Related papers: A Flexible Neural Renderer for Material Visualizat…
Neural rendering algorithms have revolutionized computer graphics, yet their impact on real-time rendering under arbitrary lighting conditions remains limited due to strict latency constraints in practical applications. The key challenge…
Augmented reality applications have rapidly spread across online platforms, allowing consumers to virtually try-on a variety of products, such as makeup, hair dying, or shoes. However, parametrizing a renderer to synthesize realistic images…
We learn a latent space for easy capture, consistent interpolation, and efficient reproduction of visual material appearance. When users provide a photo of a stationary natural material captured under flashlight illumination, first it is…
Faster rendering of synthetic images is a core problem in the field of computer graphics. Rendering algorithms, such as path-tracing is dependent on parameters like size of the image, number of light bounces, number of samples per pixel,…
Neural radiance fields provide state-of-the-art view synthesis quality but tend to be slow to render. One reason is that they make use of volume rendering, thus requiring many samples (and model queries) per ray at render time. Although…
We are witnessing an explosion of neural implicit representations in computer vision and graphics. Their applicability has recently expanded beyond tasks such as shape generation and image-based rendering to the fundamental problem of…
Transferring artistic styles onto everyday photographs has become an extremely popular task in both academia and industry. Recently, offline training has replaced on-line iterative optimization, enabling nearly real-time stylization. When…
Reconstructing object geometry and material from multiple views typically requires optimization. Differentiable path tracing is an appealing framework as it can reproduce complex appearance effects. However, it is difficult to use due to…
We introduce a neural relighting algorithm for captured indoors scenes, that allows interactive free-viewpoint navigation. Our method allows illumination to be changed synthetically, while coherently rendering cast shadows and complex…
Neural materials typically consist of a collection of neural features along with a decoder network. The main challenge in integrating such models in real-time rendering pipelines lies in the large size required to store their features in…
Creating high-quality controllable 3D human models from multi-view RGB videos poses a significant challenge. Neural radiance fields (NeRFs) have demonstrated remarkable quality in reconstructing and free-viewpoint rendering of static as…
High-resolution representations are important for vision-based robotic grasping problems. Existing works generally encode the input images into low-resolution representations via sub-networks and then recover high-resolution…
We present TraceFlow, a novel framework for high-fidelity rendering of dynamic specular scenes by addressing two key challenges: precise reflection direction estimation and physically accurate reflection modeling. To achieve this, we…
Applying convolutional neural networks to large images is computationally expensive because the amount of computation scales linearly with the number of image pixels. We present a novel recurrent neural network model that is capable of…
Indoor scenes typically exhibit complex, spatially-varying appearance from global illumination, making inverse rendering a challenging ill-posed problem. This work presents an end-to-end, learning-based inverse rendering framework…
To what extent is the success of deep visualization due to the training? Could we do deep visualization using untrained, random weight networks? To address this issue, we explore new and powerful generative models for three popular deep…
We present TimeNeRF, a generalizable neural rendering approach for rendering novel views at arbitrary viewpoints and at arbitrary times, even with few input views. For real-world applications, it is expensive to collect multiple views and…
Generating free-viewpoint videos is critical for immersive VR/AR experience but recent neural advances still lack the editing ability to manipulate the visual perception for large dynamic scenes. To fill this gap, in this paper we propose…
Deep neural networks (DNNs) have shown remarkable performance improvements on vision-related tasks such as object detection or image segmentation. Despite their success, they generally lack the understanding of 3D objects which form the…
The lack of labeled datasets in 3D vision for surgical scenes inhibits the development of robust 3D reconstruction algorithms in the medical domain. Despite the popularity of Neural Radiance Fields and 3D Gaussian Splatting in the general…