Related papers: Deep Dynamic Cloud Lighting
By analyzing the motion of people and other objects in a scene, we demonstrate how to infer depth, occlusion, lighting, and shadow information from video taken from a single camera viewpoint. This information is then used to composite new…
Atmospheric turbulence, a common phenomenon in daily life, is primarily caused by the uneven heating of the Earth's surface. This phenomenon results in distorted and blurred acquired images or videos and can significantly impact downstream…
Sunlight and shadow play critical roles in how urban spaces are utilized, thrive, and grow. While access to sunlight is essential to the success of urban environments, shadows can provide shaded places to stay during the hot seasons,…
Lighting has a strong influence on visual appearance, yet understanding and representing lighting in images remains notoriously difficult. Various lighting representations exist, such as environment maps, irradiance, spherical harmonics, or…
Variability in the sky has been known for centuries, even millennia, but our knowledge of it is very incomplete even at the bright end. Current technology makes it possible to built small, robotic optical instruments, to record images and…
Cloud microphysical parameterizations in atmospheric models describe the formation and evolution of clouds and precipitation, a central weather and climate process. Cloud-associated latent heating is a primary driver of large and…
Generating realistic shadows for inserted objects requires reasoning about scene geometry and illumination. However, most existing methods operate purely in image space, leaving the physical relationship between objects, lighting, and…
Point cloud synthesis, i.e. the generation of novel point clouds from an input distribution, remains a challenging task, for which numerous complex machine learning models have been devised. We develop a novel method that encodes…
Moving clouds affect the global solar irradiance that reaches the surface of the Earth. As a consequence, the amount of resources available to meet the energy demand in a smart grid powered using Photovoltaic (PV) systems depends on the…
The advancement of generative radiance fields has pushed the boundary of 3D-aware image synthesis. Motivated by the observation that a 3D object should look realistic from multiple viewpoints, these methods introduce a multi-view constraint…
We present a deep learning solution for estimating the incident illumination at any 3D location within a scene from an input narrow-baseline stereo image pair. Previous approaches for predicting global illumination from images either…
There have been significant advancements in dynamic novel view synthesis in recent years. However, current deep learning models often require (1) prior models (e.g., SMPL human models), (2) heavy pre-processing, or (3) per-scene…
Synthesizing a densely sampled light field from a single image is highly beneficial for many applications. The conventional method reconstructs a depth map and relies on physical-based rendering and a secondary network to improve the…
The mass and size distributions are the key characteristics of any astrophysical objects, including the densest clumps comprising the cold phase of multiphase environments. In our recent papers, we showed how individual clouds of various…
Outdoor scene relighting is a challenging problem that requires good understanding of the scene geometry, illumination and albedo. Current techniques are completely supervised, requiring high quality synthetic renderings to train a…
Unbiased sky background modeling is crucial for the analysis of deep wide-field images, but it remains a major challenge in low surface brightness astronomy. Traditional image processing algorithms are often designed to produce artificially…
Creating relightable urban scenes from images or videos is widely useful but highly ill-posed. Urban environments are typically unbounded and extend beyond the visible regions. As a result, many portions of the scene remain unobserved, yet…
In recent years, 3D vision has become a crucial field within computer vision, powering a wide range of applications such as autonomous driving, robotics, augmented reality, and medical imaging. This field relies on accurate perception,…
Novel view synthesis from an in-the-wild video is difficult due to challenges like scene dynamics and lack of parallax. While existing methods have shown promising results with implicit neural radiance fields, they are slow to train and…
Scene synthesis is a challenging problem with several industrial applications. Recently, substantial efforts have been directed to synthesize the scene using human motions, room layouts, or spatial graphs as the input. However, few studies…