We introduce OpenIllumination, a real-world dataset containing over 108K...
We introduce a theoretical framework for differentiable surface evolutio...
Neural Radiance Fields or NeRFs have become the representation of choice...
Precomputed Radiance Transfer (PRT) remains an attractive solution for
r...
Portrait synthesis creates realistic digital avatars which enable users ...
We present a one-shot method to infer and render a photorealistic 3D
rep...
Inverse path tracing has recently been applied to joint material and lig...
We propose a set of techniques to efficiently importance sample the
deri...
Under ray-optical light transport, the classical ray serves as a local a...
Novel view synthesis from a single image requires inferring occluded reg...
Monte Carlo rendering algorithms often utilize correlations between pixe...
Although neural radiance fields (NeRF) have shown impressive advances fo...
We present a method to edit complex indoor lighting from a single image ...
Coordinate-based neural networks parameterizing implicit surfaces have
e...
Blue noise error patterns are well suited to human perception, and when
...
Recently neural volumetric representations such as neural reflectance fi...
Image view synthesis has seen great success in reconstructing photoreali...
Human portraits exhibit various appearances when observed from different...
Multi-Layer Perceptrons (MLPs) make powerful functional representations ...
We propose NeuMIP, a neural method for representing and rendering a vari...
The light stage has been widely used in computer graphics for the past t...
Although Monte Carlo path tracing is a simple and effective algorithm to...
We propose a novel real-time selfie video stabilization method. Our meth...
We present Neural Reflectance Fields, a novel deep scene representation ...
The light transport (LT) of a scene describes how it appears under diffe...
We propose a learning-based approach for novel view synthesis for
multi-...
Large-scale photorealistic datasets of indoor scenes, with ground truth
...
We present a deep learning approach to reconstruct scene appearance from...
We show that passing input points through a simple Fourier feature mappi...
Recently, deep learning-based denoising approaches have led to dramatic
...
We present a method to improve the visual realism of low-quality, synthe...
We introduce a novel learning-based method to reconstruct the high-quali...
We present a method that achieves state-of-the-art results for synthesiz...
We present Uncertainty-aware Cascaded Stereo Network (UCS-Net) for 3D
re...
We propose a deep inverse rendering framework for indoor scenes. From a
...
We present a practical and robust deep learning solution for capturing a...
Lighting plays a central role in conveying the essence and depth of the
...
We explore the problem of view synthesis from a narrow baseline pair of
...
Restoring a sharp light field image from its blurry input has become
ess...
Intrinsic image decomposition is the process of separating the reflectan...
We propose a general framework for unsupervised domain adaptation, which...
In this paper we present a differential approach to photo-polarimetric s...
We present a machine learning algorithm that takes as input a 2D RGB ima...
Light field cameras have many advantages over traditional cameras, as th...
We study the problem of deblurring light fields of general 3D scenes cap...
With the introduction of consumer light field cameras, light field imagi...
We introduce a new light-field dataset of materials, and take advantage ...