| import os |
| import sys |
| import random |
| import torch |
| import numpy as np |
| import torch.nn.functional as F |
| from omegaconf import OmegaConf |
| from hydra import compose, initialize_config_dir |
| from hydra.core.global_hydra import GlobalHydra |
|
|
| from core.registry import register_method |
| from core.base_method import BaseMethod |
|
|
| sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '../../conegs'))) |
| from utils.loss_utils import l1_loss, ssim |
| from gaussian_renderer import render as native_render |
| from scene import Scene, GaussianModel |
| from scene.nerf_model import NeRFModel |
| from utils.nerf_utils import get_num_rays_to_cast |
|
|
| @register_method("conegs") |
| class ConeGSWrapper(BaseMethod): |
| def __init__(self, dataset_config, hyperparams): |
| conegs_dir = os.path.abspath(os.path.join(os.path.dirname(__file__), '../../conegs')) |
| if not GlobalHydra().is_initialized(): |
| initialize_config_dir(config_dir=os.path.join(conegs_dir, 'configs'), version_base=None) |
| self.cfg = compose(config_name="defaults") |
| |
| OmegaConf.set_struct(self.cfg, False) |
| |
| self.cfg.gaussian_model.source_path = dataset_config["source_path"] |
| self.cfg.gaussian_model.model_path = dataset_config["model_path"] |
| OmegaConf.set_struct(self.cfg, False) |
| self.cfg.gaussian_model.eval = True |
| if hasattr(self.cfg, 'dataset'): |
| self.cfg.dataset.eval = True |
| self.cfg.optimization.resolution = float(dataset_config.get("resolution", 1)) |
| |
| self.cfg.nerf_model.num_iters_pretrain = 20000 |
| self.cfg.nerf_model.nerf_train_during_3dgs = False |
| self.cfg.optimization.use_preactivation_opacity_penalty = True |
| self.cfg.optimization.opacity_penalty = 0.0002 |
| |
| if "max_points" in hyperparams: |
| self.cfg.optimization.max_points = hyperparams["max_points"] |
| |
| self.track_decoupling = hyperparams.get("track_decoupling", False) |
|
|
| self.gaussians = GaussianModel(self.cfg.gaussian_model.sh_degree) |
| self.scene = Scene(self.cfg.gaussian_model, self.gaussians, stack_train_images=self.cfg.nerf_model.stack_images) |
| self.gaussians.training_setup(self.cfg.optimization) |
| |
| bg_color = [1, 1, 1] if self.cfg.gaussian_model.white_background else [0, 0, 0] |
| self.background = torch.tensor(bg_color, dtype=torch.float32, device="cuda") |
| |
| self.nerf_model = NeRFModel(self.cfg.nerf_model) |
| self.nerf_model.pretrain_model(self.cfg, self.gaussians, self.scene, self.background) |
| |
| self.nerf_model.prop_optimizer.zero_grad(set_to_none=True) |
| self.nerf_model.model_optimizer.zero_grad(set_to_none=True) |
| if hasattr(self.scene, "stacked_images"): |
| del self.scene.stacked_images |
| if hasattr(self.scene, "stacked_cam2worlds"): |
| del self.scene.stacked_cam2worlds |
| if hasattr(self.scene, "stacked_pix2cams"): |
| del self.scene.stacked_pix2cams |
| |
| for i in range(len(self.scene.getTrainCameras())): |
| self.scene.getTrainCameras()[i].original_image = self.scene.getTrainCameras()[i].original_image.cuda() |
| for i in range(len(self.scene.getTestCameras())): |
| self.scene.getTestCameras()[i].original_image = self.scene.getTestCameras()[i].original_image.cuda() |
| |
| num_rays_to_cast = get_num_rays_to_cast(len(self.gaussians._xyz), gaussian_percentage_increase=self.cfg.optimization.gaussian_percentage_increase, nerf_train_during_3dgs=self.cfg.nerf_model.nerf_train_during_3dgs) |
