Point-Based Neural Rendering with Per-View Optimization
This work addresses the challenge of efficient and accurate neural rendering for applications like novel-view synthesis, multi-view harmonization, and stylization, representing an incremental advancement over existing approaches.
The paper tackles the problem of novel-view synthesis by introducing a method that initializes with Multi-View Stereo and optimizes scene properties per-view, resulting in improved quality and speed compared to previous methods.
There has recently been great interest in neural rendering methods. Some approaches use 3D geometry reconstructed with Multi-View Stereo (MVS) but cannot recover from the errors of this process, while others directly learn a volumetric neural representation, but suffer from expensive training and inference. We introduce a general approach that is initialized with MVS, but allows further optimization of scene properties in the space of input views, including depth and reprojected features, resulting in improved novel-view synthesis. A key element of our approach is our new differentiable point-based pipeline, based on bi-directional Elliptical Weighted Average splatting, a probabilistic depth test and effective camera selection. We use these elements together in our neural renderer, that outperforms all previous methods both in quality and speed in almost all scenes we tested. Our pipeline can be applied to multi-view harmonization and stylization in addition to novel-view synthesis.