Jianwei Guo

• Associate Professor
• Associate Professor at Institute of Automation, Chinese Academy of Sciences

As immersive experiences become increasingly popular, panoramic video has garnered significant attention in both research and applications. The high cost associated with capturing panoramic video underscores the need for efficient prompt-based generation methods. Although recent text-to-video (T2V) diffusion techniques have shown potential in stand...

The integration of deep generative networks into generating Computer-Aided Design (CAD) models has garnered increasing attention over recent years. Traditional methods often rely on discrete sequences of parametric line/curve segments to represent sketches. Differently, we introduce RECAD, a novel framework that generates Raster sketches and 3D Ext...

Parametric edge reconstruction for point cloud data is a fundamental problem in computer graphics. Existing methods first classify points as either edge points (including corners) or non-edge points, and then fit parametric edges to the edge points. However, few points are exactly sampled on edges in practical scenarios, leading to significant fitt...

Automatically generating high-quality textures for complex scenes remains a significant challenge in computer graphics. Recent advances in text-to-texture synthesis using 2D diffusion models have yielded impressive results for individual objects but struggle to maintain style consistency and semantic alignment when applied to larger scenes. These m...

Neural Radiance Field (NeRF) can render complex 3D scenes with viewpoint‐dependent effects. However, less work has been devoted to exploring its limitations in high‐resolution environments, especially when upscaled to ultra‐high resolution (e.g., 4k). Specifically, existing NeRF‐based methods face severe limitations in reconstructing high‐resolutio...

Digitalization of large-scale urban scenes (in particular buildings) has been a long-standing open problem, which attributes to the challenges in data acquisition, such as incomplete scene coverage, lack of semantics, low efficiency, and low reliability in path planning. In this paper, we address these challenges in urban building reconstruction fr...

With the continuous advancement of computer technology and graphic capabilities, the creation of 3D point clouds holds great promise across various fields. However, previous methods in this area are still facing huge challenges, such as complex training setups and limited precision in generating high-quality 3D content. Taking inspiration from the...

Single image rectification of document deformation is a challenging task. Although some recent deep learning-based methods have attempted to solve this problem, they cannot achieve satisfactory results when dealing with document images with complex deformations. In this paper, we propose a new efficient framework for document flattening. Our main i...

The popularity of online home design and floor plan customization has been steadily increasing. However, the manual conversion of floor plan images from books or paper materials into electronic resources can be a challenging task due to the vast amount of historical data available. By leveraging neural networks to identify and parse floor plans, th...

We address the 3D shape assembly of multiple geometric pieces without overlaps, a scenario often encountered in 3D shape design, field archeology, and robotics. Existing methods depend on strong assumptions on the number of shape pieces and coherent geometry or semantics of shape pieces. Despite raising attention to 3D registration with complex or...

Textureless objects, repetitive patterns and limited computational resources pose significant challenges to man-made structure reconstruction from images, because feature-points-based reconstruction methods usually fail due to the lack of distinct texture or ambiguous point matches. Meanwhile multi-view stereo approaches also suffer from high compu...

Specular highlight detection and removal is a fundamental problem in computer vision and image processing. In this paper, we present an efficient end-to-end deep learning model for automatically detecting and removing specular highlights in a single image. In particular, an encoder–decoder network is utilized to detect specular highlights, and then...

The point pair feature (PPF) is widely used in manufacturing for estimating 6-D poses. The key to the success of PPF matching is to establish correct 3-D correspondences between the object and the scene, i.e., finding as many valid similar point pairs as possible. However, efficient sampling of point pairs has been overlooked in existing framewor...

Registering urban point clouds is a quite challenging task due to the large-scale, noise and data incompleteness of LiDAR scanning data. In this paper, we propose SARNet, a novel semantic augmented registration network aimed at achieving efficient registration of urban point clouds at city scale. Different from previous methods that construct corre...

The growing size of point clouds enlarges consumptions of storage, transmission, and computation of 3D scenes. Raw data is redundant, noisy, and non-uniform. Therefore, simplifying point clouds for achieving compact, clean, and uniform points is becoming increasingly important for 3D vision and graphics tasks. Previous learning based methods aim to...

We present TreePartNet , a neural network aimed at reconstructing tree geometry from point clouds obtained by scanning real trees. Our key idea is to learn a natural neural decomposition exploiting the assumption that a tree comprises locally cylindrical shapes. In particular, reconstruction is a two-step process. First, two networks are used to de...

Reconstructing high-fidelity 3D facial texture from a single image is a challenging task since the lack of complete face information and the domain gap between the 3D face and 2D image. The most recent works tackle facial texture reconstruction problem by applying either generation-based or reconstruction-based methods. Although each method has its...

Specular reflections pose great challenges on various multimedia and computer vision tasks, e.g. , image segmentation, detection and matching. In this paper, we build a large-scale Paired Specular-Diffuse (PSD) image dataset, where the images are carefully captured by using real-world objects and the ground-truth specular-free diffuse images are...

Automatic registration of point clouds captured by terrestrial laser scanning (TLS) plays an important role in many fields including remote sensing (e.g., transportation management, 3-D reconstruction in large-scale urban areas and environment monitoring), computer vision, and virtual reality and robotics. However, noise, outliers, nonuniform point...

Realistic 3D tree reconstruction is still a tedious and time-consuming task in the graphics community. In this paper, we propose a simple and efficient method for reconstructing 3D tree models with high fidelity from a single image. The key to single image-based tree reconstruction is to recover 3D shape information of trees via a deep neural netwo...

We present a novel and efficient approach to estimate 6D object poses of known objects in complex scenes represented by point clouds. Our approach is based on the well-known point pair feature (PPF) matching, which utilizes self-similar point pairs to compute potential matches and thereby cast votes for the object pose by a voting scheme. The main...

Automatic understanding of floor plan images is a key component of various applications. Due to the style diversity of rural housing design, the latest learning-based approaches cannot achieve satisfactory recognition results. In this paper, we present a new framework for parsing floor plans of rural residence that combines semantic neural networks...

Meaningful feature curves provide high-level shape representation of the geometrical shapes and are useful in various applications. In this paper, we propose an automatic method on the basis of the quadric surface fitting technique to extract complete feature curve networks (FCNs) from 3D surface meshes, as well as finding cycles and generating a h...

Recognizing and fitting shape primitives from underlying 3D models is a key component of many computer graphics applications. Although there exists many structure recovery methods, they usually fail to identify blending surfaces, which are small transition regions between relatively large primary patches. To address this issue, we present a novel a...

The traditional stem model is inconsistent with the real geometry of the stem. Terrestrial laser scanning (TLS) provides a possibility of constructing a realistic stem model. In this study, we present a 3D stem model, which includes the stem axis curve and stem cross-sectional profile curve, with geometrical consistency and stem parameter retrieval...

We propose a novel framework for computing descriptors for characterizing points on three-dimensional surfaces. First, we present a new non-learned feature that uses graph wavelets to decompose the Dirichlet energy on a surface. We call this new feature Wavelet Energy Decomposition Signature (WEDS). Second, we propose a new Multiscale Graph Convolu...

We introduce an inverse procedural modeling approach that learns L-system representations of pixel images with branching structures. Our fully automatic model generates a compact set of textual rewriting rules that describe the input. We use deep learning to discover atomic structures such as line segments or branchings. Orientation and scaling of...

A discriminative local shape descriptor plays an important role in various applications. In this paper, we present a novel deep learning framework that derives discriminative local descriptors for deformable 3D shapes. We use local “geometry images” to encode the multi-scale local features of a point, via an intrinsic parameterization method based...

We propose a novel framework for computing descriptors for characterizing points on three-dimensional surfaces. First, we present a new non-learned feature that uses graph wavelets to decompose the Dirichlet energy on a surface. We call this new feature wavelet energy decomposition signature (WEDS). Second, we propose a new multiscale graph convolu...

We present a novel local shape descriptor, named wavelet energy decomposition signature (WEDS) for robustly matching non-rigid 3D shapes with different resolutions. The local shape descriptors are generated by decomposing Dirichlet energy on the input triangular mesh. Our approach can be either applied directly or used as the input to other learnin...

In this poster, we proposed a refined scheme and system to realize the multi-directional 3D printing with the strength as the traditional unidirectional 3D printing. With the introduction of the 10.6m CO2 laser, the printing system can heat the interfaces of the already printed components and increase the intermolecular-penetrating diffusion while...

In this paper, we present a novel real-time approach to generate high-quality stippling on 3D scenes. The proposed method is built on a precomputed 2D sample sequence called incremental Voronoi set with blue-noise properties. A rejection sampling scheme is then applied to achieve tone reproduction, by thresholding the sample indices proportional to...

In this paper, we describe a novel procedural modeling technique for generating realistic plant models from multi-view photographs. The realism is enhanced via visual and spatial information acquired from images. In contrast to previous approaches that heavily rely on user interaction to segment plants or recover branches in images, our method auto...

In this paper, we present a novel deep learning framework that derives discriminative local descriptors for 3D surface shapes. In contrast to previous convolutional neural networks (CNNs) that rely on rendering multi-view images or extracting intrinsic shape properties, we parameterize the multi-scale localized neighborhoods of a keypoint into regu...

Generating an interior support structure is a key issue in 3D model geometric optimization for 3D printing. Most existing interior support structures have been designed by simulating lightweight structures naturally exist. One limitation of the existing method is that only one single structure is used for the model. However, different parts of a 3D...

Modelling and simulation of tree growth that is faithful to the living environment and numerically consistent to botanic knowledge are important topics for realistic modelling in computer graphics. The realism factors concerned include the effects of complex environment on tree growth and the reliability of the simulation in botanical research, suc...

Plants are ubiquitous in the nature, and realistic plant modeling plays an important role in a variety of applications. Over the last decades, an immense amount of efforts have been dedicated to plant modeling. These approaches can be classified into two major categories: procedural modeling [Palubicki et al. 2009; Stava et al. 2014] and data-drive...

In the field of computer graphics, maximal Poisson-disk sampling (MPS) is a fundamental research topic. An ideal sampling set should satisfy unbiased sampling property, minimal distance property, and maximal sampling property. In general, MPS is obtained by Dart Throwing, as we all know, the drawback of this method is unable to precisely control th...

The existing methods of curve interpolation cannot solve practical application problems of constructing a closed smooth curve with global convexity for planar convex hull point set. For this purpose, a curve interpolation algorithm for constructing a closed G² continuity curve with global convexity is proposed. A planar convex hull point set was us...

We describe a simple push-pull optimization (PPO) algorithm for blue-noise sampling by enforcing spatial constraints on given point sets. Constraints can be a minimum distance between samples, a maximum distance between an arbitrary point and the nearest sample, and a maximum deviation of a sample's capacity (area of Voronoi cell) from the mean cap...

We present a novel technique that produces two-dimensional low-discrepancy (LD) blue noise point sets for sampling. Using one-dimensional binary van der Corput sequences, we construct two-dimensional LD point sets, and rearrange them to match a target spectral profile while preserving their low discrepancy. We store the rearrangement information in...

Maximal Poisson-disk Sampling (MPS) is a fundamental research topic in computer graphics. An ideal MPS pattern should satisfy three properties: bias-free, minimal distance, maximal coverage. The classic approach for generating MPS is dart throwing, but this method is unable to precisely control the number of samples when achieving maximality [Ebeid...

This paper provides a comprehensive overview of the state-of-the-art for processing large-scale 3D point cloud based on optical acquisition. We first summarize the general pipeline of point cloud processing, ranging from filtering to the final reconstruction, and give further detailed introduction. On this basis we give a general insight over the p...

We present a novel method for high-quality blue-noise sampling on mesh surfaces with prescribed cell-sizes for the underlying tessellation (capacity constraint). Unlike the previous surface sampling approach that only uses capacity constraints as a regularizer of the Centroidal Voronoi Tessellation (CVT) energy, our approach enforces an exact capac...

Point distributions with different characteristics have a crucial influence on graphics applications. Various analysis tools have been developed in recent years, mainly for blue noise sampling in Euclidean domains. In this paper, we present a new method to analyze the properties of general sampling patterns that are distributed on mesh surfaces. Th...

In this paper, we propose a simple yet effective method to generate 3D-conforming tetrahedral meshes from closed 2-manifold surfaces. Our approach is inspired by recent work on maximal Poisson-disk sampling (MPS), which can generate well-distributed point sets in arbitrary domains. We first perform MPS on the boundary of the input domain, we then s...

In this paper, we survey recent approaches to blue-noise sampling and discuss their beneficial applications. We discuss the sampling algorithms that use points as sampling primitives and classify the sampling algorithms based on various aspects, e.g., the sampling domain and the type of algorithm. We demonstrate several well-known applications that...

In this paper, we present a novel method for surface sampling and remeshing with good blue-noise properties. Our approach is based on the farthest point optimization (FPO), a relaxation technique that generates high quality blue-noise point sets in 2D. We propose two important generalizations of the original FPO framework: adaptive sampling and sam...

In this paper, we present a simple yet efficient algorithm for triangulating a 2D input domain containing a Poisson-disk sampled point set. The proposed algorithm combines a regular grid and a discrete clustering approach to speedup the triangulation. Moreover, our triangulation algorithm is flexible and performs well on more general point sets suc...

Poisson-disk sampling is one of the fundamental research problems in computer graphics that has many applications. In this paper, we study the problem of maximal Poisson-disk sampling on mesh surfaces. We present a simple approach that generalizes the 2D maximal sampling framework to surfaces. The key observation is to use a subdivided mesh as the...

In this paper, we present an information-theoretic framework to compute the shape similarity between 3D polygonal models. Given a 3D model, an information channel between a sphere of viewpoints around the model and its polygonal mesh is defined to compute the specific information associated with each viewpoint. The obtained information sphere can b...

We present an information-theoretic framework to compute the shape similarity between 3D polygonal models. From an information channel between a sphere of viewpoints and the polygonal mesh of a model, an information sphere is obtained and used as a shape descriptor of the model. Given two models, the minimum distance between their information spher...

This paper describes an approach, where an O3D-based virtual environment for learning cultural heritage is combined with a game environment to provide a friendly environment that makes learning more pleasant. We describe the game flow, design approach, and the exploration-based O3D API for creating interactive learning environment first. By using i...

This paper describes an integrated method of designing and implementing an indoor virtual environment interactively for cultural heritage exhibiton based on our immersion educational learning system by using O3D(Open web standard for 3D graphics). By using the 3D museum construction tool offered by our system, users can create their personal museum...