Related papers: PX-NET: Simple and Efficient Pixel-Wise Training o…
Image relighting has emerged as a problem of significant research interest inspired by augmented reality applications. Physics-based traditional methods, as well as black box deep learning models, have been developed. The existing deep…
Inferring the 3D shape of an object from an RGB image has shown impressive results, however, existing methods rely primarily on recognizing the most similar 3D model from the training set to solve the problem. These methods suffer from poor…
Photometric Stereo methods seek to reconstruct the 3d shape of an object from motionless images obtained with varying illumination. Most existing methods solve a restricted problem where the physical reflectance model, such as Lambertian…
Reconstructing the 3D shape of an object using several images under different light sources is a very challenging task, especially when realistic assumptions such as light propagation and attenuation, perspective viewing geometry and…
Inferring the physical properties of 3D scenes from visual information is a critical yet challenging task for creating interactive and realistic virtual worlds. While humans intuitively grasp material characteristics such as elasticity or…
Existing deep calibrated photometric stereo networks basically aggregate observations under different lights based on the pre-defined operations such as linear projection and max pooling. While they are effective with the dense capture,…
Recovering the 3D shape of transparent objects using a small number of unconstrained natural images is an ill-posed problem. Complex light paths induced by refraction and reflection have prevented both traditional and deep multiview stereo…
This paper solves the Sparse Photometric stereo through Lighting Interpolation and Normal Estimation using a generative Network (SPLINE-Net). SPLINE-Net contains a lighting interpolation network to generate dense lighting observations given…
Indoor scene understanding is central to applications such as robot navigation and human companion assistance. Over the last years, data-driven deep neural networks have outperformed many traditional approaches thanks to their…
Outdoor scene relighting is a challenging problem that requires good understanding of the scene geometry, illumination and albedo. Current techniques are completely supervised, requiring high quality synthetic renderings to train a…
Recently, deep learning-based single image reflection separation methods have been exploited widely. To benefit the learning approach, a large number of training image pairs (i.e., with and without reflections) were synthesized in various…
Recently, learning-based multi-view stereo methods have achieved promising results. However, they all overlook the visibility difference among different views, which leads to an indiscriminate multi-view similarity definition and greatly…
This paper addresses the problem of inverse rendering from photometric images. Existing approaches for this problem suffer from the effects of self-shadows, inter-reflections, and lack of constraints on the surface reflectance, leading to…
A fundamental problem in computer vision is that of inferring the intrinsic, 3D structure of the world from flat, 2D images of that world. Traditional methods for recovering scene properties such as shape, reflectance, or illumination rely…
Reflections are very common phenomena in our daily photography, which distract people's attention from the scene behind the glass. The problem of removing reflection artifacts is important but challenging due to its ill-posed nature. The…
Recently, 3D face reconstruction from a single image has achieved great success with the help of deep learning and shape prior knowledge, but they often fail to produce accurate geometry details. On the other hand, photometric stereo…
Intrinsic image decomposition is the process of separating the reflectance and shading layers of an image, which is a challenging and underdetermined problem. In this paper, we propose to systematically address this problem using a deep…
This paper addresses the problem of photometric stereo, in both calibrated and uncalibrated scenarios, for non-Lambertian surfaces based on deep learning. We first introduce a fully convolutional deep network for calibrated photometric…
In recent years, self-supervised learning has attracted widespread academic debate and addressed many of the key issues of computer vision. The present research focus is on how to construct a good agent task that allows for improved network…
We introduce the first end-to-end learning-based solution to near-field Photometric Stereo (PS), where the light sources are close to the object of interest. This setup is especially useful for reconstructing large immobile objects. Our…