arXiv subjects

Songhua Li

Publications and source records attributed to Songhua Li.

8 recordsLinked to original sources

arXiv2026

VGGT-Align: Bridging Local Reconstruction and Global Consistency for Long-Sequence 3D Reconstruction

Maintaining global geometric consistency is a central challenge in long-sequence 3D reconstruction, with scale drift being the most critical failure mode. In chunk-based inference pipelines, the scale degree of freedom in sequential Sim(3) alignment is left unconstrained, causing estimation errors to compound multiplicatively and distort global trajectories and point cloud geometry. We present a scale-consistency enhancement framework built on a key insight: in structured environments such as driving scenes, geometric quantities arising from environmental regularity remain inherently invariant across temporal segments, and discrepancies in their per-chunk measurements directly expose inter-chunk scale drift. We propose Scene Geometric Invariant Anchoring (SGIA), which extracts dominant geometric invariants from each chunk's predicted point cloud via coarse-to-fine robust estimation and exploits their cross-chunk consistency to establish scale constraints independent of point cloud registration, explicitly degenerating 7-DoF Sim(3) alignment into 6-DoF rigid-body transformation and severing chain-wise scale error propagation at its source. We further introduce a lightweight test-time adaptation strategy that fine-tunes only normalization-layer parameters via multi-objective self-supervision, progressively improving intra-chunk predictions along the sequence. Both modules are plug-and-play and require no offline retraining. Experiments on multiple long-sequence benchmarks demonstrate state-of-the-art performance, reducing absolute trajectory error by up to 32% with significant gains in trajectory stability and reconstruction quality. Code: https://github.com/WZ-CS/VGGT-Align

cs.CV↗

arXiv2026

VGGT-CD: Training-Free Robust Registration for 3D Change Detection

3D change detection from multi-view images is essential for urban monitoring, disaster assessment, and autonomous driving. However, existing methods predominantly operate in the 2D domain, where viewpoint variations are mistaken for physical changes and depth is unavailable. While visual geometry foundation models like VGGT rapidly produce dense point clouds from unposed images, independent per-epoch reconstruction encounters fundamental obstacles: unpredictable inter-epoch scale ambiguity, registration-change paradox where scene changes corrupt alignment, and pervasive edge-flying noise. To address these challenges, we present VGGT-CD, a training-free pipeline decoupling cross-temporal registration from dynamic-change interference. In the Coarse Stage, sparse keyframe joint inference establishes a unified metric space and yields an initial Sim(3) prior. In the Fine Stage, dense reconstructions are purified by isolating static-background correspondences. A closed-form centroid alignment refines the translation while locking scale and rotation, using a residual self-check to mathematically guarantee non-degradation. Evaluated on an 11-scene benchmark from the World Across Time dataset, VGGT-CD reduces Absolute Trajectory Error by 44% outdoors and 59% indoors. It completes registration over 6 times faster, producing high-purity 3D change maps without task-specific training.

cs.CV↗

arXiv2025

Review of Feed-forward 3D Reconstruction: From DUSt3R to VGGT

3D reconstruction, which aims to recover the dense three-dimensional structure of a scene, is a cornerstone technology for numerous applications, including augmented/virtual reality, autonomous driving, and robotics. While traditional pipelines like Structure from Motion (SfM) and Multi-View Stereo (MVS) achieve high precision through iterative optimization, they are limited by complex workflows, high computational cost, and poor robustness in challenging scenarios like texture-less regions. Recently, deep learning has catalyzed a paradigm shift in 3D reconstruction. A new family of models, exemplified by DUSt3R, has pioneered a feed-forward approach. These models employ a unified deep network to jointly infer camera poses and dense geometry directly from an Unconstrained set of images in a single forward pass. This survey provides a systematic review of this emerging domain. We begin by dissecting the technical framework of these feed-forward models, including their Transformer-based correspondence modeling, joint pose and geometry regression mechanisms, and strategies for scaling from two-view to multi-view scenarios. To highlight the disruptive nature of this new paradigm, we contrast it with both traditional pipelines and earlier learning-based methods like MVSNet. Furthermore, we provide an overview of relevant datasets and evaluation metrics. Finally, we discuss the technology's broad application prospects and identify key future challenges and opportunities, such as model accuracy and scalability, and handling dynamic scenes.

cs.CV↗

arXiv2023

Staying Fresh: Efficient Algorithms for Timely Social Information Distribution

In location-based social networks (LBSNs), users sense urban point-of-interest (PoI) information in the vicinity and share such information with friends in online social networks. Given users' limited social connections and severe lags in disseminating fresh PoI to all, major LBSNs aim to enhance users' social PoI sharing by selecting $k$ out of $m$ users as hotspots and broadcasting their fresh PoI information to the entire user community. This motivates us to study a new combinatorial optimization problem that involves the interplay between an urban sensing network and an online social network. We prove that this problem is NP-hard and also renders existing approximation solutions not viable. Through analyzing the interplay effects between the two networks, we successfully transform the involved PoI-sharing process across two networks to matrix computations for deriving a closed-form objective to hold desirable properties (e.g., submodularity and monotonicity). This finding enables us to develop a polynomial-time algorithm that guarantees a ($1-\frac{m-2}{m}(\frac{k-1}{k})^k$) approximation of the optimum. Furthermore, we allow each selected user to move around and sense more PoI information to share and propose an augmentation-adaptive algorithm with decent performance guarantees. Finally, our theoretical results are corroborated by our simulation findings using both synthetic and real-world datasets.

