Related papers: Screen Space Indirect Lighting with Visibility Bit…
This paper presents a novel approach for enabling robust robotic perception in dark environments using infrared (IR) stream. IR stream is less susceptible to noise than RGB in low-light conditions. However, it is dominated by active emitter…
Most recent diffusion-based methods still show a large gap compared to non-diffusion methods for video frame interpolation, in both accuracy and efficiency. Most of them formulate the problem as a denoising procedure in latent space…
Integrating a foreground object into a background scene with illumination harmonization is an important but challenging task in computer vision and augmented reality community. Existing methods mainly focus on foreground and background…
This paper presents an integrated approach to Visual SLAM, merging online sequential photometric calibration within a Hybrid direct-indirect visual SLAM (H-SLAM). Photometric calibration helps normalize pixel intensity values under…
This paper introduces a diffusion-based framework for universal image segmentation, making agnostic segmentation possible without depending on mask-based frameworks and instead predicting the full segmentation in a holistic manner. We…
High resolution depth-maps, obtained by upsampling sparse range data from a 3D-LIDAR, find applications in many fields ranging from sensory perception to semantic segmentation and object detection. Upsampling is often based on combining…
Although many spectral unmixing models have been developed to address spectral variability caused by variable incident illuminations, the mechanism of the spectral variability is still unclear. This paper proposes an unmixing model, named…
We have developed a general method for finding apparent horizons in 3D numerical relativity. Instead of solving for the partial differential equation describing the location of the apparent horizons, we expand the closed 2D surfaces in…
Non-line-of-sight (NLOS) imaging relies on collecting light that is rendered incoherent from the multiple scattering events and is then post-processed to provide an estimate of the hidden scene. Here we employ coherent phase control of the…
In computer vision, convolutional neural networks (CNNs) have recently achieved new levels of performance for several inverse problems where RGB pixel appearance is mapped to attributes such as positions, normals or reflectance. In computer…
Recent work has shown that diffusion models can serve as powerful neural rendering engines that can be leveraged for inserting virtual objects into images. However, unlike typical physics-based renderers, these neural rendering engines are…
This paper presents a novel optimization-based method for non-line-of-sight (NLOS) imaging that aims to reconstruct hidden scenes under general setups with significantly reduced reconstruction time. In NLOS imaging, the visible surfaces of…
Optical see-through head-mounted displays (OST HMDs) typically display virtual content at a fixed focal distance while users need to integrate this information with real-world information at different depth layers. This problem is…
Real-time depth of field in game cinematics tends to approximate the semi-transparent silhouettes of out-of-focus objects through post-processing techniques. We leverage ray tracing hardware acceleration and spatio-temporal reconstruction…
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…
Vision Transformers are at the heart of the current surge of interest in foundation models for histopathology. They process images by breaking them into smaller patches following a regular grid, regardless of their content. Yet, not all…
We propose a real-time method to estimate spatiallyvarying indoor lighting from a single RGB image. Given an image and a 2D location in that image, our CNN estimates a 5th order spherical harmonic representation of the lighting at the given…
Volumetric video relighting is essential for bringing captured performances into virtual worlds, but current approaches struggle to deliver temporally stable, production-ready results. Diffusion-based intrinsic decomposition methods show…
Constraining the distribution of small-scale structure in our universe allows us to probe alternatives to the cold dark matter paradigm. Strong gravitational lensing offers a unique window into small dark matter halos ($<10^{10} M_\odot$)…
In this work we study the tomography of the spatial structure of light. We develop a simple technique that allows one to perform the tomography over the space of fixed order modes. The technique is based on two spatially resolved intensity…