arXiv subjects

Shuqin Gao

Publications and source records attributed to Shuqin Gao.

10 recordsLinked to original sources

arXiv2026

MetroGS: Efficient and Stable Reconstruction of Geometrically Accurate High-Fidelity Large-Scale Scenes

Recently, 3D Gaussian Splatting and its derivatives have achieved significant breakthroughs in large-scale scene reconstruction. However, how to efficiently and stably achieve high-quality geometric fidelity remains a core challenge. To address this issue, we introduce MetroGS, a novel Gaussian Splatting framework for efficient and robust reconstruction in complex urban environments. Our method is built upon a distributed 2D Gaussian Splatting representation as the core foundation, serving as a unified backbone for subsequent modules. To handle potential sparse regions in complex scenes, we propose a structured dense enhancement scheme that utilizes SfM priors and a pointmap model to achieve a denser initialization, while incorporating a sparsity compensation mechanism to improve reconstruction completeness. Furthermore, we design a progressive hybrid geometric optimization strategy that organically integrates monocular and multi-view optimization to achieve efficient and accurate geometric refinement. Finally, to address the appearance inconsistency commonly observed in large-scale scenes, we introduce a depth-guided appearance modeling approach that learns spatial features with 3D consistency, facilitating effective decoupling between geometry and appearance and further enhancing reconstruction stability. Experiments on large-scale urban datasets demonstrate that MetroGS achieves superior geometric accuracy, rendering quality, offering a unified solution for high-fidelity large-scale scene reconstruction.

cs.CV↗

arXiv2026

TreeGaussian: Tree-Guided Cascaded Contrastive Learning for Hierarchical Consistent 3D Gaussian Scene Segmentation and Understanding

3D Gaussian Splatting (3DGS) has emerged as a real-time, differentiable representation for neural scene understanding. However, existing 3DGS-based methods struggle to represent hierarchical 3D semantic structures and capture whole-part relationships in complex scenes. Moreover, dense pairwise comparisons and inconsistent hierarchical labels from 2D priors hinder feature learning, resulting in suboptimal segmentation. To address these limitations, we introduce TreeGaussian, a tree-guided cascaded contrastive learning framework that explicitly models hierarchical semantic relationships and reduces redundancy in contrastive supervision. By constructing a multi-level object tree, TreeGaussian enables structured learning across object-part hierarchies. In addition, we propose a two-stage cascaded contrastive learning strategy that progressively refines feature representations from global to local, mitigating saturation and stabilizing training. A Consistent Segmentation Detection (CSD) mechanism and a graph-based denoising module are further introduced to align segmentation modes across views while suppressing unstable Gaussian points, enhancing segmentation consistency and quality. Extensive experiments, including open-vocabulary 3D object selection, 3D point cloud understanding, and ablation studies, demonstrate the effectiveness and robustness of our approach.

cs.CV↗

arXiv2025

HAIF-GS: Hierarchical and Induced Flow-Guided Gaussian Splatting for Dynamic Scene

Reconstructing dynamic 3D scenes from monocular videos remains a fundamental challenge in 3D vision. While 3D Gaussian Splatting (3DGS) achieves real-time rendering in static settings, extending it to dynamic scenes is challenging due to the difficulty of learning structured and temporally consistent motion representations. This challenge often manifests as three limitations in existing methods: redundant Gaussian updates, insufficient motion supervision, and weak modeling of complex non-rigid deformations. These issues collectively hinder coherent and efficient dynamic reconstruction. To address these limitations, we propose HAIF-GS, a unified framework that enables structured and consistent dynamic modeling through sparse anchor-driven deformation. It first identifies motion-relevant regions via an Anchor Filter to suppress redundant updates in static areas. A self-supervised Induced Flow-Guided Deformation module induces anchor motion using multi-frame feature aggregation, eliminating the need for explicit flow labels. To further handle fine-grained deformations, a Hierarchical Anchor Propagation mechanism increases anchor resolution based on motion complexity and propagates multi-level transformations. Extensive experiments on synthetic and real-world benchmarks validate that HAIF-GS significantly outperforms prior dynamic 3DGS methods in rendering quality, temporal coherence, and reconstruction efficiency.

cs.CV↗

arXiv2025

From Tokens to Nodes: Semantic-Guided Motion Control for Dynamic 3D Gaussian Splatting