| self.nerf_model.estimator_params["n_rays"] = num_rays_to_cast |
| self.nerf_model.estimator_params["stratified"] = False |
| self.nerf_model.estimator_params["requires_grad"] = False |
|
|
| self.viewpoint_stack = self.scene.getTrainCameras().copy() |
| self.last_n_gaussians = len(self.gaussians.get_xyz) |
|
|
| def _get_u_step(self, params, grads): |
| u_vecs = [] |
| for p, g in zip(params, grads): |
| if g is None: |
| continue |
| state = self.gaussians.optimizer.state.get(p, None) |
| if state is not None and "exp_avg_sq" in state: |
| v = state["exp_avg_sq"] |
| pg_lr = 1e-4 |
| for pg in self.gaussians.optimizer.param_groups: |
| if any(p is param for param in pg["params"]): |
| pg_lr = pg["lr"] |
| break |
| u = (pg_lr / (torch.sqrt(v) + 1e-15)) * g |
| else: |
| u = g |
| u_vecs.append(u.view(-1)) |
| if len(u_vecs) == 0: |
| return torch.zeros(1, device="cuda") |
| return torch.cat(u_vecs) |
|
|
| def train_iteration(self, step): |
| self.gaussians.update_learning_rate(step) |
| if step % self.cfg.optimization.SH_increase_iter == 0: |
| self.gaussians.oneupSHdegree() |
| |
| if not self.viewpoint_stack: |
| self.viewpoint_stack = self.scene.getTrainCameras().copy() |
| |
| viewpoint_cam = self.viewpoint_stack.pop(random.randint(0, len(self.viewpoint_stack) - 1)) |
| gt_image = viewpoint_cam.original_image.cuda() |
| |
| bg = torch.rand((3), device="cuda") if self.cfg.optimization.random_background else self.background |
| render_pkg = native_render(viewpoint_cam, self.gaussians, self.cfg.pipeline, bg) |
| image = render_pkg["render"] |
| |
| l1_full = torch.abs((image - gt_image)) |
| ssim_full = ssim(image, gt_image) |
| loss_target = (1.0 - self.cfg.optimization.lambda_dssim) * l1_full.mean() |
| loss_ssim_part = self.cfg.optimization.lambda_dssim * (1.0 - ssim_full.mean()) |
| |
| opacity = self.gaussians._opacity if self.cfg.optimization.use_preactivation_opacity_penalty else torch.abs(self.gaussians.get_opacity) |
| loss_opacity = self.cfg.optimization.opacity_penalty * opacity.mean() |
| |
| loss = loss_target + loss_ssim_part + loss_opacity |
| |
| weights = (1.0 - self.cfg.optimization.densification_lambda_dssim) * l1_full.mean(0) + self.cfg.optimization.densification_lambda_dssim * (1.0 - ssim_full.mean(0)) |
| weights = torch.clamp_min(weights, 0.0) |
| |
| metrics = {} |
| |
| if self.track_decoupling and step % 100 == 0: |
| semantic_groups = { |
| "spatial": [self.gaussians._xyz], |
| "geometry": [self.gaussians._scaling, self.gaussians._rotation], |
| "opacity": [self.gaussians._opacity], |
| "appearance": [self.gaussians._features_dc, self.gaussians._features_rest] |
| } |
| |
| self.gaussians.optimizer.zero_grad(set_to_none=True) |
| loss_target.backward(retain_graph=True) |
| grad_target_dict = {} |
| for k, params in semantic_groups.items(): |
| grad_target_dict[k] = [p.grad.clone() if p.grad is not None else torch.zeros_like(p) for p in params] |
| |
| self.gaussians.optimizer.zero_grad(set_to_none=True) |
| loss_opacity.backward(retain_graph=True) |
| grad_parasitic_dict = {} |
| for k, params in semantic_groups.items(): |
| grad_parasitic_dict[k] = [p.grad.clone() if p.grad is not None else torch.zeros_like(p) for p in params] |
| |
| for k in semantic_groups.keys(): |
| u_t = self._get_u_step(semantic_groups[k], grad_target_dict[k]) |
