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
defrender(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")+0try:
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 =Noneif 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 =Noneif override_color isNone: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}