Visualize 3D Gaussian splatting

[ssheorey]

3D Gaussian splatting is a novel 3D representation that enables fast scene reconstruction and real time photorealistic rendering. We are adding support for 3DGS in Open3D. As part of that, we also want to add the ability to render 3DGS scenes.

Steps:

1. Study the Open3D visualizer and GLSL shaders used.
2. Update visualizer to call a SPIR-V shader directly with ARB_gl_SPIRV.
3. Use 3DGS SYCL rendering kernels from the [isl-org gsplat fork](https://github.com/isl-org/gsplat) to render 3DGS scenes.
4. Add Python binding.

Tests:

• Load these Numpy files and display scene. Compare with reference gsplat viewer.

Open3D Tensor point cloud representation:

• pcd.point[‘positions’] (N,3) – (x,y,z) for each splat.
• pcd.point[‘opacity’] – (N,) opacity
• pcd.point[‘rot’] (N, 4) - quaternion rotation of Gaussian.
• pcd.point[‘scale'] (N, 3) - x, y, z scales for Gaussian.
• pcd.point[‘f_dc’] (N, 3) – DC components for RGB colors.
• pcd.point[‘f_rest’] (N, Nc, 3) – SH coeffs for RGB colors. (Nc = 4, 9 or 16)

Reference:

• Reference viewer: https://projects.markkellogg.org/threejs/demo_gaussian_splats_3d.php