt_depth) if isinstance(dpt_depth, Image.Image) else dpt_depth
-            if len(fused_depth.shape) > 2:
-                fused_depth = np.mean(fused_depth, axis=2)
-            # Apply more conservative normalization
-            p_low, p_high = np.percentile(fused_depth, [2, 98])
-            fused_depth = np.clip((fused_depth - p_low) / (p_high - p_low), 0, 1) if p_high > p_low else fused_depth
-            # Apply compression to limit extreme depths
-            fused_depth = np.power(fused_depth, 0.85)
-        
-        # Save depth map for debugging
-        depth_debug_path = os.path.join(output_dir, "depth_map.png")
-        cv2.imwrite(depth_debug_path, (fused_depth * 255).astype(np.uint8))
-        
-        return fused_depth
+                             # Improved fusion of depth maps
+                            fused_depth = fuse_depth_maps(dpt_depth, da_depth, detail_level)
+                        else:
+                            # Just use DPT with enhanced processing if Depth Anything is not available
+                            fused_depth = np.array(dpt_depth) if isinstance(dpt_depth, Image.Image) else dpt_depth
+                            if len(fused_depth.shape) > 2:
+                                fused_depth = np.mean(fused_depth, axis=2)
+                            # Apply more conservative normalization
+                            p_low, p_high = np.percentile(fused_depth, [2, 98])
+                            fused_depth = np.clip((fused_depth - p_low) / (p_high - p_low), 0, 1) if p_high > p_low else fused_depth
+                            # Apply compression to limit extreme depths
+                            fused_depth = np.power(fused_depth, 0.85)
+        
+                        # Save depth map for debugging
+                        depth_debug_path = os.path.join(output_dir, "depth_map.png")
+                        cv2.imwrite(depth_debug_path, (fused_depth * 255).astype(np.uint8))
+        
+                        return fused_depth
+       
                 
                 fused_depth, error = process_with_timeout(estimate_depth, [], TIMEOUT_SECONDS)