| u_p = self._get_u_step(semantic_groups[k], grad_parasitic_dict[k]) |
| |
| norm_t = torch.norm(u_t) |
| norm_p = torch.norm(u_p) |
| |
| if norm_p > 1e-7 and norm_t > 1e-7: |
| s_group = F.cosine_similarity(u_t.unsqueeze(0), u_p.unsqueeze(0)).squeeze() |
| r_group = norm_p / (norm_t + norm_p + 1e-7) |
| ti = float(r_group * torch.clamp(-s_group, min=0.0)) |
| else: |
| ti = 0.0 |
| metrics[f"TI_{k}"] = ti |
| |
| self.gaussians.optimizer.zero_grad(set_to_none=True) |
| loss.backward() |
| else: |
| loss.backward() |
|
|
| with torch.no_grad(): |
| if self.cfg.optimization.use_3dgs_densification and step < self.cfg.optimization.densify_until_iter: |
| radii = render_pkg["radii"] |
| visibility_filter = render_pkg["visibility_filter"] |
| self.gaussians.max_radii2D[visibility_filter] = torch.max(self.gaussians.max_radii2D[visibility_filter], radii[visibility_filter]) |
| self.gaussians.add_densification_stats(render_pkg["viewspace_points"], render_pkg["visibility_filter"], render_pkg.get("optimized_samples_index", 0)) |
|
|
| if step > self.cfg.optimization.densify_from_iter and step % 100 == 0: |
| size_threshold = 20 if step > 3000 else None |
| self.gaussians.densify_and_prune(0.0002, 0.005, self.scene.cameras_extent, size_threshold, max_points=self.cfg.optimization.max_points) |
| |
| if step % 3000 == 0: |
| self.gaussians.reset_opacity() |
|
|
| self.gaussians.optimizer.step() |
| self.gaussians.optimizer.zero_grad(set_to_none=True) |
|
|
| if self.cfg.optimization.densify_from_iter < step and step < self.cfg.optimization.densify_until_iter and (self.cfg.optimization.gaussian_percentage_increase or self.cfg.optimization.max_points): |
| num_rays_to_cast = get_num_rays_to_cast(len(self.gaussians._xyz), gaussian_percentage_increase=self.cfg.optimization.gaussian_percentage_increase, nerf_train_during_3dgs=self.cfg.nerf_model.nerf_train_during_3dgs) |
| self.nerf_model.cast_rays_during_optimization(weights, num_rays_to_cast, viewpoint_cam, self.cfg, self.gaussians, self.scene, bg, step) |
|
|
| with torch.no_grad(): |
| if self.cfg.optimization.densify_from_iter < step and step % 100 == 0: |
| dead_mask = (self.gaussians.get_opacity <= 0.005).squeeze(-1) |
| if step < self.cfg.optimization.densify_until_iter: |
| self.gaussians.prune_points(dead_mask) |
| if self.cfg.optimization.gaussian_percentage_increase or self.cfg.optimization.max_points: |
| self.gaussians.initialize_new_points(use_cone_radius=True, max_points=self.cfg.optimization.max_points, opacity_init_value=self.cfg.optimization.opacity_init_value) |
|
|
| num_gaussians = self.gaussians.get_xyz.shape[0] |
| stashed_count = len(self.gaussians.stashed_xyz) if hasattr(self.gaussians, "stashed_xyz") and self.gaussians.stashed_xyz is not None else 0 |
| |
| metrics.update({ |
| "loss": float(loss), |
| "loss_l1": float(loss_target), |
| "loss_ssim": float(loss_ssim_part), |
| "num_gaussians": int(num_gaussians), |
| "delta_N": int(num_gaussians - self.last_n_gaussians), |
| "peak_vram_GB": float(torch.cuda.max_memory_allocated() / (1024 ** 3)), |
| "stashed_points_count": int(stashed_count), |
| "penalty_loss_ratio": float(loss_opacity / (loss + 1e-7)) |
| }) |
| self.last_n_gaussians = num_gaussians |
| |
| histograms = {} |
| if step % 1000 == 0: |
| histograms["opacity"] = torch.sigmoid(self.gaussians._opacity).clone().detach() |
