MixRT: Mixed Neural Representations For Real-Time NeRF Rendering
This work addresses the problem of real-time rendering for NeRF applications on edge devices, offering an incremental improvement over existing methods.
The paper tackles the challenge of achieving real-time NeRF rendering in large-scale scenes by proposing MixRT, a mixed representation combining a low-quality mesh, view-dependent displacement map, and compressed NeRF model, which enables over 30 FPS at 1280x720 resolution on edge devices with better rendering quality and smaller storage size.
Neural Radiance Field (NeRF) has emerged as a leading technique for novel view synthesis, owing to its impressive photorealistic reconstruction and rendering capability. Nevertheless, achieving real-time NeRF rendering in large-scale scenes has presented challenges, often leading to the adoption of either intricate baked mesh representations with a substantial number of triangles or resource-intensive ray marching in baked representations. We challenge these conventions, observing that high-quality geometry, represented by meshes with substantial triangles, is not necessary for achieving photorealistic rendering quality. Consequently, we propose MixRT, a novel NeRF representation that includes a low-quality mesh, a view-dependent displacement map, and a compressed NeRF model. This design effectively harnesses the capabilities of existing graphics hardware, thus enabling real-time NeRF rendering on edge devices. Leveraging a highly-optimized WebGL-based rendering framework, our proposed MixRT attains real-time rendering speeds on edge devices (over 30 FPS at a resolution of 1280 x 720 on a MacBook M1 Pro laptop), better rendering quality (0.2 PSNR higher in indoor scenes of the Unbounded-360 datasets), and a smaller storage size (less than 80% compared to state-of-the-art methods).