Many computer vision techniques infer properties of our physical world from images.
Although images are formed through the physics of light and mechanics, computer vision …

Existing inverse rendering combined with neural rendering methods can only perform
editable novel view synthesis on object-specific scenes, while we present intrinsic neural …

Intrinsic imaging or intrinsic image decomposition has traditionally been described as the
problem of decomposing an image into two layers: a reflectance, the albedo invariant color …

We present a method to automatically compute correct gradients with respect to geometric
scene parameters in neural SDF renderers. Recent physically-based differentiable …

Abstract Learning from Demonstration (LfD) is an efficient technique for robots to acquire
new skills through expert observation, significantly mitigating the need for laborious manual …

Model-based reinforcement learning is recognized with the potential to be significantly more
sample efficient than model-free reinforcement learning. How an accurate model can be …

In the past decades, Monte Carlo methods have shown their ability to solve PDEs,
independently of the dimensionality of the integration domain and for different use-cases (eg …

Bokeh is widely used in photography to draw attention to the subject while effectively
isolating distractions in the background. Computational methods can simulate bokeh effects …

Computing the gradients of a rendering process is paramount for diverse applications in
computer vision and graphics. However, accurate computation of these gradients is …

Node-graph-based procedural materials are vital to 3D content creation within the computer
graphics industry. Leveraging the expressive representation of procedural materials, artists …