Stain normalization is a key computational method in pathology that transforms histological stain images of one style to another. Modern methods are mostly based on neural image-to-image translation techniques. For very large image inputs, which are common in practice (e.g., whole slide images (WSIs)), the inferences are forced to run multiple times, each on a different subset of the image, due to GPU memory constraints. To minimize the differences between different outputs, several modifications [1], [2] of the standard instance-normalization (IN) layers have been proposed. Despite the reduced color variances, visible seams remain even with these approaches, which are disruptive to histologists when they closely examine the stitched results. These seams are also detrimental to the performance of some downstream tasks such as tumor classification. Hence, we propose a novel approach to effectively remove the seams by utilizing a Pix2Pix [3]-based neural network and an alpha blending-based post-processing step. Tested on real-world medical and natural image datasets, we found that our method performed much better than traditional Poisson image editing-based seam removal approaches. Our approaches qualitatively (in terms of the visibility of the seams) and quantitatively improved the results by prior stain normalization methods by large margins.

This paper focuses on improving the reconstruction of 2D floorplans from unstructured 3D point clouds. We identify opportunities for enhancement over the existing methods in three main areas: semantic quality, efficient representation, and local geometric details. To address these, we presents SLIBO-Net, an innovative approach to reconstructing 2D floorplans from unstructured 3D point clouds. We propose a novel transformer-based architecture that employs an efficient floorplan representation, providing improved room shape supervision and allowing for manageable token numbers. By incorporating geometric priors as a regularization mechanism and post-processing step, we enhance the capture of local geometric details. We also propose a scale-independent evaluation metric, correcting the discrepancy in error treatment between varying floorplan sizes. Our approach notably achieves a new state-of-the-art on the Structure3D dataset. The resultant floorplans exhibit enhanced semantic plausibility, substantially improving the overall quality and realism of the reconstructions. Our code and dataset are available online.

We propose a novel approach to compute high-resolution (2048x1024 and higher) depths for panoramas that is significantly faster and qualitatively and qualitatively more accurate than the current state-of-the-art method [23]. As traditional neural network-based methods have limitations in the output image sizes (up to 1024x512) due to GPU memory constraints, both [23] and our method rely on stitching multiple perspective disparity or depth images to come out a unified panoramic depth map. However, to achieve globally consistent stitching, [23] relied on solving extensive disparity map alignment and Poisson-based blending problems, leading to high computation time. Instead, we propose to use an existing panoramic depth map (computed in realtime by any panorama-based method) as the common target for the individual perspective depth maps to register to. This key idea made producing globally consistent stitching results from a straightforward task. Our experiments show that our method generates qualitatively better results than existing panorama-based methods, and further outperforms them quantitatively on datasets unseen by these methods.

We propose a novel hematoxylin and eosin (H&E) stain normalization method based on a modified U-Net neural network architecture. Unlike previous deep-learning methods that were often based on generative adversarial networks (GANs), we take a teacher-student approach and use paired datasets generated by a trained CycleGAN to train a U-Net to perform the stain normalization task. Through experiments, we compared our method to two recent competing methods, CycleGAN and StainNet, a lightweight approach also based on the teacher-student model. We found that our method is faster and can process larger images with better quality compared to CycleGAN. We also compared to StainNet and found that our method delivered quantitatively and qualitatively better results.

We present a deep learning framework, called DuLa-Net, to predict Manhattan-world 3D room layouts from a single RGB panorama. To achieve better prediction accuracy, our method leverages two projections of the panorama at once, namely the equirectangular panorama-view and the perspective ceiling-view, that each contains different clues about the room layouts. Our network architecture consists of two encoder-decoder branches for analyzing each of the two views. In addition, a novel feature fusion structure is proposed to connect the two branches, which are then jointly trained to predict the 2D floor plans and layout heights. To learn more complex room layouts, we introduce the Realtor360 dataset that contains panoramas of Manhattan-world room layouts with different numbers of corners. Experimental results show that our work outperforms recent state-of-the-art in prediction accuracy and performance, especially in the rooms with non-cuboid layouts.

