Related papers: A Diffusion Approach to Radiance Field Relighting …
We present a method to separate a single image captured under two illuminants, with different spectra, into the two images corresponding to the appearance of the scene under each individual illuminant. We do this by training a deep neural…
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.…
The emerging Neural Radiance Field (NeRF) shows great potential in representing 3D scenes, which can render photo-realistic images from novel view with only sparse views given. However, utilizing NeRF to reconstruct real-world scenes…
Previous raw image-based low-light image enhancement methods predominantly relied on feed-forward neural networks to learn deterministic mappings from low-light to normally-exposed images. However, they failed to capture critical…
Radiance field reconstruction aims to recover high-quality 3D representations from multi-view RGB images. Recent advances, such as 3D Gaussian splatting, enable real-time rendering with high visual fidelity on sufficiently powerful graphics…
3D scene reconstruction is essential for applications in virtual reality, robotics, and autonomous driving, enabling machines to understand and interact with complex environments. Traditional 3D Gaussian Splatting techniques rely on images…
We consider the problem of reconstructing a full 360{\deg} photographic model of an object from a single image of it. We do so by fitting a neural radiance field to the image, but find this problem to be severely ill-posed. We thus take an…
Achieving photorealistic 3D view synthesis and relighting of human portraits is pivotal for advancing AR/VR applications. Existing methodologies in portrait relighting demonstrate substantial limitations in terms of generalization and 3D…
Gaussian Splatting has become a popular technique for various 3D Computer Vision tasks, including novel view synthesis, scene reconstruction, and dynamic scene rendering. However, the challenge of natural-looking object insertion, where the…
Novel-view synthesis through diffusion models has demonstrated remarkable potential for generating diverse and high-quality images. Yet, the independent process of image generation in these prevailing methods leads to challenges in…
This paper proposes a hybrid radiance field representation for unbounded immersive light field reconstruction which supports high-quality rendering and aggressive view extrapolation. The key idea is to first formally separate the foreground…
Radiance field methods, such as Neural Radiance Field or 3D Gaussian Splatting, have emerged as seminal 3D representations for synthesizing realistic novel views. For practical applications, there is ongoing research on flexible scene…
Neural radiance field is an emerging rendering method that generates high-quality multi-view consistent images from a neural scene representation and volume rendering. Although neural radiance field-based techniques are robust for scene…
Diffusion models currently achieve state-of-the-art performance for both conditional and unconditional image generation. However, so far, image diffusion models do not support tasks required for 3D understanding, such as view-consistent 3D…
We tackle the challenge of learning a distribution over complex, realistic, indoor scenes. In this paper, we introduce Generative Scene Networks (GSN), which learns to decompose scenes into a collection of many local radiance fields that…
Synthesizing normal-light novel views from low-light multiview images is an important yet challenging task, given the low visibility and high ISO noise present in the input images. Existing low-light enhancement methods often struggle to…
Dynamic scene representation and reconstruction have undergone transformative advances in recent years, catalyzed by breakthroughs in neural radiance fields and 3D Gaussian splatting techniques. While initially developed for static…
Vision based robot manipulation uses cameras to capture one or more images of a scene containing the objects to be manipulated. Taking multiple images can help if any object is occluded from one viewpoint but more visible from another…
Existing multi-view 3D object reconstruction methods heavily rely on sufficient overlap between input views, where occlusions and sparse coverage in practice frequently yield severe reconstruction incompleteness. Recent advancements in…
Relighting of human images enables post-photography editing of lighting effects in portraits. The current mainstream approach uses neural networks to approximate lighting effects without explicitly accounting for the principle of physical…