Related papers: Harmonics Virtual Lights : fast projection of lumi…
Indoor lighting estimation from a single image or video remains a challenge due to its highly ill-posed nature, especially when the lighting condition of the scene varies spatially and temporally. We propose a method that estimates from an…
Recent research on Simultaneous Localization and Mapping (SLAM) based on implicit representation has shown promising results in indoor environments. However, there are still some challenges: the limited scene representation capability of…
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…
We present a method to edit complex indoor lighting from a single image with its predicted depth and light source segmentation masks. This is an extremely challenging problem that requires modeling complex light transport, and disentangling…
Holographic displays hold the promise of providing authentic depth cues, resulting in enhanced immersive visual experiences for near-eye applications. However, current holographic displays are hindered by speckle noise, which limits…
Volumetric rendering based methods, like NeRF, excel in HDR view synthesis from RAWimages, especially for nighttime scenes. While, they suffer from long training times and cannot perform real-time rendering due to dense sampling…
Vision-language models (VLMs) have transformed multimodal reasoning, but feeding hundreds of visual patch tokens into LLMs incurs quadratic computational costs, straining memory and context windows. Traditional approaches face a trade-off:…
Vision-Language Models (VLMs) are increasingly tasked with ultra-long multimodal understanding. While linear architectures offer constant computation and memory footprints, they often struggle with high-frequency visual perception compared…
Most novel view synthesis methods -- including Neural Radiance Fields (NeRF) -- struggle to capture the high dynamic range (HDR) radiance required for realistic image-based lighting (IBL). This limitation stems from a reliance on low…
Light field (LF) representations aim to provide photo-realistic, free-viewpoint viewing experiences. However, the most popular LF representations are images from multiple views. Multi-view image-based representations generally need to…
We present a simple yet effective technique to estimate lighting in a single input image. Current techniques rely heavily on HDR panorama datasets to train neural networks to regress an input with limited field-of-view to a full environment…
Illumination estimation from a single image is critical in 3D rendering and it has been investigated extensively in the computer vision and computer graphic research community. On the other hand, existing works estimate illumination by…
Holographic near-eye displays offer unprecedented capabilities for virtual and augmented reality systems, including perceptually important focus cues. Although artificial intelligence--driven algorithms for computer-generated holography…
We present a novel technique for implicit neural representation of light fields at continuously defined viewpoints with high quality and fidelity. Our implicit neural representation maps 4D coordinates defining two-plane parameterization of…
Camera-based 3D Semantic Scene Completion (SSC) is a critical task for autonomous driving and robotic scene understanding. It aims to infer a complete 3D volumetric representation of both semantics and geometry from a single image. Existing…
Aperture array interferometers, such as that proposed for the Square Kilometre Array (SKA), will see the entire sky, hence the standard approach to simulating visibilities will not be applicable since it relies on a tangent plane…
Holography is capable of rendering three-dimensional scenes with full-depth control, and delivering transformative experiences across numerous domains, including virtual and augmented reality, education, and communication. However,…
The halo model (HM) describes the inhomogeneous universe as a collection of halos. The full nonlinear power spectrum of the universe is well approximated by the HM, whose prediction can be easily computed without lengthy numerical…
Neural scene representations, both continuous and discrete, have recently emerged as a powerful new paradigm for 3D scene understanding. Recent efforts have tackled unsupervised discovery of object-centric neural scene representations.…
We propose an efficient lighting estimation pipeline that is suitable to run on modern mobile devices, with comparable resource complexities to state-of-the-art mobile deep learning models. Our pipeline, PointAR, takes a single RGB-D image…