| import os |
| import sys |
| import random |
| import math |
| import torch |
| import numpy as np |
| import torch.nn.functional as F |
| from argparse import ArgumentParser |
|
|
| 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__), '../../ContextGS_offy'))) |
| from utils.loss_utils import l1_loss, ssim |
| from gaussian_renderer import prefilter_voxel, render as native_render |
| from scene import Scene, GaussianModel |
| from arguments import ModelParams, PipelineParams, OptimizationParams |
|
|
| @register_method("contextgs") |
| class ContextGS_offyWrapper(BaseMethod): |
| def __init__(self, dataset_config, hyperparams): |
| self.parser = ArgumentParser() |
| self.lp = ModelParams(self.parser) |
| self.op = OptimizationParams(self.parser) |
| self.pp = PipelineParams(self.parser) |
| |
| self.parser.add_argument('--level_num', type=int, default=3) |
| self.parser.add_argument('--level_scale', type=int, default=10) |
| self.parser.add_argument("--n_features", type=int, default=4) |
| self.parser.add_argument("--lmbda", type=float, default=0.001) |
| self.parser.add_argument("--lmbda_rec", type=float, default=1) |
| self.parser.add_argument("--disable_hyper", default=False, action="store_true") |
| |
| self.args = self.parser.parse_args([]) |
|
|
| self.args.source_path = dataset_config["source_path"] |
| self.args.model_path = dataset_config["model_path"] |
| self.args.eval = True |
| self.args.resolution = dataset_config.get("resolution", 1) |
| self.track_decoupling = hyperparams.get("track_decoupling", False) |
|
|
| self.dataset = self.lp.extract(self.args) |
| self.opt = self.op.extract(self.args) |
| self.pipe = self.pp.extract(self.args) |
| self.args_param = self.args |
|
|
| self.gaussians = GaussianModel( |
| self.dataset.feat_dim, |
| self.dataset.n_offsets, |
| self.dataset.voxel_size, |
| self.dataset.update_depth, |
| self.dataset.update_init_factor, |
| self.dataset.update_hierachy_factor, |
| self.dataset.use_feat_bank, |
| n_features_per_level=self.args_param.n_features, |
| level_num=self.args_param.level_num, |
| hyper_divisor=self.dataset.hyper_divisor, |
| target_ratio=self.dataset.target_ratio, |
| disable_hyper=self.args_param.disable_hyper |
| ) |
| |
| import sys as _sys |
| _scene, _explicit_res = None, None |
| for _i, _a in enumerate(_sys.argv[:-1]): |
| _v = _sys.argv[_i + 1] |
| if _a == "--scene": _scene = _v |
| elif _a == "--source_path": _scene = _v.rstrip("/").split("/")[-1] |
| elif _a == "--resolution": |
| try: _explicit_res = int(_v) |
| except: pass |
| _OUTDOOR_360 = {"bicycle", "flowers", "garden", "stump", "treehill"} |
| if _explicit_res is not None and _explicit_res > 0: |
| _res = _explicit_res |
| elif _scene is not None: |
| _res = 4 if _scene in _OUTDOOR_360 else 2 |
| else: |
| _res = None |
| try: |
| if _res is not None: |
| self.dataset.resolution = _res |
| print("[res-fix] scene=%s explicit=%s -> res=%s (%s)" % (_scene, _explicit_res, _res, __file__)) |
| except Exception as _e: |
| print("[res-fix] FAILED:", _e) |
| |
| self.scene = Scene(self.dataset, self.gaussians) |
| self.gaussians.update_anchor_bound() |
| self.gaussians.training_setup(self.opt) |
|
|
| bg_color = [1, 1, 1] if self.dataset.white_background else [0, 0, 0] |
| self.background = torch.tensor(bg_color, dtype=torch.float32, device="cuda") |
| self.viewpoint_stack = self.scene.getTrainCameras().copy() |
| |
| self.last_n_gaussians = self.gaussians.get_anchor.shape[0] |
|
|
| def train_iteration(self, step): |
