MERF: Memory-Efficient Radiance Fields for Real-time View Synthesis in Unbounded Scenes
This enables real-time view synthesis for large, unbounded scenes, addressing a bottleneck for applications like virtual reality or interactive graphics, though it is incremental in improving efficiency over existing methods.
The paper tackles the problem of high memory consumption and computational intensity in neural radiance fields for large-scale scenes, achieving real-time rendering in a browser with reduced memory usage while preserving photorealistic quality.
Neural radiance fields enable state-of-the-art photorealistic view synthesis. However, existing radiance field representations are either too compute-intensive for real-time rendering or require too much memory to scale to large scenes. We present a Memory-Efficient Radiance Field (MERF) representation that achieves real-time rendering of large-scale scenes in a browser. MERF reduces the memory consumption of prior sparse volumetric radiance fields using a combination of a sparse feature grid and high-resolution 2D feature planes. To support large-scale unbounded scenes, we introduce a novel contraction function that maps scene coordinates into a bounded volume while still allowing for efficient ray-box intersection. We design a lossless procedure for baking the parameterization used during training into a model that achieves real-time rendering while still preserving the photorealistic view synthesis quality of a volumetric radiance field.