| scales = torch.exp(self.gaussians._scaling).clone().detach() |
| histograms["scaling"] = scales |
| scales_2d = scales[:, :2] if scales.shape[1] >= 2 else scales |
| gamma = scales_2d.max(dim=-1)[0] / (scales_2d.min(dim=-1)[0] + 1e-7) |
| histograms["anisotropy"] = gamma |
| histograms["sh_dc_mag"] = self.gaussians._features_dc.detach().norm(dim=-1) |
|
|
| return metrics, histograms |
|
|
| def render(self, camera): |
| with torch.no_grad(): |
| render_pkg = native_render(camera, self.gaussians, self.cfg.pipeline, self.background) |
| return {"image": render_pkg["render"], "depth": render_pkg.get("depth", None)} |
|
|
| def save(self, save_dir, step): |
| self.scene.save(step) |
|
|
| def load(self, model_path, iteration): |
| self.gaussians.load_ply(os.path.join(model_path, 'point_cloud', f'iteration_{iteration}', 'point_cloud.ply')) |
|
|
| def get_spatial_centers(self): |
| return self.gaussians._xyz |
|
|
| def compute_physical_metrics(self, cameras=None): |
| metrics = {} |
| with torch.no_grad(): |
| raw_scales = self.gaussians._scaling |
| scales = torch.exp(raw_scales) |
| |
| scales_2d = scales[:, :2] if scales.dim() > 1 and scales.shape[1] >= 2 else scales.unsqueeze(-1).expand(-1, 2) |
| |
| max_S, _ = torch.max(scales_2d, dim=1) |
| min_S, _ = torch.min(scales_2d, dim=1) |
| gamma = max_S / (min_S + 1e-7) |
| |
| metrics["gamma_median"] = float(torch.median(gamma)) |
| metrics["gamma_90th_percentile"] = float(torch.quantile(gamma, 0.90)) |
| metrics["scale_mean"] = float(torch.mean(scales_2d)) |
| metrics["alpha_mean"] = float(torch.mean(torch.sigmoid(self.gaussians._opacity))) |
| |
| dc, rest = self.gaussians._features_dc, self.gaussians._features_rest |
| if rest is not None and rest.shape[1] > 0: |
| metrics["sh_energy_ratio"] = float(rest.norm(dim=-1).mean() / (dc.norm(dim=-1).mean() + 1e-7)) |
| |
| if cameras is not None and len(cameras) > 0: |
| view_dirs = [] |
| for c in cameras: |
| view_dirs.append(c.world_view_transform[:3, 2].tolist()) |
| view_dirs = F.normalize(torch.tensor(view_dirs, dtype=torch.float32, device="cuda"), dim=1) |
|
|
| rots = F.normalize(self.gaussians._rotation.clone(), dim=1) |
| w, x, y, z = rots.unbind(dim=-1) |
| normals = F.normalize(torch.stack([2*(x*z + w*y), 2*(y*z - w*x), 1-2*(x*x + y*y)], dim=-1), dim=1) |
| |
| max_cos, _ = torch.max(torch.abs(torch.matmul(normals, view_dirs.T)), dim=1) |
| metrics["billboard_bias_ratio"] = float((max_cos > 0.90).float().mean()) |
|
|
| return metrics |
|
|
| def evaluate_spatial_field(self, query_points: torch.Tensor, cameras=None) -> torch.Tensor: |
| with torch.no_grad(): |
| V = query_points.shape[0] |
| densities = torch.zeros(V, device="cuda") |
| xyz, opacities = self.gaussians._xyz, torch.sigmoid(self.gaussians._opacity).squeeze() |
| scales = torch.exp(self.gaussians._scaling) |
| sigma_sq = (scales[:, :2].max(dim=1)[0].pow(2)) if scales.shape[1] >= 2 else scales.squeeze().pow(2) |
| |
| N_gaussians = xyz.shape[0] |
| chunk_size = max(1, 30_000_000 // (N_gaussians + 1)) |
| for i in range(0, V, chunk_size): |
| end = min(i + chunk_size, V) |
| dist_sq = torch.cdist(query_points[i:end], xyz, p=2).pow(2) |
| weights = torch.exp(-0.5 * dist_sq / (sigma_sq.unsqueeze(0) + 1e-7)) |
| densities[i:end] = torch.sum(weights * opacities.unsqueeze(0), dim=1) |
| return densities |
|
|
