Related papers: Half-body Portrait Relighting with Overcomplete Li…
We present the first neural relighting approach for rendering high-fidelity personalized hands that can be animated in real-time under novel illumination. Our approach adopts a teacher-student framework, where the teacher learns appearance…
We present GroomLight, a novel method for relightable hair appearance modeling from multi-view images. Existing hair capture methods struggle to balance photorealistic rendering with relighting capabilities. Analytical material models,…
Face relighting aims to synthesize realistic portraits under novel illumination while preserving identity and geometry. However, progress remains constrained by the limited availability of large-scale, physically consistent illumination…
Relighting, which synthesizes a novel view under a given lighting condition (unseen in training time), is a must feature for immersive photo-realistic experience. However, real-time relighting is challenging due to high computation cost of…
We propose TensoIR, a novel inverse rendering approach based on tensor factorization and neural fields. Unlike previous works that use purely MLP-based neural fields, thus suffering from low capacity and high computation costs, we extend…
3D representation and reconstruction of human bodies have been studied for a long time in computer vision. Traditional methods rely mostly on parametric statistical linear models, limiting the space of possible bodies to linear…
Inverse rendering, the process of inferring scene properties from images, is a challenging inverse problem. The task is ill-posed, as many different scene configurations can give rise to the same image. Most existing solutions incorporate…
The field of computational imaging has witnessed a promising paradigm shift with the emergence of untrained neural networks, offering novel solutions to inverse computational imaging problems. While existing techniques have demonstrated…
We present an object relighting system that allows an artist to select an object from an image and insert it into a target scene. Through simple interactions, the system can adjust illumination on the inserted object so that it appears…
General image completion and extrapolation methods often fail on portrait images where parts of the human body need to be recovered - a task that requires accurate human body structure and appearance synthesis. We present a two-stage deep…
In this work, we focus on outdoor lighting estimation by aggregating individual noisy estimates from images, exploiting the rich image information from wide-angle cameras and/or temporal image sequences. Photographs inherently encode…
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…
Recent advances have shown that large-scale video diffusion models can be repurposed as neural renderers by first decomposing videos into intrinsic scene representations and then performing forward rendering under novel illumination. While…
We report the possibility of using a simple neural network for effortless restoration of low-light images inspired by the retina model, which mimics the neurophysiological principles and dynamics of various types of optical neurons. The…
We present Relightable Holoported Characters (RHC), a novel person-specific method for free-view rendering and relighting of full-body and highly dynamic humans solely observed from sparse-view RGB videos at inference. In contrast to…
At the heart of the success of deep learning is the quality of the data. Through data augmentation, one can train models with better generalization capabilities and thus achieve greater results in their field of interest. In this work, we…
We present a scheme for fast environment light estimation from the RGBD appearance of individual objects and their local image areas. Conventional inverse rendering is too computationally demanding for real-time applications, and the…
We study human pose estimation in extremely low-light images. This task is challenging due to the difficulty of collecting real low-light images with accurate labels, and severely corrupted inputs that degrade prediction quality…
Models for image representation learning are typically designed for either recognition or generation. Various forms of contrastive learning help models learn to convert images to embeddings that are useful for classification, detection, and…
Representing visual signals with implicit coordinate-based neural networks, as an effective replacement of the traditional discrete signal representation, has gained considerable popularity in computer vision and graphics. In contrast to…