Dynamic 3D reconstruction from monocular videos remains difficult due to the ambiguity inferring 3D motion from limited views and computational demands of modeling temporally varying scenes. While recent sparse control methods alleviate computation by reducing millions of Gaussians to thousands of control points, they suffer from a critical limitation: they allocate points purely by geometry, leading to static redundancy and dynamic insufficiency. We propose a motion-adaptive framework that aligns control density with motion complexity. Leveraging semantic and motion priors from vision foundation models, we establish patch-token-node correspondences and apply motion-adaptive compression to concentrate control points in dynamic regions while suppressing redundancy in static backgrounds. Our approach achieves flexible representational density adaptation through iterative voxelization and motion tendency scoring, directly addressing the fundamental mismatch between control point allocation and motion complexity. To capture temporal evolution, we introduce spline-based trajectory parameterization initialized by 2D tracklets, replacing MLP-based deformation fields to achieve smoother motion representation and more stable optimization. Extensive experiments demonstrate significant improvements in reconstruction quality and efficiency over existing state-of-the-art methods.

cs.CV↗

arXiv2025

STDR: Spatio-Temporal Decoupling for Real-Time Dynamic Scene Rendering

Although dynamic scene reconstruction has long been a fundamental challenge in 3D vision, the recent emergence of 3D Gaussian Splatting (3DGS) offers a promising direction by enabling high-quality, real-time rendering through explicit Gaussian primitives. However, existing 3DGS-based methods for dynamic reconstruction often suffer from \textit{spatio-temporal incoherence} during initialization, where canonical Gaussians are constructed by aggregating observations from multiple frames without temporal distinction. This results in spatio-temporally entangled representations, making it difficult to model dynamic motion accurately. To overcome this limitation, we propose \textbf{STDR} (Spatio-Temporal Decoupling for Real-time rendering), a plug-and-play module that learns spatio-temporal probability distributions for each Gaussian. STDR introduces a spatio-temporal mask, a separated deformation field, and a consistency regularization to jointly disentangle spatial and temporal patterns. Extensive experiments demonstrate that incorporating our module into existing 3DGS-based dynamic scene reconstruction frameworks leads to notable improvements in both reconstruction quality and spatio-temporal consistency across synthetic and real-world benchmarks.

cs.GR↗

arXiv2024

GradiSeg: Gradient-Guided Gaussian Segmentation with Enhanced 3D Boundary Precision

While 3D Gaussian Splatting enables high-quality real-time rendering, existing Gaussian-based frameworks for 3D semantic segmentation still face significant challenges in boundary recognition accuracy. To address this, we propose a novel 3DGS-based framework named GradiSeg, incorporating Identity Encoding to construct a deeper semantic understanding of scenes. Our approach introduces two key modules: Identity Gradient Guided Densification (IGD) and Local Adaptive K-Nearest Neighbors (LA-KNN). The IGD module supervises gradients of Identity Encoding to refine Gaussian distributions along object boundaries, aligning them closely with boundary contours. Meanwhile, the LA-KNN module employs position gradients to adaptively establish locality-aware propagation of Identity Encodings, preventing irregular Gaussian spreads near boundaries. We validate the effectiveness of our method through comprehensive experiments. Results show that GradiSeg effectively addresses boundary-related issues, significantly improving segmentation accuracy without compromising scene reconstruction quality. Furthermore, our method's robust segmentation capability and decoupled Identity Encoding representation make it highly suitable for various downstream scene editing tasks, including 3D object removal, swapping and so on.

cs.CV↗

arXiv2024

The Impact of Autonomous Vehicles on Ride-Hailing Platforms with Strategic Human Drivers

Motivated by the rapid development of autonomous vehicle technology, this work focuses on the challenges of introducing them in ride-hailing platforms with conventional strategic human drivers. We consider a ride-hailing platform that operates a mixed fleet of autonomous vehicles (AVs) and conventional vehicles (CVs), where AVs are fully controlled by the platform and CVs are operated by self-interested human drivers. Each vehicle is modelled as a Markov Decision Process that maximizes long-run average reward by choosing its repositioning actions. The behavior of the CVs corresponds to a large game where agents interact through resource constraints that result in queuing delays. In our fluid model, drivers may wait in queues in the different regions when the supply of drivers tends to exceed the service demand by customers. Our primary objective is to optimize the mixed AV-CV system so that the total profit of the platform generated by AVs and CVs is maximized. To achieve that, we formulate this problem as a bi-level optimization problem OPT where the platform moves first by controlling the actions of the AVs and the demand revealed to CVs, and then the CVs react to the revealed demand by forming an equilibrium that can be characterized by the solution of a convex optimization problem. We prove several interesting structural properties of the optimal solution and analyze simple heuristics such as AV-first where we solve for the optimal dispatch of AVs without taking into account the subsequent reaction of the CVs. We propose three numerical algorithms to solve OPT which is a non-convex problem in the platform decision parameters. We evaluate their performance and use them to show some interesting trends in the optimal AV-CV fleet dimensioning when supply is exogenous and endogenous.

