Related papers: mitransient: Transient light transport in Mitsuba …
Although image-based virtual try-on has made considerable progress, emerging approaches still encounter challenges in producing high-fidelity and robust fitting images across diverse scenarios. These methods often struggle with issues such…
Light Field Networks, the re-formulations of radiance fields to oriented rays, are magnitudes faster than their coordinate network counterparts, and provide higher fidelity with respect to representing 3D structures from 2D observations.…
Accurate trajectory prediction can improve General Aviation safety in non-towered terminal airspace, where high traffic density increases accident risk. We present ASCENT, a lightweight transformer-based model for multi-modal 3D aircraft…
Transformer-based architectures have become the shared backbone of natural language processing and computer vision. However, understanding how these models operate remains challenging, particularly in vision settings, where images are…
Recent advances in robotic learning in simulation have shown impressive results in accelerating learning complex manipulation skills. However, the sim-to-real gap, caused by discrepancies between simulation and reality, poses significant…
Transparent objects, such as glass walls and doors, constitute architectural obstacles hindering the mobility of people with low vision or blindness. For instance, the open space behind glass doors is inaccessible, unless it is correctly…
Identifying, visualising and ultimately tracking dynamically moving non-fluorescent nanoparticles in the presence of non-specific scattering is a long-standing challenge across the nano- and life-sciences. In this work we demonstrate that…
Preserving boundary continuity in the translation of 360-degree panoramas remains a significant challenge for existing text-driven image-to-image translation methods. These methods often produce visually jarring discontinuities at the…
We introduce latent intuitive physics, a transfer learning framework for physics simulation that can infer hidden properties of fluids from a single 3D video and simulate the observed fluid in novel scenes. Our key insight is to use latent…
Image-based lighting is a widely used technique to reproduce shading under real-world lighting conditions, especially in real-time rendering applications. A particularly challenging scenario involves materials exhibiting a sparkling or…
Future surveys such as the Legacy Survey of Space and Time (LSST) of the Vera C. Rubin Observatory will observe an order of magnitude more astrophysical transient events than any previous survey before. With this deluge of photometric data,…
Many astronomical sources produce transient phenomena at radio frequencies, but the transient sky at low frequencies (<300 MHz) remains relatively unexplored. Blind surveys with new widefield radio instruments are setting increasingly…
Motion transfer enables controllable video generation by transferring temporal dynamics from a reference video to synthesize a new video conditioned on a target caption. However, existing Diffusion Transformer (DiT)-based methods are…
We have developed a method to determine the transient surface density and transient rate for any given survey, using Monte-Carlo simulations. This method allows us to determine the transient rate as a function of both the flux and the…
Learning neural radiance fields of a scene has recently allowed realistic novel view synthesis of the scene, but they are limited to synthesize images under the original fixed lighting condition. Therefore, they are not flexible for the…
We introduce DiffPhysCam, a differentiable camera simulator designed to support robotics and embodied AI applications by enabling gradient-based optimization in visual perception pipelines. Generating synthetic images that closely mimic…
Microwave-to-optics transduction is emerging as a vital technology for scaling quantum computers and quantum networks. To establish useful entanglement links between qubit processing units, several key conditions have to be simultaneously…
3D Gaussian Splatting (3DGS) has emerged as a prominent 3D representation for high-fidelity and real-time rendering. Prior work has coupled physics simulation with Gaussians, but predominantly targets soft, deformable materials, leaving…
Image-to-image translation aims to learn a mapping between a source and a target domain, enabling tasks such as style transfer, appearance transformation, and domain adaptation. In this work, we explore a diffusion-based framework for…
Monte Carlo rendering of translucent objects with heterogeneous scattering properties is often expensive both in terms of memory and computation. If we do path tracing and use a high dynamic range lighting environment, the rendering becomes…