Search Results for author:
Found 28 papers, 13 papers with code
The Sky's the Limit: Re-lightable Outdoor Scenes via a Sky-pixel Constrained Illumination Prior and Outside-In Visibility
We also introduce a novel `outside-in' method for computing differentiable sky visibility based on a neural directional distance function.
RENI++ A Rotation-Equivariant, Scale-Invariant, Natural Illumination Prior
Training our model on a curated dataset of 1. 6K HDR environment maps of natural scenes, we compare it against traditional representations, demonstrate its applicability for an inverse rendering task and show environment map completion from partial observations.
ID2image: Leakage of non-ID information into face descriptors and inversion from descriptors to images
Information about the environment (such as background and lighting) or changeable aspects of the face (such as pose, expression, presence of glasses, hat etc.)
If At First You Don't Succeed: Test Time Re-ranking for Zero-shot, Cross-domain Retrieval
In this paper we propose a novel method for zero-shot, cross-domain image retrieval in which we make two key contributions.
Neural apparent BRDF fields for multiview photometric stereo
We propose to tackle the multiview photometric stereo problem using an extension of Neural Radiance Fields (NeRFs), conditioned on light source direction.
Rotation-Equivariant Conditional Spherical Neural Fields for Learning a Natural Illumination Prior
Training our model on a curated dataset of 1. 6K HDR environment maps of natural scenes, we compare it against traditional representations, demonstrate its applicability for an inverse rendering task and show environment map completion from partial observations.
Self-supervised Outdoor Scene Relighting
Outdoor scene relighting is a challenging problem that requires good understanding of the scene geometry, illumination and albedo.
Outdoor inverse rendering from a single image using multiview self-supervision
In this paper we show how to perform scene-level inverse rendering to recover shape, reflectance and lighting from a single, uncontrolled image using a fully convolutional neural network.
Least squares surface reconstruction on arbitrary domains
Almost universally in computer vision, when surface derivatives are required, they are computed using only first order accurate finite difference approximations.
A Morphable Face Albedo Model
In this paper, we bring together two divergent strands of research: photometric face capture and statistical 3D face appearance modelling.
Towards a complete 3D morphable model of the human head
Eye and eye region models are incorporated into the head model, along with basic models of the teeth, tongue and inner mouth cavity.
3D Morphable Face Models -- Past, Present and Future
In this paper, we provide a detailed survey of 3D Morphable Face Models over the 20 years since they were first proposed.
Depth from a polarisation + RGB stereo pair
In this paper, we propose a hybrid depth imaging system in which a polarisation camera is augmented by a second image from a standard digital camera.
Combining 3D Morphable Models: A Large scale Face-and-Head Model
Three-dimensional Morphable Models (3DMMs) are powerful statistical tools for representing the 3D surfaces of an object class.
Decomposing multispectral face images into diffuse and specular shading and biophysical parameters
We propose a novel biophysical and dichromatic reflectance model that efficiently characterises spectral skin reflectance.
InverseRenderNet: Learning single image inverse rendering
By incorporating a differentiable renderer, our network can learn from self-supervision.
Statistical transformer networks: learning shape and appearance models via self supervision
In this configuration, our model learns an active appearance model and a means to fit the model from scratch with no supervision at all, even identity labels.
A 3D Morphable Model of Craniofacial Shape and Texture Variation
We present a fully automatic pipeline to train 3D Morphable Models (3DMMs), with contributions in pose normalisation, dense correspondence using both shape and texture information, and high quality, high resolution texture mapping.
Linear Differential Constraints for Photo-polarimetric Height Estimation
From a numerical point of view, we use a least-squares formulation of the discrete version of the problem.
3D Morphable Models as Spatial Transformer Networks
In this paper, we show how a 3D Morphable Model (i. e. a statistical model of the 3D shape of a class of objects such as faces) can be used to spatially transform input data as a module (a 3DMM-STN) within a convolutional neural network.
What does 2D geometric information really tell us about 3D face shape?
We show that this is not the case and that geometric information is an ambiguous cue.
BRISKS: Binary Features for Spherical Images on a Geodesic Grid
For interest point detection, we use a variant of the Accelerated Segment Test (AST) corner detector which operates on our geodesic grid.
Ear-to-ear Capture of Facial Intrinsics
We present a practical approach to capturing ear-to-ear face models comprising both 3D meshes and intrinsic textures (i. e. diffuse and specular albedo).
Functional Faces: Groupwise Dense Correspondence Using Functional Maps
In this paper we present a method for computing dense correspondence between a set of 3D face meshes using functional maps.
Fitting a 3D Morphable Model to Edges: A Comparison Between Hard and Soft Correspondences
We propose a fully automatic method for fitting a 3D morphable model to single face images in arbitrary pose and lighting.
Example-Based Modeling of Facial Texture From Deficient Data
We present an approach to modeling ear-to-ear, high-quality texture from one or more partial views of a face with possibly poor resolution and noise.
Shell PCA: Statistical Shape Modelling in Shell Space
In this paper we describe how to perform Principal Components Analysis in "shell space".
