A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
Viewformer is a NeRF-free neural rendering method that uses transformers to synthesize novel views from few sparsely covering context images.
Unknown
Neutex introduces neural texture mapping for volumetric neural rendering, enabling realistic image synthesis by leveraging volumetric neural rendering techniques.
Unknown
Kaleido introduces a family of generative models for photorealistic, unified object- and scene-level neural rendering by treating 3D as a sequence-to-sequence problem.
Unknown
FreeNeRF introduces free frequency regularization to improve few-shot neural rendering by addressing frequency-related challenges in NeRF training.
Noah Snavely, Steven M. Seitz, Richard Szeliski
Presents a system for interactively browsing and exploring large unstructured photo collections using a novel 3D interface with image-based modeling and rendering.
Lukas Radl, Michael Steiner, Mathias Parger, et al.
StopThePop introduces a hierarchical rasterization approach for 3D Gaussian Splatting that eliminates popping artifacts and view inconsistencies with minimal overhead, enabling faster rendering and reduced memory.
Matthias Zwicker, Jussi Räsänen, Mario Botsch, et al.
A novel point rendering algorithm using homogeneous coordinates for perspective-correct splatting with EWA filtering and GPU implementation.
Mark Bentum, Barthold Lichtenbelt, Thomas Malzbender
This paper presents a frequency analysis of gradient estimators in volume rendering and introduces a new gradient filter based on the derivative of the interpolation filter, such as the cubic spline, for improved accuracy and computational efficiency
Matthias Zwicker, Hanspeter Pfister, Jeroen van Baar, et al.
EWA splatting introduces a resampling filter framework using elliptical Gaussian kernels for high-quality, alias-free rendering of volume and point-sampled surface data.
Justus Thies, Michael Zollhöfer, Matthias Nießner
Introduces Deferred Neural Rendering with Neural Textures, combining traditional graphics pipelines with learnable components to synthesize photo-realistic images from imperfect 3D content.
Unknown
GaussianPro introduces progressive propagation to improve 3D Gaussian Splatting's rendering quality and robustness when initial point clouds are sparse or incomplete.
Unknown
This paper introduces a generalizable patch-based neural rendering method that synthesizes novel views from sparse input images without per-scene optimization.