rt-octree.github.io - RT-Octree: Accelerate PlenOctree Rendering with Batched Regular Tracking and Neural Denoising for Real-time Neural Radiance Fiel

home > domains > rt-octree.github.io

Description: RT-Octree: Accelerate PlenOctree Rendering with Batched Regular Tracking and Neural Denoising for Real-time Neural Radiance Fields

nerf (138) rt-octree (1) plenoctree (1)

Example domain paragraphs

Neural Radiance Fields (NeRF) has demonstrated its ability to generate high-quality synthesized views. Nonetheless, due to its slow inference speed, there is a need to explore faster inference methods. In this paper, we propose RT-Octree, which uses batched regular tracking based on PlenOctree with neural denoising to achieve better real-time performance. We achieve this by modifying the volume rendering algorithm to regular tracking. We batch all samples for each pixel in one single ray-voxel intersection

Using nerfies you can create fun visual effects. This Dolly zoom effect would be impossible without nerfies since it would require going through a wall.

As a byproduct of our method, we can also solve the matting problem by ignoring samples that fall outside of a bounding box during rendering.

Links to rt-octree.github.io (1)

• yiranran.github.io Ran Yi