| self.gaussians.update_learning_rate(step) |
| |
| 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)) |
| |
| retain_grad = (step < self.opt.update_until and step >= 0) |
| voxel_visible_mask = prefilter_voxel(viewpoint_cam, self.gaussians, self.pipe, self.background) |
| render_pkg = native_render(viewpoint_cam, self.gaussians, self.pipe, self.background, visible_mask=voxel_visible_mask, retain_grad=retain_grad, step=step) |
| |
| image = render_pkg["render"] |
| viewspace_point_tensor = render_pkg["viewspace_points"] |
| visibility_filter = render_pkg["visibility_filter"] |
| offset_selection_mask = render_pkg["selection_mask"] |
| opacity = render_pkg["neural_opacity"] |
| scaling = render_pkg["scaling"] |
| bit_per_param = render_pkg.get("bit_per_param", None) |
| |
| gt_image = viewpoint_cam.original_image.cuda() |
| |
| Ll1 = l1_loss(image, gt_image) |
| ssim_value = ssim(image, gt_image) |
| scaling_reg = scaling.prod(dim=1).mean() |
| |
| loss_target = self.args_param.lmbda_rec * ((1.0 - self.opt.lambda_dssim) * Ll1 + self.opt.lambda_dssim * (1.0 - ssim_value)) |
| |
| loss_parasitic = 0.01 * scaling_reg |
| if bit_per_param is not None: |
| loss_parasitic = loss_parasitic + self.args_param.lmbda * bit_per_param |
| loss_parasitic = loss_parasitic + 5e-4 * torch.mean(torch.sigmoid(self.gaussians._mask)) |
| |
| loss = loss_target + loss_parasitic |
|
|
| grad_cos_sim = 0.0 |
| parasitic_ratio = 0.0 |
| stats = {} |
|
|
| if self.track_decoupling and step % 100 == 0: |
| param_groups_map = { |
| "spatial": [self.gaussians._anchor, self.gaussians._offset], |
| "geometry": [self.gaussians._scaling, self.gaussians._rotation], |
| "opacity": [self.gaussians._opacity, self.gaussians._mask], |
| "appearance": [self.gaussians._anchor_feat, self.gaussians._hyper_latent], |
| } |
|
|
| self.gaussians.optimizer.zero_grad(set_to_none=True) |
| loss_target.backward(retain_graph=True) |
| grads_target = {} |
| for group_name, params in param_groups_map.items(): |
| grads_target[group_name] = [] |
| for p in params: |
| if p.grad is not None: |
| grads_target[group_name].append(p.grad.clone()) |
| else: |
| grads_target[group_name].append(torch.zeros_like(p)) |
|
|
| self.gaussians.optimizer.zero_grad(set_to_none=True) |
| loss_parasitic.backward(retain_graph=True) |
| grads_parasitic = {} |
| for group_name, params in param_groups_map.items(): |
| grads_parasitic[group_name] = [] |
| for p in params: |
| if p.grad is not None: |
| grads_parasitic[group_name].append(p.grad.clone()) |
| else: |
| grads_parasitic[group_name].append(torch.zeros_like(p)) |
|
|
| for group_name, params in param_groups_map.items(): |
| u_t_list = [] |
| u_p_list = [] |
| for i, p in enumerate(params): |
| state = self.gaussians.optimizer.state.get(p, None) |
| if state is not None and "exp_avg_sq" in state: |
| v_t = state["exp_avg_sq"] |
| else: |
| v_t = torch.ones_like(p) |
| |
| for param_group in self.gaussians.optimizer.param_groups: |
| if id(p) in [id(opt_p) for opt_p in param_group['params']]: |
| lr = param_group['lr'] |
| break |
| else: |
| lr = 1e-3 |
|
|
| u_t = (lr / (torch.sqrt(v_t) + 1e-8)) * grads_target[group_name][i] |
| u_p = (lr / (torch.sqrt(v_t) + 1e-8)) * grads_parasitic[group_name][i] |
| u_t_list.append(u_t.reshape(-1)) |
| u_p_list.append(u_p.reshape(-1)) |
| |
| gt = torch.cat(u_t_list) |
| gp = torch.cat(u_p_list) |
| |
| if gt.norm() > 0 and gp.norm() > 0: |
| cos = float(F.cosine_similarity(gt.unsqueeze(0), gp.unsqueeze(0))) |
