Differentiable Point-Based Radiance Fields for Efficient View Synthesis
This work addresses the computational and memory bottlenecks in view synthesis for computer vision and graphics applications, offering a significant efficiency improvement over existing methods.
The paper tackles the problem of inefficient novel view synthesis by proposing a differentiable rendering algorithm that uses a learned point representation instead of volume-based methods, achieving up to 300x faster training and inference than NeRF with minimal quality loss and less than 10 MB memory for static scenes.
We propose a differentiable rendering algorithm for efficient novel view synthesis. By departing from volume-based representations in favor of a learned point representation, we improve on existing methods more than an order of magnitude in memory and runtime, both in training and inference. The method begins with a uniformly-sampled random point cloud and learns per-point position and view-dependent appearance, using a differentiable splat-based renderer to evolve the model to match a set of input images. Our method is up to 300x faster than NeRF in both training and inference, with only a marginal sacrifice in quality, while using less than 10~MB of memory for a static scene. For dynamic scenes, our method trains two orders of magnitude faster than STNeRF and renders at near interactive rate, while maintaining high image quality and temporal coherence even without imposing any temporal-coherency regularizers.