Automatic 3D content creation has achieved rapid progress recently due to the availability of
pre-trained, large language models and image diffusion models, forming the emerging topic …

Decomposing a scene into its shape, reflectance, and illumination is a challenging but
important problem in computer vision and graphics. This problem is inherently more …

Decomposing a scene into its shape, reflectance and illumination is a fundamental problem
in computer vision and graphics. Neural approaches such as NeRF have achieved …

The advent of neural 3D Gaussians has recently brought about a revolution in the field of
neural rendering facilitating the generation of high-quality renderings at real-time speeds …

Creation of 3D content by stylization is a promising yet challenging problem in computer
vision and graphics research. In this work, we focus on stylizing photorealistic appearance …

Gradient-based methods are becoming increasingly important for computer graphics,
machine learning, and computer vision. The ability to compute gradients is crucial to …

We present Neural Reflectance Fields, a novel deep scene representation that encodes
volume density, normal and reflectance properties at any 3D point in a scene using a fully …

Inverse rendering of an object under entirely unknown capture conditions is a fundamental
challenge in computer vision and graphics. Neural approaches such as NeRF have …

Abstract We propose Deep Feature Interpolation (DFI), a new data-driven baseline for
automatic high-resolution image transformation. As the name suggests, DFI relies only on …

Reconstructing shape and reflectance properties from images is a highly under-constrained
problem, and has previously been addressed by using specialized hardware to capture …