threestudio/models/renderers/nerf_volume_renderer.py [248:281]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            t_starts_, t_ends_ = self.estimator.sampling(
                prop_sigma_fns=[partial(prop_sigma_fn, proposal_network=self.geometry)],
                prop_samples=[self.cfg.num_samples_per_ray_importance],
                num_samples=self.cfg.num_samples_per_ray,
                n_rays=n_rays,
                near_plane=self.cfg.near_plane,
                far_plane=self.cfg.far_plane,
                sampling_type="uniform",
                stratified=self.randomized,
            )
            ray_indices = (
                torch.arange(n_rays, device=rays_o_flatten.device)
                .unsqueeze(-1)
                .expand(-1, t_starts_.shape[1])
            )
            ray_indices = ray_indices.flatten()
            t_starts_ = t_starts_.flatten()
            t_ends_ = t_ends_.flatten()
        else:
            raise NotImplementedError

        ray_indices, t_starts_, t_ends_ = validate_empty_rays(
            ray_indices, t_starts_, t_ends_
        )
        ray_indices = ray_indices.long()
        t_starts, t_ends = t_starts_[..., None], t_ends_[..., None]
        t_origins = rays_o_flatten[ray_indices]
        t_dirs = rays_d_flatten[ray_indices]
        t_light_positions = light_positions_flatten[ray_indices]
        t_positions = (t_starts + t_ends) / 2.0
        positions = t_origins + t_dirs * t_positions
        t_intervals = t_ends - t_starts

        if self.training:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



threestudio/models/renderers/neus_volume_renderer.py [223:256]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            t_starts_, t_ends_ = self.estimator.sampling(
                prop_sigma_fns=[partial(prop_sigma_fn, proposal_network=self.geometry)],
                prop_samples=[self.cfg.num_samples_per_ray_importance],
                num_samples=self.cfg.num_samples_per_ray,
                n_rays=n_rays,
                near_plane=self.cfg.near_plane,
                far_plane=self.cfg.far_plane,
                sampling_type="uniform",
                stratified=self.randomized,
            )
            ray_indices = (
                torch.arange(n_rays, device=rays_o_flatten.device)
                .unsqueeze(-1)
                .expand(-1, t_starts_.shape[1])
            )
            ray_indices = ray_indices.flatten()
            t_starts_ = t_starts_.flatten()
            t_ends_ = t_ends_.flatten()
        else:
            raise NotImplementedError

        ray_indices, t_starts_, t_ends_ = validate_empty_rays(
            ray_indices, t_starts_, t_ends_
        )
        ray_indices = ray_indices.long()
        t_starts, t_ends = t_starts_[..., None], t_ends_[..., None]
        t_origins = rays_o_flatten[ray_indices]
        t_dirs = rays_d_flatten[ray_indices]
        t_light_positions = light_positions_flatten[ray_indices]
        t_positions = (t_starts + t_ends) / 2.0
        positions = t_origins + t_dirs * t_positions
        t_intervals = t_ends - t_starts

        if self.training:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -