From the Industry: Selected Papers
A curated list of recent papers and relevant publications
Practical Pigment Mixing for Digital Painting
Šárka Sochorová, Ondřej Jamriška
"In this paper, we introduce a practical approach that enables mixing colors with K–M while keeping everything in RGB. We achieve this by establishing a latent color space, where RGB colors are represented as mixtures of primary pigments together with additive residuals. The latents can be manipulated with linear operations, leading to expected, plausible results."
Orientation Keypoints for 6D Human Pose Estimation
Martin Fisch, Ronald Clark
Inspired by how motion-capture systems use a set of point markers to estimate full bone rotations, this method uses virtual markers to generate sufficient information to accurately infer rotations with simple post processing.
Deep Lighting Environment Map Estimation from Spherical Panoramas
Vasilis Gkitsas, Nikolaos Zioulis, Federico Alvarez, Dimitrios Zarpalas, Petros Daras
Using the uncoupled limited Laval HDR lighting dataset and the larger 3D60 color and normal dataset jointly, coupling them through relighting in order to learn a single-shot HDR lighting estimator from a single LDR spherical panorama.
FILM: Frame Interpolation for Large Motion
Fitsum Reda, Janne Kontkanen, Eric Tabellion, Deqing Sun, Caroline Pantofaru, Brian Curless
FILM turns near-duplicate photos into a slow motion footage that look like shot with a video camera.
Instant Neural Graphics Primitives with a Multiresolution Hash Encoding
Thomas Müller, Alex Evans, Christoph Schied, Alexander Keller
A small neural network is augmented by a multiresolution hash table of trainable feature vectors whose values are optimized through stochastic gradient descent. The multiresolution structure allows the network to disambiguate hash collisions, making for a simple architecture that is trivial to parallelize on modern GPUs.
Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields
Jonathan T. Barron, Ben Mildenhall, Dor Verbin
Presents an extension of mip-NeRF (a NeRF variant that addresses sampling and aliasing) that uses a non-linear scene parameterization, online distillation, and a novel distortion-based regularizer to overcome the challenges presented by unbounded scenes.
Extracting Triangular 3D Models, Materials, and Lighting From Images
Jacob Munkberg, Jon Hasselgren, Tianchang Shen, Jun Gao, Wenzheng Chen, Alex Evans, Thomas Müller, Sanja Fidler
Presents an efficient method for joint optimization of topology, materials and lighting from multi-view image observations
Get Started Now
Try Runway from right inside your browser. No downloads, no steep learning curves. Just pure creative experimentation. What will you make with Runway?
START CREATING NOW