Neural rendering methods have significantly advanced photo-realistic 3D scene rendering in various academic and industrial applications. The recent 3D Gaussian Splatting method …
Z Chen, Z Li, L Song, L Chen, J Yu… - Proceedings of the …, 2023 - openaccess.thecvf.com
We present a novel type of neural fields that uses general radial bases for signal representation. State-of-the-art neural fields typically rely on grid-based representations for …
Accurately and efficiently modeling dynamic scenes and motions is considered so challenging a task due to temporal dynamics and motion complexity. To address these …
We propose Strivec, a novel neural representation that models a 3D scene as a radiance field with sparsely distributed and compactly factorized local tensor feature grids. Our …
J Kulhanek, T Sattler - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
Abstract Neural Radiance Fields (NeRFs) are a very recent and very popular approach for the problems of novel view synthesis and 3D reconstruction. A popular scene representation …
We propose GS-LRM, a scalable large reconstruction model that can predict high-quality 3D Gaussian primitives from 2–4 posed sparse images in\(\sim\) 0.23 s on single A100 GPU …
R Shi, X Wei, C Wang, H Su - Proceedings of the IEEE/CVF …, 2024 - openaccess.thecvf.com
We present ZeroRF a novel per-scene optimization method addressing the challenge of sparse view 360deg reconstruction in neural field representations. Current breakthroughs …
Motion magnification helps us visualize subtle, imperceptible motion. However, prior methods only work for 2D videos captured with a fixed camera. We present a 3D motion …
B Yi, W Zeng, S Buchanan… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Factored feature volumes offer a simple way to build more compact, efficient, and intepretable neural fields, but also introduce biases that are not necessarily beneficial for …