CVMar 24, 2022

NPBG++: Accelerating Neural Point-Based Graphics

arXiv:2203.13318v110 citationsh-index: 64
Originality Incremental advance
AI Analysis

This work addresses the problem of efficient and realistic view synthesis for computer graphics applications, representing an incremental improvement over prior neural point-based methods.

The paper tackles novel view synthesis by introducing NPBG++, a system that accelerates rendering with high realism and low scene fitting time, achieving similar image quality to previous methods while reducing fitting and rendering runtimes.

We present a new system (NPBG++) for the novel view synthesis (NVS) task that achieves high rendering realism with low scene fitting time. Our method efficiently leverages the multiview observations and the point cloud of a static scene to predict a neural descriptor for each point, improving upon the pipeline of Neural Point-Based Graphics in several important ways. By predicting the descriptors with a single pass through the source images, we lift the requirement of per-scene optimization while also making the neural descriptors view-dependent and more suitable for scenes with strong non-Lambertian effects. In our comparisons, the proposed system outperforms previous NVS approaches in terms of fitting and rendering runtimes while producing images of similar quality.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes