arXiv subjects

Yanyan Li

Publications and source records attributed to Yanyan Li.

At least 37 records · Page 2Linked to original sources

arXiv2024

Open-Structure: Structural Benchmark Dataset for SLAM Algorithms

This paper presents Open-Structure, a novel benchmark dataset for evaluating visual odometry and SLAM methods. Compared to existing public datasets that primarily offer raw images, Open-Structure provides direct access to point and line measurements, correspondences, structural associations, and co-visibility factor graphs, which can be fed to various stages of SLAM pipelines to mitigate the impact of data preprocessing modules in ablation experiments. The dataset comprises two distinct types of sequences from the perspective of scenarios. The first type maintains reasonable observation and occlusion relationships, as these critical elements are extracted from public image-based sequences using our dataset generator. In contrast, the second type consists of carefully designed simulation sequences that enhance dataset diversity by introducing a wide range of trajectories and observations. Furthermore, a baseline is proposed using our dataset to evaluate widely used modules, including camera pose tracking, parametrization, and factor graph optimization, within SLAM systems. By evaluating these state-of-the-art algorithms across different scenarios, we discern each module's strengths and weaknesses in the context of camera tracking and optimization processes. The Open-Structure dataset and baseline system are openly accessible on website: \url{https://open-structure.github.io}, encouraging further research and development in the field of SLAM.

cs.RO↗

arXiv2024

Robust Gaussian Splatting SLAM by Leveraging Loop Closure

3D Gaussian Splatting algorithms excel in novel view rendering applications and have been adapted to extend the capabilities of traditional SLAM systems. However, current Gaussian Splatting SLAM methods, designed mainly for hand-held RGB or RGB-D sensors, struggle with tracking drifts when used with rotating RGB-D camera setups. In this paper, we propose a robust Gaussian Splatting SLAM architecture that utilizes inputs from rotating multiple RGB-D cameras to achieve accurate localization and photorealistic rendering performance. The carefully designed Gaussian Splatting Loop Closure module effectively addresses the issue of accumulated tracking and mapping errors found in conventional Gaussian Splatting SLAM systems. First, each Gaussian is associated with an anchor frame and categorized as historical or novel based on its timestamp. By rendering different types of Gaussians at the same viewpoint, the proposed loop detection strategy considers both co-visibility relationships and distinct rendering outcomes. Furthermore, a loop closure optimization approach is proposed to remove camera pose drift and maintain the high quality of 3D Gaussian models. The approach uses a lightweight pose graph optimization algorithm to correct pose drift and updates Gaussians based on the optimized poses. Additionally, a bundle adjustment scheme further refines camera poses using photometric and geometric constraints, ultimately enhancing the global consistency of scenarios. Quantitative and qualitative evaluations on both synthetic and real-world datasets demonstrate that our method outperforms state-of-the-art methods in camera pose estimation and novel view rendering tasks. The code will be open-sourced for the community.

cs.RO↗

arXiv2024

LiLoc: Lifelong Localization using Adaptive Submap Joining and Egocentric Factor Graph

This paper proposes a versatile graph-based lifelong localization framework, LiLoc, which enhances its timeliness by maintaining a single central session while improves the accuracy through multi-modal factors between the central and subsidiary sessions. First, an adaptive submap joining strategy is employed to generate prior submaps (keyframes and poses) for the central session, and to provide priors for subsidiaries when constraints are needed for robust localization. Next, a coarse-to-fine pose initialization for subsidiary sessions is performed using vertical recognition and ICP refinement in the global coordinate frame. To elevate the accuracy of subsequent localization, we propose an egocentric factor graph (EFG) module that integrates the IMU preintegration, LiDAR odometry and scan match factors in a joint optimization manner. Specifically, the scan match factors are constructed by a novel propagation model that efficiently distributes the prior constrains as edges to the relevant prior pose nodes, weighted by noises based on keyframe registration errors. Additionally, the framework supports flexible switching between two modes: relocalization (RLM) and incremental localization (ILM) based on the proposed overlap-based mechanism to select or update the prior submaps from central session. The proposed LiLoc is tested on public and custom datasets, demonstrating accurate localization performance against state-of-the-art methods. Our codes will be publicly available on https://github.com/Yixin-F/LiLoc.

cs.RO↗

arXiv2024

RevGNN: Negative Sampling Enhanced Contrastive Graph Learning for Academic Reviewer Recommendation

Acquiring reviewers for academic submissions is a challenging recommendation scenario. Recent graph learning-driven models have made remarkable progress in the field of recommendation, but their performance in the academic reviewer recommendation task may suffer from a significant false negative issue. This arises from the assumption that unobserved edges represent negative samples. In fact, the mechanism of anonymous review results in inadequate exposure of interactions between reviewers and submissions, leading to a higher number of unobserved interactions compared to those caused by reviewers declining to participate. Therefore, investigating how to better comprehend the negative labeling of unobserved interactions in academic reviewer recommendations is a significant challenge. This study aims to tackle the ambiguous nature of unobserved interactions in academic reviewer recommendations. Specifically, we propose an unsupervised Pseudo Neg-Label strategy to enhance graph contrastive learning (GCL) for recommending reviewers for academic submissions, which we call RevGNN. RevGNN utilizes a two-stage encoder structure that encodes both scientific knowledge and behavior using Pseudo Neg-Label to approximate review preference. Extensive experiments on three real-world datasets demonstrate that RevGNN outperforms all baselines across four metrics. Additionally, detailed further analyses confirm the effectiveness of each component in RevGNN.

cs.IR↗

arXiv2024

GeoGaussian: Geometry-aware Gaussian Splatting for Scene Rendering

During the Gaussian Splatting optimization process, the scene's geometry can gradually deteriorate if its structure is not deliberately preserved, especially in non-textured regions such as walls, ceilings, and furniture surfaces. This degradation significantly affects the rendering quality of novel views that deviate significantly from the viewpoints in the training data. To mitigate this issue, we propose a novel approach called GeoGaussian. Based on the smoothly connected areas observed from point clouds, this method introduces a novel pipeline to initialize thin Gaussians aligned with the surfaces, where the characteristic can be transferred to new generations through a carefully designed densification strategy. Finally, the pipeline ensures that the scene's geometry and texture are maintained through constrained optimization processes with explicit geometry constraints. Benefiting from the proposed architecture, the generative ability of 3D Gaussians is enhanced, especially in structured regions. Our proposed pipeline achieves state-of-the-art performance in novel view synthesis and geometric reconstruction, as evaluated qualitatively and quantitatively on public datasets.

cs.CV↗

arXiv2024

ShapeMatcher: Self-Supervised Joint Shape Canonicalization, Segmentation, Retrieval and Deformation

In this paper, we present ShapeMatcher, a unified self-supervised learning framework for joint shape canonicalization, segmentation, retrieval and deformation. Given a partially-observed object in an arbitrary pose, we first canonicalize the object by extracting point-wise affine-invariant features, disentangling inherent structure of the object with its pose and size. These learned features are then leveraged to predict semantically consistent part segmentation and corresponding part centers. Next, our lightweight retrieval module aggregates the features within each part as its retrieval token and compare all the tokens with source shapes from a pre-established database to identify the most geometrically similar shape. Finally, we deform the retrieved shape in the deformation module to tightly fit the input object by harnessing part center guided neural cage deformation. The key insight of ShapeMaker is the simultaneous training of the four highly-associated processes: canonicalization, segmentation, retrieval, and deformation, leveraging cross-task consistency losses for mutual supervision. Extensive experiments on synthetic datasets PartNet, ComplementMe, and real-world dataset Scan2CAD demonstrate that ShapeMaker surpasses competitors by a large margin.

cs.CV↗

arXiv2024

A Bi-variant Variational Model for Diffeomorphic Image Registration with Relaxed Jacobian Determinant Constraints

Diffeomorphic registration is a widely used technique for finding a smooth and invertible transformation between two coordinate systems, which are measured using template and reference images. The point-wise volume-preserving constraint $\det(\nabla\bmφ(\bm{x})) =1$ is effective in some cases, but may be too restrictive in others, especially when local deformations are relatively large. This can result in poor matching when enforcing large local deformations. In this paper, we propose a new bi-variant diffeomorphic image registration model that introduces a soft constraint on the Jacobian equation $\det(\nabla\bmφ(\bm{x})) = f(\bm{x}) > 0$. This allows local deformations to shrink and grow within a flexible range $0<κ_{m}<\det(\nabla\bmφ(\bm{x}))<κ_{M}$. The Jacobian determinant of transformation is explicitly controlled by optimizing the relaxation function $f(\bm{x})$. To prevent deformation folding and improve the smoothness of the transformation, a positive constraint is imposed on the optimization of the relaxation function $f(\bm{x})$, and a regularizer is used to ensure the smoothness of $f(\bm{x})$. Furthermore, the positivity constraint ensures that $f(\bm{x})$ is as close to one as possible, which helps to achieve a volume-preserving transformation on average. We also analyze the existence of the minimizer for the variational model and propose a penalty-splitting algorithm with a multilevel strategy to solve this model. Numerical experiments demonstrate the convergence of the proposed algorithm and show that the positivity constraint can effectively control the range of relative volume without compromising the accuracy of the registration. Moreover, the proposed model generates diffeomorphic maps for large local deformations and outperforms several existing registration models in terms of performance.

cs.CV↗

arXiv2023

A Liouville theorem in the Heisenberg group

In this paper we classify positive solutions to the critical semilinear elliptic equation in $\mathbb{H}^n$. We prove that they are the Jerison-Lee's bubbles, provided $n=1$ or $n\geq 2$ and a suitable control at infinity holds. The proofs are based on a classical Jerison-Lee's differential identity and on pointwise/integral estimates recently obtained for critical semilinear and quasilinear elliptic equations in $\mathbb{R}^n$. In particular, the result in $\mathbb{H}^1$ can be seen as the analogue of the celebrated Caffarelli-Gidas-Spruck classification theorem.

math.AP↗

arXiv2023

Towards Table-to-Text Generation with Pretrained Language Model: A Table Structure Understanding and Text Deliberating Approach

Although remarkable progress on the neural table-to-text methods has been made, the generalization issues hinder the applicability of these models due to the limited source tables. Large-scale pretrained language models sound like a promising solution to tackle such issues. However, how to effectively bridge the gap between the structured table and the text input by fully leveraging table information to fuel the pretrained model is still not well explored. Besides, another challenge of integrating the deliberation mechanism into the text-to-text pretrained model for solving the table-to-text task remains seldom studied. In this paper, to implement the table-to-text generation with pretrained language model, we propose a table structure understanding and text deliberating approach, namely TASD. Specifically, we devise a three-layered multi-head attention network to realize the table-structure-aware text generation model with the help of the pretrained language model. Furthermore, a multi-pass decoder framework is adopted to enhance the capability of polishing generated text for table descriptions. The empirical studies, as well as human evaluation, on two public datasets, validate that our approach can generate faithful and fluent descriptive texts for different types of tables.

cs.CL↗

arXiv2022

E-Graph: Minimal Solution for Rigid Rotation with Extensibility Graphs

Minimal solutions for relative rotation and translation estimation tasks have been explored in different scenarios, typically relying on the so-called co-visibility graph. However, how to build direct rotation relationships between two frames without overlap is still an open topic, which, if solved, could greatly improve the accuracy of visual odometry. In this paper, a new minimal solution is proposed to solve relative rotation estimation between two images without overlapping areas by exploiting a new graph structure, which we call Extensibility Graph (E-Graph). Differently from a co-visibility graph, high-level landmarks, including vanishing directions and plane normals, are stored in our E-Graph, which are geometrically extensible. Based on E-Graph, the rotation estimation problem becomes simpler and more elegant, as it can deal with pure rotational motion and requires fewer assumptions, e.g. Manhattan/Atlanta World, planar/vertical motion. Finally, we embed our rotation estimation strategy into a complete camera tracking and mapping system which obtains 6-DoF camera poses and a dense 3D mesh model. Extensive experiments on public benchmarks demonstrate that the proposed method achieves state-of-the-art tracking performance.

cs.CV↗

arXiv2022

Gradient estimates for the insulated conductivity problem: the non-umbilical case

We study the insulated conductivity problem with inclusions embedded in a bounded domain in $\mathbb R^n$, for $n \ge 3$. The gradient of solutions may blow up as $\varepsilon$, the distance between inclusions, approaches to $0$. We established in a recent paper optimal gradient estimates for a class of inclusions including balls. In this paper, we prove such gradient estimates for general strictly convex inclusions. Unlike the perfect conductivity problem, the estimates depend on the principal curvatures of the inclusions, and we show that these estimates are characterized by the first non-zero eigenvalue of a divergence form elliptic operator on $\mathbb S^{n-2}$.

math.AP↗

arXiv2021

Time-free solution to independent set problem using P systems with active membranes

Membrane computing is a branch of natural computingwhich abstracts fromthe structure and the functioning of living cells. The computation models obtained in the field of membrane computing are usually called P systems. P systems have been used to solve computationally hard problems efficiently on the assumption that the execution of each rule is completed in exactly one time-unit (a global clock is assumed for timing and synchronizing the execution of rules). However, in biological reality, different biological processes take different times to be completed, which can also be influenced by many environmental factors. In this work, with this biological reality, we give a time-free solution to independent set problemusing P systems with active membranes, which solve the problem independent of the execution time of the involved rules.

cs.CC↗

arXiv2021

Semantic Dense Reconstruction with Consistent Scene Segments

In this paper, a method for dense semantic 3D scene reconstruction from an RGB-D sequence is proposed to solve high-level scene understanding tasks. First, each RGB-D pair is consistently segmented into 2D semantic maps based on a camera tracking backbone that propagates objects' labels with high probabilities from full scans to corresponding ones of partial views. Then a dense 3D mesh model of an unknown environment is incrementally generated from the input RGB-D sequence. Benefiting from 2D consistent semantic segments and the 3D model, a novel semantic projection block (SP-Block) is proposed to extract deep feature volumes from 2D segments of different views. Moreover, the semantic volumes are fused into deep volumes from a point cloud encoder to make the final semantic segmentation. Extensive experimental evaluations on public datasets show that our system achieves accurate 3D dense reconstruction and state-of-the-art semantic prediction performances simultaneously.

cs.CV↗

arXiv2021

Adversarial Neural Trip Recommendation

Trip recommender system, which targets at recommending a trip consisting of several ordered Points of Interest (POIs), has long been treated as an important application for many location-based services. Currently, most prior arts generate trips following pre-defined objectives based on constraint programming, which may fail to reflect the complex latent patterns hidden in the human mobility data. And most of these methods are usually difficult to respond in real time when the number of POIs is large. To that end, we propose an Adversarial Neural Trip Recommendation (ANT) framework to tackle the above challenges. First of all, we devise a novel attention-based encoder-decoder trip generator that can learn the correlations among POIs and generate well-designed trips under given constraints. Another novelty of ANT relies on an adversarial learning strategy integrating with reinforcement learning to guide the trip generator to produce high-quality trips. For this purpose, we introduce a discriminator, which distinguishes the generated trips from real-life trips taken by users, to provide reward signals to optimize the generator. Moreover, we devise a novel pre-train schema based on learning from demonstration, which speeds up the convergence to achieve a sufficient-and-efficient training process. Extensive experiments on four real-world datasets validate the effectiveness and efficiency of our proposed ANT framework, which demonstrates that ANT could remarkably outperform the state-of-the-art baselines with short response time.

cs.LG↗

arXiv2021

Diffeomorphic Image Registration with An Optimal Control Relaxation and Its Implementation

Image registration has played an important role in image processing problems, especially in medical imaging applications. It is well known that when the deformation is large, many variational models cannot ensure diffeomorphism. In this paper, we propose a new registration model based on an optimal control relaxation constraint for large deformation images, which can theoretically guarantee that the registration mapping is diffeomorphic. We present an analysis of optimal control relaxation for indirectly seeking the diffeomorphic transformation of Jacobian determinant equation and its registration applications, including the construction of diffeomorphic transformation as a special space. We also provide an existence result for the control increment optimization problem in the proposed diffeomorphic image registration model with an optimal control relaxation. Furthermore, a fast iterative scheme based on the augmented Lagrangian multipliers method (ALMM) is analyzed to solve the control increment optimization problem, and a convergence analysis is followed. Finally, a grid unfolding indicator is given, and a robust solving algorithm for using the deformation correction and backtrack strategy is proposed to guarantee that the solution is diffeomorphic. Numerical experiments show that the registration model we proposed can not only get a diffeomorphic mapping when the deformation is large, but also achieves the state-of-the-art performance in quantitative evaluations in comparing with other classical models.

math.NA↗

arXiv2021

The axisymmetric $σ_k$-Nirenberg problem

We study the problem of prescribing $σ_k$-curvature for a conformal metric on the standard sphere $\mathbb{S}^n$ with $2 \leq k < n/2$ and $n \geq 5$ in axisymmetry. Compactness, non-compactness, existence and non-existence results are proved in terms of the behaviors of the prescribed curvature function $K$ near the north and the south poles. For example, consider the case when the north and the south poles are local maximum points of $K$ of flatness order $β\in [2,n)$. We prove among other things the following statements. (1) When $β>n-2k$, the solution set is compact, has a nonzero total degree counting and is therefore non-empty. (2) When $ β= n-2k$, there is an explicit positive constant $C(K)$ associated with $K$. If $C(K)>1$, the solution set is compact with a nonzero total degree counting and is therefore non-empty. If $C(K)<1$, the solution set is compact but the total degree counting is $0$, and the solution set is sometimes empty and sometimes non-empty. (3) When $\frac{2}{n-2k}\le β< n-2k$, the solution set is compact, but the total degree counting is zero, and the solution set is sometimes empty and sometimes non-empty. (4) When $β< \frac{n-2k}{2}$, there exists $K$ for which there exists a blow-up sequence of solutions with unbounded energy. In this same range of $β$, there exists also some $K$ for which the solution set is empty.

math.AP↗

arXiv2021

SRH-Net: Stacked Recurrent Hourglass Network for Stereo Matching

The cost aggregation strategy shows a crucial role in learning-based stereo matching tasks, where 3D convolutional filters obtain state of the art but require intensive computation resources, while 2D operations need less GPU memory but are sensitive to domain shift. In this paper, we decouple the 4D cubic cost volume used by 3D convolutional filters into sequential cost maps along the direction of disparity instead of dealing with it at once by exploiting a recurrent cost aggregation strategy. Furthermore, a novel recurrent module, Stacked Recurrent Hourglass (SRH), is proposed to process each cost map. Our hourglass network is constructed based on Gated Recurrent Units (GRUs) and down/upsampling layers, which provides GRUs larger receptive fields. Then two hourglass networks are stacked together, while multi-scale information is processed by skip connections to enhance the performance of the pipeline in textureless areas. The proposed architecture is implemented in an end-to-end pipeline and evaluated on public datasets, which reduces GPU memory consumption by up to 56.1\% compared with PSMNet using stacked hourglass 3D CNNs without the degradation of accuracy. Then, we further demonstrate the scalability of the proposed method on several high-resolution pairs, while previously learned approaches often fail due to the memory constraint. The code is released at \url{https://github.com/hongzhidu/SRHNet}.

cs.CV↗

arXiv2021

Symmetry of hypersurfaces with ordered mean curvature in one direction

For a connected $n$-dimensional compact smooth hypersurface $M$ without boundary embedded in $\mathbb{R}^{n+1}$, a classical result of Aleksandrov shows that it must be a sphere if it has constant mean curvature. Li and Nirenberg studied a one-directional analog of this result: if every pair of points $(x',a), (x',b)\in M$ with $a<b$ has ordered mean curvature $H(x',b)\leq H(x',a)$, then $M$ is symmetric about some hyperplane $x_{n+1}=c$ under some additional conditions. Their proof was done by the moving plane method and some variations of the Hopf Lemma. We obtain the symmetry of $M$ under some weaker assumptions using a variational argument, giving a positive answer to the conjecture given by Li and Nirenberg.

math.AP↗