cs.GT↗

arXiv2023

Average-Case Analysis of Greedy Matching for Large-Scale D2D Resource Sharing

Given the proximity of many wireless users and their diversity in consuming local resources (e.g., data-plans, computation and energy resources), device-to-device (D2D) resource sharing is a promising approach towards realizing a sharing economy. This paper adopts an easy-to-implement greedy matching algorithm with distributed fashion and only sub-linear O(log n) parallel complexity (in user number n) for large-scale D2D sharing. Practical cases indicate that the greedy matching's average performance is far better than the worst-case approximation ratio 50% as compared to the optimum. However, there is no rigorous average-case analysis in the literature to back up such encouraging findings and this paper is the first to present such analysis for multiple representative classes of graphs. For 1D linear networks, we prove that our greedy algorithm performs better than 86.5% of the optimum. For 2D grids, though dynamic programming cannot be directly applied, we still prove this average performance ratio to be above 76%. For the more challenging Erdos-Renyi random graphs, we equivalently reduce to the asymptotic analysis of random trees and successfully prove a ratio up to 79%. Finally, we conduct experiments using real data to simulate realistic D2D networks, and show that our analytical performance measure approximates well practical cases.

cs.DC↗

arXiv2021

Average-Case Analysis of Greedy Matching for D2D Resource Sharing

Given the proximity of many wireless users and their diversity in consuming local resources (e.g., data-plans, computation and even energy resources), device-to-device (D2D) resource sharing is a promising approach towards realizing a sharing economy. In the resulting networked economy, $n$ users segment themselves into sellers and buyers that need to be efficiently matched locally. This paper adopts an easy-to-implement greedy matching algorithm with distributed fashion and only sub-linear $O(\log n)$ parallel complexity, which offers a great advantage compared to the optimal but computational-expensive centralized matching. But is it efficient compared to the optimal matching? Extensive simulations indicate that in a large number of practical cases the average loss is no more than $10\%$, a far better result than the $50\%$ loss bound in the worst case. However, there is no rigorous average-case analysis in the literature to back up such encouraging findings, which is a fundamental step towards supporting the practical use of greedy matching in D2D sharing. This paper is the first to present the rigorous average analysis of certain representative classes of graphs with random parameters, by proposing a new asymptotic methodology. For typical 2D grids with random matching weights we rigorously prove that our greedy algorithm performs better than $84.9\%$ of the optimal, while for typical Erdos-Renyi random graphs we prove a lower bound of $79\%$ when the graph is neither dense nor sparse. Finally, we use realistic data to show that our random graph models approximate well D2D sharing networks encountered in practice.

cs.DC↗

arXiv2020

Distributed Double Auctions for Large-Scale Device-to-Device Resource Trading

Mobile users in future wireless networks face limited wireless resources such as data plan, computation capacity and energy storage. Given that some of these users may not be utilizing fully their wireless resources, device-to-device (D2D) resource sharing is a promising approach to exploit users' diversity in resource use and for pooling their resources locally. In this paper, we propose a novel two-sided D2D trading market model that enables a large number of locally connected users to trade resources. Traditional resource allocation solutions are mostly centralized without considering users' local D2D connectivity constraints, becoming unscalable for large-scale trading. In addition, there may be market failure since selfish users will not truthfully report their actual valuations and quantities for buying or selling resources. To address these two key challenges, we first investigate the distributed resource allocation problem with D2D assignment constraints. Based on the greedy idea of maximum weighted matching, we propose a fast algorithm to achieve near-optimal average allocative efficiency. Then, we combine it with a new pricing mechanism that adjusts the final trading prices for buying and selling resources in a way that buyers and sellers are incentivized to truthfully report their valuations and available resource quantities. Unlike traditional double auctions with a central controller, this pricing mechanism is fully distributed in the sense that the final trading prices between each matched pair of users only depend on their own declarations and hence can be calculated locally. Finally, we analyze the repeated execution of the proposed D2D trading mechanism in multiple rounds and determine the best trading frequency.

cs.GT↗