added new model file.

nerfstudio/models/nerfacto_4k.py

@@ -0,0 +1,172 @@
+# Copyright 2022 The Nerfstudio Team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+"""
+NeRF implementation that combines many recent advancements, optimized for hi-res images.
+"""
+
+from __future__ import annotations
+
+from dataclasses import dataclass
+from typing import Dict, Tuple
+
+import torch
+
+from nerfstudio.cameras.rays import RayBundle
+from nerfstudio.field_components.field_heads import FieldHeadNames
+from nerfstudio.model_components.losses import (
+    distortion_loss,
+    interlevel_loss,
+    orientation_loss,
+    pred_normal_loss,
+)
+from nerfstudio.models.nerfacto import NerfactoModel, NerfactoModelConfig
+from nerfstudio.utils import colormaps
+
+
+@dataclass
+class Nerfacto4KModelConfig(NerfactoModelConfig):
+    """Nerfacto-4K Model Config"""
+
+
+class Nerfacto4KModel(NerfactoModel):
+    """Nerfacto model
+
+    Args:
+        config: Nerfacto configuration to instantiate model
+    """
+
+    config: Nerfacto4KModelConfig
+
+    def populate_modules(self):
+        """Set the fields and modules."""
+        super().populate_modules()
+
+    def get_outputs(self, ray_bundle: RayBundle):
+        ray_samples, weights_list, ray_samples_list = self.proposal_sampler(ray_bundle, density_fns=self.density_fns)
+        field_outputs = self.field(ray_samples, compute_normals=self.config.predict_normals)
+        weights = ray_samples.get_weights(field_outputs[FieldHeadNames.DENSITY])
+        weights_list.append(weights)
+        ray_samples_list.append(ray_samples)
+
+        rgb = self.renderer_rgb(rgb=field_outputs[FieldHeadNames.RGB], weights=weights)
+        depth = self.renderer_depth(weights=weights, ray_samples=ray_samples)
+        accumulation = self.renderer_accumulation(weights=weights)
+
+        outputs = {
+            "rgb": rgb,
+            "accumulation": accumulation,
+            "depth": depth,
+        }
+
+        if self.config.predict_normals:
+            outputs["normals"] = self.renderer_normals(normals=field_outputs[FieldHeadNames.NORMALS], weights=weights)
+            outputs["pred_normals"] = self.renderer_normals(field_outputs[FieldHeadNames.PRED_NORMALS], weights=weights)
+
+        # These use a lot of GPU memory, so we avoid storing them for eval.
+        if self.training:
+            outputs["weights_list"] = weights_list
+            outputs["ray_samples_list"] = ray_samples_list
+
+        if self.training and self.config.predict_normals:
+            outputs["rendered_orientation_loss"] = orientation_loss(
+                weights.detach(), field_outputs[FieldHeadNames.NORMALS], ray_bundle.directions
+            )
+
+            outputs["rendered_pred_normal_loss"] = pred_normal_loss(
+                weights.detach(),
+                field_outputs[FieldHeadNames.NORMALS].detach(),
+                field_outputs[FieldHeadNames.PRED_NORMALS],
+            )
+
+        for i in range(self.config.num_proposal_iterations):
+            outputs[f"prop_depth_{i}"] = self.renderer_depth(weights=weights_list[i], ray_samples=ray_samples_list[i])
+
+        return outputs
+
+    def get_metrics_dict(self, outputs, batch):
+        metrics_dict = {}
+        image = batch["image"].to(self.device)
+        metrics_dict["psnr"] = self.psnr(outputs["rgb"], image)
+        if self.training:
+            metrics_dict["distortion"] = distortion_loss(outputs["weights_list"], outputs["ray_samples_list"])
+        return metrics_dict
+
+    def get_loss_dict(self, outputs, batch, metrics_dict=None):
+        loss_dict = {}
+        image = batch["image"].to(self.device)
+        loss_dict["rgb_loss"] = self.rgb_loss(image, outputs["rgb"])
+        if self.training:
+            loss_dict["interlevel_loss"] = self.config.interlevel_loss_mult * interlevel_loss(
+                outputs["weights_list"], outputs["ray_samples_list"]
+            )
+            assert metrics_dict is not None and "distortion" in metrics_dict
+            loss_dict["distortion_loss"] = self.config.distortion_loss_mult * metrics_dict["distortion"]
+            if self.config.predict_normals:
+                # orientation loss for computed normals
+                loss_dict["orientation_loss"] = self.config.orientation_loss_mult * torch.mean(
+                    outputs["rendered_orientation_loss"]
+                )
+
+                # ground truth supervision for normals
+                loss_dict["pred_normal_loss"] = self.config.pred_normal_loss_mult * torch.mean(
+                    outputs["rendered_pred_normal_loss"]
+                )
+        return loss_dict
+
+    def get_image_metrics_and_images(
+        self, outputs: Dict[str, torch.Tensor], batch: Dict[str, torch.Tensor]
+    ) -> Tuple[Dict[str, float], Dict[str, torch.Tensor]]:
+
+        image = batch["image"].to(self.device)
+        rgb = outputs["rgb"]
+        acc = colormaps.apply_colormap(outputs["accumulation"])
+        depth = colormaps.apply_depth_colormap(
+            outputs["depth"],
+            accumulation=outputs["accumulation"],
+        )
+
+        combined_rgb = torch.cat([image, rgb], dim=1)
+        combined_acc = torch.cat([acc], dim=1)
+        combined_depth = torch.cat([depth], dim=1)
+
+        # Switch images from [H, W, C] to [1, C, H, W] for metrics computations
+        image = torch.moveaxis(image, -1, 0)[None, ...]
+        rgb = torch.moveaxis(rgb, -1, 0)[None, ...]
+
+        psnr = self.psnr(image, rgb)
+        ssim = self.ssim(image, rgb)
+        lpips = self.lpips(image, rgb)
+
+        # all of these metrics will be logged as scalars
+        metrics_dict = {"psnr": float(psnr.item()), "ssim": float(ssim)}  # type: ignore
+        metrics_dict["lpips"] = float(lpips)
+
+        images_dict = {"img": combined_rgb, "accumulation": combined_acc, "depth": combined_depth}
+
+        # normals to RGB for visualization. TODO: use a colormap
+        if "normals" in outputs:
+            images_dict["normals"] = (outputs["normals"] + 1.0) / 2.0
+        if "pred_normals" in outputs:
+            images_dict["pred_normals"] = (outputs["pred_normals"] + 1.0) / 2.0
+
+        for i in range(self.config.num_proposal_iterations):
+            key = f"prop_depth_{i}"
+            prop_depth_i = colormaps.apply_depth_colormap(
+                outputs[key],
+                accumulation=outputs["accumulation"],
+            )
+            images_dict[key] = prop_depth_i
+
+        return metrics_dict, images_dict