代码记录：3D Gaussian Splatting 渲染(Rendering)代码

前言

• 3D GS的渲染部分(从3D Gaussian 到 2D image)本应该是整个框架中最重要的部分，但是由于具体是通过Cuda编程实现，而作者也已经把这部分包装成了库，调用即可，因此，我们首先来看看3D GS代码中如何安排这部分的代码来进行渲染。
• 渲染的过程是将3D Gaussian 点云投影到2D平面上生成渲染的图像。

位置

• render函数位于gaussian_renderer\ __init__.py

源码

def render(viewpoint_camera, pc : GaussianModel, pipe, bg_color : torch.Tensor, scaling_modifier = 1.0, override_color = None):
    """
    Render the scene. 
    
    Background tensor (bg_color) must be on GPU!
    """
 
    # Create zero tensor. We will use it to make pytorch return gradients of the 2D (screen-space) means
    screenspace_points = torch.zeros_like(pc.get_xyz, dtype=pc.get_xyz.dtype, requires_grad=True, device="cuda") + 0
    try:
        screenspace_points.retain_grad()
    except:
        pass

    # Set up rasterization configuration
    tanfovx = math.tan(viewpoint_camera.FoVx * 0.5)
    tanfovy = math.tan(viewpoint_camera.FoVy * 0.5)

    raster_settings = GaussianRasterizationSettings(
        image_height=int(viewpoint_camera.image_height),
        image_width=int(viewpoint_camera.image_width),
        tanfovx=tanfovx,
        tanfovy=tanfovy,
        bg=bg_color,
        scale_modifier=scaling_modifier,
        viewmatrix=viewpoint_camera.world_view_transform,
        projmatrix=viewpoint_camera.full_proj_transform,
        sh_degree=pc.active_sh_degree,
        campos=viewpoint_camera.camera_center,
        prefiltered=False,
        debug=pipe.debug
    )

    rasterizer = GaussianRasterizer(raster_settings=raster_settings)

    means3D = pc.get_xyz
    means2D = screenspace_points
    opacity = pc.get_opacity

    # If precomputed 3d covariance is provided, use it. If not, then it will be computed from
    # scaling / rotation by the rasterizer.
    scales = None
    rotations = None
    cov3D_precomp = None
    if pipe.compute_cov3D_python:
        cov3D_precomp = pc.get_covariance(scaling_modifier)
    else:
        scales = pc.get_scaling
        rotations = pc.get_rotation

    # If precomputed colors are provided, use them. Otherwise, if it is desired to precompute colors
    # from SHs in Python, do it. If not, then SH -> RGB conversion will be done by rasterizer.
    shs = None
    colors_precomp = None
    if override_color is None:
        if pipe.convert_SHs_python:
            shs_view = pc.get_features.transpose(1, 2).view(-1, 3, (pc.max_sh_degree+1)**2)
            dir_pp = (pc.get_xyz - viewpoint_camera.camera_center.repeat(pc.get_features.shape[0], 1))
            dir_pp_normalized = dir_pp/dir_pp.norm(dim=1, keepdim=True)
            sh2rgb = eval_sh(pc.active_sh_degree, shs_view, dir_pp_normalized)
            colors_precomp = torch.clamp_min(sh2rgb + 0.5, 0.0)
        else:
            shs = pc.get_features
    else:
        colors_precomp = override_color

    # Rasterize visible Gaussians to image, obtain their radii (on screen). 
    rendered_image, radii = rasterizer(
        means3D = means3D,
        means2D = means2D,
        shs = shs,
        colors_precomp = colors_precomp,
        opacities = opacity,
        scales = scales,
        rotations = rotations,
        cov3D_precomp = cov3D_precomp)

    # Those Gaussians that were frustum culled or had a radius of 0 were not visible.
    # They will be excluded from value updates used in the splitting criteria.
    return {"render": rendered_image,
            "viewspace_points": screenspace_points,
            "visibility_filter" : radii > 0,
            "radii": radii}

输入参数

• viewpoint_camera: 要渲染的相机视角
• pc: 高斯模型对象
• pipe:
• bg_color: 背景颜色张量
• scaling_modifier: 缩放修正因子
• override_color: 覆盖颜色

输出参数

• rendered_image: 渲染出的图像
• screenspace_points:屏幕空间点
• visibility_filter:
• radii: 半径信息

具体分析：

screenspace_points = torch.zeros_like(pc.get_xyz, dtype=pc.get_xyz.dtype, requires_grad=True, device="cuda") + 0

• 屏幕空间中点的位置，screenspace_points的形状是(N,3)，N为高斯中的点的个数。

# Set up rasterization configuration
tanfovx = math.tan(viewpoint_camera.FoVx * 0.5)
tanfovy = math.tan(viewpoint_camera.FoVy * 0.5)

• 这里计算视场角在水平和垂直方向上的正切值。

raster_settings = GaussianRasterizationSettings(
    image_height=int(viewpoint_camera.image_height),
    image_width=int(viewpoint_camera.image_width),
    tanfovx=tanfovx,
    tanfovy=tanfovy,
    bg=bg_color,
    scale_modifier=scaling_modifier,
    viewmatrix=viewpoint_camera.world_view_transform,#外参
    projmatrix=viewpoint_camera.full_proj_transform,#内参
    sh_degree=pc.active_sh_degree,#球谐系数的阶数
    campos=viewpoint_camera.camera_center,#相机中心位置
    prefiltered=False,
    debug=pipe.debug #是否启用调试模式
)

rasterizer = GaussianRasterizer(raster_settings=raster_settings)

• 接下来就调用了库函数GaussianRasterizationSettings(…)设置栅格化的参数。然后创建rasterizer对象，用于将高斯分布投影到屏幕上。

rendered_image, radii = rasterizer(
    means3D = means3D,
    means2D = means2D,
    shs = shs,
    colors_precomp = colors_precomp,
    opacities = opacity,
    scales = scales,
    rotations = rotations,
    cov3D_precomp = cov3D_precomp)

• 最后进行渲染，生成渲染图像。