| r = float(gp.norm() / (gt.norm() + gp.norm() + 1e-7)) |
| ti = r * max(0.0, -cos) |
| else: |
| ti = 0.0 |
| stats[f"sti_{group_name}"] = ti |
|
|
| all_gt = torch.cat([torch.cat(u_t_list) for group_name, params in param_groups_map.items() for i, p in enumerate(params)]) |
| all_gp = torch.cat([torch.cat(u_p_list) for group_name, params in param_groups_map.items() for i, p in enumerate(params)]) |
| if all_gt.norm() > 0 and all_gp.norm() > 0: |
| grad_cos_sim = float(F.cosine_similarity(all_gt.unsqueeze(0), all_gp.unsqueeze(0))) |
| parasitic_ratio = float(all_gp.norm() / (all_gt.norm() + 1e-7)) |
|
|
| self.gaussians.optimizer.zero_grad(set_to_none=True) |
| loss.backward() |
| else: |
| loss.backward() |
|
|
| with torch.no_grad(): |
| if step < self.opt.update_until and step > self.opt.start_stat: |
| self.gaussians.training_statis(viewspace_point_tensor, opacity, visibility_filter, offset_selection_mask, voxel_visible_mask) |
| if step not in range(3000, 4000): |
| if step > self.opt.update_from and step % self.opt.update_interval == 0: |
| self.gaussians.adjust_anchor(check_interval=self.opt.update_interval, success_threshold=self.opt.success_threshold, grad_threshold=self.opt.densify_grad_threshold, min_opacity=self.opt.min_opacity) |
| elif step == self.opt.update_until: |
| del self.gaussians.opacity_accum |
| del self.gaussians.offset_gradient_accum |
| del self.gaussians.offset_denom |
| torch.cuda.empty_cache() |
|
|
| if step < self.opt.iterations: |
| self.gaussians.optimizer.step() |
| self.gaussians.optimizer.zero_grad(set_to_none=True) |
|
|
| num_gaussians = self.gaussians.get_anchor.shape[0] |
| metrics = { |
| "loss": float(loss), "loss_l1": float(loss_target), "loss_ssim": float(loss_parasitic), |
| "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)), |
| "grad_cos_sim": float(grad_cos_sim), "parasitic_ratio": float(parasitic_ratio) |
| } |
| metrics.update(stats) |
| |
| if bit_per_param is not None: |
| metrics["bit_per_param"] = float(bit_per_param) |
| |
| self.last_n_gaussians = num_gaussians |
| |
| histograms = {} |
| if step % 1000 == 0: |
| histograms["opacity"] = torch.sigmoid(self.gaussians._opacity).clone().detach() |
| scales = self.gaussians.get_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["anchor_feat_mag"] = self.gaussians._anchor_feat.detach().norm(dim=-1) |
|
|
| return metrics, histograms |
|
|
| def render(self, camera): |
| with torch.no_grad(): |
| voxel_visible_mask = prefilter_voxel(camera, self.gaussians, self.pipe, self.background) |
| render_pkg = native_render(camera, self.gaussians, self.pipe, self.background, visible_mask=voxel_visible_mask) |
| 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_sparse_gaussian(os.path.join(model_path, 'point_cloud', f'iteration_{iteration}', 'point_cloud.ply')) |
|
|
| def get_spatial_centers(self): |
| return self.gaussians.get_anchor |
|
|
| def compute_physical_metrics(self, cameras=None): |
| metrics = {} |
| with torch.no_grad(): |
| scales = self.gaussians.get_scaling |
| 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))) |
| |
| feat, hyper = self.gaussians._anchor_feat, self.gaussians._hyper_latent |
| if hyper is not None and hyper.shape[1] > 0: |
| metrics["hyper_energy_ratio"] = float(hyper.norm(dim=-1).mean() / (feat.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 = self.gaussians.get_anchor |
| opacities = torch.sigmoid(self.gaussians._opacity).squeeze() |
| scales = self.gaussians.get_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 |
|
|
|
|