Checkerboard patterns with black rectangles can be derived from quad meshes with orthogonal diagonals. First, we present an initial theoretical analysis of these quad meshes. The analysis reveals many possible applications in geometry processing and also motivates the numerical optimization for aesthetic and functional checkerboard pattern design. Second, we describe an optimization algorithm that transforms initial 2D and 3D quad meshes into quad meshes with orthogonal diagonals. Third, we present a 2D checkerboard pattern design framework based on integer programming inspired by the logo design of the 2020 Olympic games. Our results show a variety of 2D and 3D checkerboard patterns that can be derived from 2D or 3D quad meshes with orthogonal diagonals.

We present a framework to generate mesh patterns that consist of a hybrid of both triangles and quads. Given a 3D surface, the generated patterns fit the surface boundaries and curvatures. Such regular and near regular triangle-quad hybrid meshes provide two key advantages: first, novel-looking polygonal patterns achieved by mixing different arrangements of triangles and quads together; second, a finer discretization of angle deficits than utilizing triangles or quads alone. Users have controls over the generated patterns in global and local levels. We demonstrate applications of our approach in architectural geometry and pattern design on surfaces.

Connectivity and layout of underlying networks largely determine agent behavior and usage in many environments. For example, transportation networks determine the flow of traffic in a neighborhood, whereas building floorplans determine the flow of people in a workspace. Designing such networks from scratch is challenging as even local network changes can have large global effects. We investigate how to computationally create networks starting from only high-level functional specifications. Such specifications can be in the form of network density, travel time versus network length, traffic type, destination location, etc. We propose an integer programming-based approach that guarantees that the resultant networks are valid by fulfilling all the specified hard constraints and that they score favorably in terms of the objective function. We evaluate our algorithm in two different design settings, street layout and floorplans to demonstrate that diverse networks can emerge purely from high-level functional specifications.

We present a framework for exploring topologically unique quadrangulations of an input shape. First, the input shape is segmented into surface patches. Second, different topologies are enumerated and explored in each patch. This is realized by an efficient subdivision-based quadrangulation algorithm that can exhaustively enumerate all mesh topologies within a patch. To help users navigate the potentially huge collection of variations, we propose tools to preview and arrange the results. Furthermore, the requirement that all patches need to be jointly quadrangulatable is formulated as a linear integer program. Finally, we apply the framework to shape-space exploration, remeshing, and design to underline the importance of topology exploration.

In this paper, we tackle the problem of tiling a domain with a set of deformable templates. A valid solution to this problem completely covers the domain with templates such that the templates do not overlap. We generalize existing specialized solutions and formulate a general layout problem by modeling important constraints and admissible template deformations. Our main idea is to break the layout algorithm into two steps: a discrete step to lay out the approximate template positions and a continuous step to refine the template shapes. Our approach is suitable for a large class of applications, including floorplans, urban layouts, and arts and design.

Abstract We propose a connectivity editing framework for quad‐dominant meshes. In our framework, the user can edit the mesh connectivity to control the location, type, and number of irregular vertices (with more or fewer than four neighbors) and irregular faces (non‐quads). We provide a theoretical analysis of the problem, discuss what edits are possible and impossible, and describe how to implement an editing framework that realizes all possible editing operations. In the results, we show example edits and illustrate the advantages and disadvantages of different strategies for quad‐dominant mesh design.

We propose new connectivity editing operations for quadrilateral meshes with the unique ability to explicitly control the location, orientation, type, and number of the irregular vertices (valence not equal to four) in the mesh while preserving sharp edges. We provide theoretical analysis on what editing operations are possible and impossible and introduce threefundamentaloperations to move and re-orient a pair of irregular vertices. We argue that our editing operations are fundamental, because they only change the quad mesh in the smallest possible region and involve the fewest irregular vertices (i.e., two). The irregular vertex movement operations are supplemented by operations for the splitting, merging, canceling, and aligning of irregular vertices. We explain how the proposed high-level operations are realized through graph-level editing operations such as quad collapses, edge flips, and edge splits. The utility of these mesh editing operations are demonstrated by improving the connectivity of quad meshes generated from state-of-art quadrangulation techniques.