Binary opacity grids: Capturing fine geometric detail for mesh-based view synthesis

C Reiser, S Garbin, P Srinivasan, D Verbin… - ACM Transactions on …, 2024 - dl.acm.org
While surface-based view synthesis algorithms are appealing due to their low computational
requirements, they often struggle to reproduce thin structures. In contrast, more expensive …

Smerf: Streamable memory efficient radiance fields for real-time large-scene exploration

D Duckworth, P Hedman, C Reiser, P Zhizhin… - ACM Transactions on …, 2024 - dl.acm.org
Recent techniques for real-time view synthesis have rapidly advanced in fidelity and speed,
and modern methods are capable of rendering near-photorealistic scenes at interactive …

3D Gaussian Ray Tracing: Fast Tracing of Particle Scenes

N Moenne-Loccoz, A Mirzaei, O Perel… - ACM Transactions on …, 2024 - dl.acm.org
Particle-based representations of radiance fields such as 3D Gaussian Splatting have found
great success for reconstructing and re-rendering of complex scenes. Most existing methods …

Gaussian frosting: Editable complex radiance fields with real-time rendering

A Guédon, V Lepetit - European Conference on Computer Vision, 2024 - Springer
Abstract We propose Gaussian Frosting, a novel mesh-based representation for high-quality
rendering and editing of complex 3D effects in real-time. Our approach builds on the recent …

Generalizable human gaussians for sparse view synthesis

Y Kwon, B Fang, Y Lu, H Dong, C Zhang… - … on Computer Vision, 2024 - Springer
Recent progress in neural rendering has brought forth pioneering methods, such as NeRF
and Gaussian Splatting, which revolutionize view rendering across various domains like …

What You See is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANs

A Trevithick, M Chan, T Takikawa… - Proceedings of the …, 2024 - openaccess.thecvf.com
Abstract 3D-aware Generative Adversarial Networks (GANs) have shown remarkable
progress in learning to generate multi-view-consistent images and 3D geometries of scenes …

Neurodin: A two-stage framework for high-fidelity neural surface reconstruction

Y Wang, D Huang, W Ye, G Zhang, W Ouyang… - arxiv preprint arxiv …, 2024 - arxiv.org
Signed Distance Function (SDF)-based volume rendering has demonstrated significant
capabilities in surface reconstruction. Although promising, SDF-based methods often fail to …

Magicclay: Sculpting meshes with generative neural fields

A Barda, V Kim, N Aigerman, AH Bermano… - SIGGRAPH Asia 2024 …, 2024 - dl.acm.org
The recent developments in neural fields have brought phenomenal capabilities to the field
of shape generation, but they lack crucial properties, such as incremental control—a …

Livescene: Language embedding interactive radiance fields for physical scene rendering and control

D Qu, Q Chen, P Zhang, X Gao, B Zhao… - arxiv preprint arxiv …, 2024 - arxiv.org
This paper scales object-level reconstruction to complex scenes, advancing interactive
scene reconstruction. We introduce two datasets, OmniSim and InterReal, featuring 28 …

Volumetric rendering with baked quadrature fields

G Sharma, D Rebain, KM Yi, A Tagliasacchi - European Conference on …, 2024 - Springer
We propose a novel Neural Radiance Field (NeRF) representation for non-opaque scenes
that enables fast inference by utilizing textured polygons. Despite the high-quality novel view …