Related papers: Facetwise Mesh Refinement for Multi-View Stereo
Recovering the shape and appearance of real-world objects from natural 2D images is a long-standing and challenging inverse rendering problem. In this paper, we introduce a novel hybrid differentiable rendering method to efficiently…
Facial expression image editing requires fine-grained control to strictly preserve human identity and background while precisely manipulating expression. However, existing editing benchmarks primarily focus on general scenarios, lacking…
Neural Radiance Fields (NeRF) have constituted a remarkable breakthrough in image-based 3D reconstruction. However, their implicit volumetric representations differ significantly from the widely-adopted polygonal meshes and lack support…
Single-view 3D object reconstruction is a fundamental and challenging computer vision task that aims at recovering 3D shapes from single-view RGB images. Most existing deep learning based reconstruction methods are trained and evaluated on…
Quality control is a critical aspect of manufacturing, particularly in ensuring the proper assembly of small components in production lines. Existing solutions often rely on single-view imaging or manual inspection, which are prone to…
This paper studies the problem of view synthesis with certain amount of rotations from a pair of images, what we called stereo unstructured magnification. While the multi-plane image representation is well suited for view synthesis with…
Stitched images provide a wide field-of-view (FoV) but suffer from unpleasant irregular boundaries. To deal with this problem, existing image rectangling methods devote to searching an initial mesh and optimizing a target mesh to form the…
Multi-view triangulation is the gold standard for 3D reconstruction from 2D correspondences given known calibration and sufficient views. However in practice, expensive multi-view setups -- involving tens sometimes hundreds of cameras --…
Much recent progress has been made in reconstructing the 3D shape of an object from an image of it, i.e. single view 3D reconstruction. However, it has been suggested that current methods simply adopt a "nearest-neighbor" strategy, instead…
I present a generalization of Chew's first algorithm for Delaunay mesh refinement. In his algorithm, Chew splits the line segments of the input planar straight line graph (PSLG) into shorter subsegments whose lengths are nearly identical.…
Pose refinement is an interesting and practically relevant research direction. Pose refinement can be used to (1) obtain a more accurate pose estimate from an initial prior (e.g., from retrieval), (2) as pre-processing, i.e., to provide a…
Learning-based Multi-View Stereo (MVS) methods have made remarkable progress in recent years. However, how to effectively train the network without using real-world labels remains a challenging problem. In this paper, driven by the recent…
An adaptive refinement strategy, based on an equilibrated flux a posteriori error estimator, is proposed in the context of defeaturing problems. Defeaturing consists of removing features from complex domains to simplify mesh generation and…
Finding accurate correspondences among different views is the Achilles' heel of unsupervised Multi-View Stereo (MVS). Existing methods are built upon the assumption that corresponding pixels share similar photometric features. However,…
Stereo matching is a fundamental task in scene comprehension. In recent years, the method based on iterative optimization has shown promise in stereo matching. However, the current iteration framework employs a single-peak lookup, which…
Sample-induced aberrations and optical imperfections limit the resolution of fluorescence microscopy. Phase diversity is a powerful technique that leverages complementary phase information in sequentially acquired images with deliberately…
Multi-view depth estimation plays a critical role in reconstructing and understanding the 3D world. Recent learning-based methods have made significant progress in it. However, multi-view depth estimation is fundamentally a…
Photometric stereo, a problem of recovering 3D surface normals using images of an object captured under different lightings, has been of great interest and importance in computer vision research. Despite the success of existing traditional…
Multispectral demosaicing is crucial to reconstruct full-resolution spectral images from snapshot mosaiced measurements, enabling real-time imaging from neurosurgery to autonomous driving. Classical methods are blurry, while supervised…
We tackle the problem of monocular-to-stereo video conversion and propose a novel architecture for inpainting and refinement of the warped right view obtained by depth-based reprojection of the input left view. We extend the Stable Video…