4k citations · 4.2k across the 8 of their papers we have counts for
12 papers
Compact Neural Graphics Primitives with Learned Hash Probing
Towaki Takikawa, Thomas Müller, Merlin Nimier-David +4
Neural graphics primitives are faster and achieve higher quality when their neural networks are augmented by spatial data structures that hold trainable features arranged in a grid…
Variable Bitrate Neural Fields
Towaki Takikawa, Alex Evans, Jonathan Tremblay +4
Neural approximations of scalar and vector fields, such as signed distance functions and radiance fields, have emerged as accurate, high-quality representations. State-of-the-art r…
RTMV: A Ray-Traced Multi-View Synthetic Dataset for Novel View Synthesis
Jonathan Tremblay, Moustafa Meshry, Alex Evans +9
We present a large-scale synthetic dataset for novel view synthesis consisting of ~300k images rendered from nearly 2000 complex scenes using high-quality ray tracing at high resol…
Instant Neural Graphics Primitives with a Multiresolution Hash Encoding
Thomas Müller, Alex Evans, Christoph Schied +1
Neural graphics primitives, parameterized by fully connected neural networks, can be costly to train and evaluate. We reduce this cost with a versatile new input encoding that perm…
Path Guiding Using Spatio-Directional Mixture Models
Ana Dodik, Marios Papas, Cengiz Öztireli +1
We propose a learning-based method for light-path construction in path tracing algorithms, which iteratively optimizes and samples from what we refer to as spatio-directional Gauss…
Extracting Triangular 3D Models, Materials, and Lighting From Images
Jacob Munkberg, Jon Hasselgren, Tianchang Shen +5
We present an efficient method for joint optimization of topology, materials and lighting from multi-view image observations. Unlike recent multi-view reconstruction approaches, wh…