cs.SI↗

arXiv2023

On Incentivizing Social Information Sharing Through Routing Games

Crowdsourcing services, such as Waze, leverage a mass of mobile users to learn massive point-of-interest (PoI) information while traveling and share it as a public good. Given that crowdsourced users mind their travel costs and possess various preferences over the PoI information along different paths, we formulate the problem as a novel non-atomic multi-path routing game with positive network externalities among users in social information sharing. In the absence of any incentive design, our price of anarchy (PoA) analysis shows that users' selfish routing on the path with the lowest cost will limit information diversity and lead to $PoA = 0$ with an arbitrarily large efficiency loss from the social optimum. This motivates us to design effective incentive mechanisms to remedy while upholding desirable properties such as individual rationality, incentive compatibility, and budget balance for practical users. Without requiring a specific user's path preference, we present a non-monetary mechanism called Adaptive Information Restriction (AIR) that reduces non-cooperative users' access to the public good as an indirect penalty, which meets all the desirable properties. By meticulously adapting penalty fractions to the actual user flows along different paths, our AIR achieves non-trivial $PoA = \frac{1}{4}$ with low complexity $O(k\log k+\log m)$, where $k$ and $m$ denote the numbers of involved paths and user types, respectively. If the system can further enable pricing for users, we then propose a new monetary mechanism called Adaptive Side-Payment (ASP), which adaptively charges and rewards users according to their chosen paths, respectively. Our ASP mechanism successively achieves a $PoA = \frac{1}{2}$ with even reduced complexity $O(k\log k)$. Finally, our theoretical findings are well corroborated by our experimental results using a real-world public dataset.

cs.GT↗

arXiv2023

Age of Information Diffusion on Social Networks

To promote viral marketing, major social platforms (e.g., Facebook Marketplace and Pinduoduo) repeatedly select and invite different users (as seeds) in online social networks to share fresh information about a product or service with their friends. Thereby, we are motivated to optimize a multi-stage seeding process of viral marketing in social networks, and adopt the recent notions of the peak and the average age of information (AoI) to measure the timeliness of promotion information received by network users. Our problem is different from the literature on information diffusion in social networks, which limits to one-time seeding and overlooks AoI dynamics or information replacement over time. As a critical step, we manage to develop closed-form expressions that characterize and trace AoI dynamics over any social network. For the peak AoI problem, we first prove the NP-hardness of our multi-stage seeding problem by a highly non-straightforward reduction from the dominating set problem, and then present a new polynomial-time algorithm that achieves good approximation guarantees (e.g., less than 2 for linear network topology). To minimize the average AoI, we also prove that our problem is NP-hard by properly reducing it from the set cover problem. Benefiting from our two-sided bound analysis on the average AoI objective, we build up a new framework for approximation analysis and link our problem to a much simplified sum-distance minimization problem. This intriguing connection inspires us to develop another polynomial-time algorithm that achieves a good approximation guarantee. Additionally, our theoretical results are well corroborated by experiments on a real social network.

cs.SI↗

arXiv2021

Online Ride-Hitching in UAV Travelling

The unmanned aerial vehicle (UAV) has emerged as a promising solution to provide delivery and other mobile services to customers rapidly, yet it drains its stored energy quickly when travelling on the way and (even if solar-powered) it takes time for charging power on the way before reaching the destination. To address this issue, existing works focus more on UAV's path planning with designated system vehicles providing charging service. However, in some emergency cases and rural areas where system vehicles are not available, public trucks can provide more feasible and cost-saving services and hence a silver lining. In this paper, we explore how a single UAV can save flying distance by exploiting public trucks, to minimize the travel time of the UAV. We give the first theoretical work studying online algorithms for the problem, which guarantees a worst-case performance. We first consider the offline problem knowing future truck trip information far ahead of time. By delicately transforming the problem into a graph satisfying both time and power constraints, we present a shortest-path algorithm that outputs the optimal solution of the problem. Then, we proceed to the online setting where trucks appear in real-time and only inform the UAV of their trip information some certain time $Δt$ beforehand. As a benchmark, we propose a well-constructed lower bound that an online algorithm could achieve. We propose an online algorithm MyopicHitching that greedily takes truck trips and an improved algorithm $Δt$-Adaptive that further tolerates a waiting time in taking a ride. Our theoretical analysis shows that $Δt$-Adaptive is asymptotically optimal in the sense that its ratio approaches the proposed lower bounds as $Δt$ increases.

cs.DS↗

arXiv2020

Online Maximum $k$-Interval Coverage Problem

We study the online maximum coverage problem on a line, in which, given an online sequence of sub-intervals (which may intersect among each other) of a target large interval and an integer $k$, we aim to select at most $k$ of the sub-intervals such that the total covered length of the target interval is maximized. The decision to accept or reject each sub-interval is made immediately and irrevocably (no preemption) right at the release timestamp of the sub-interval. We comprehensively study different settings of this problem regarding both the length of a released sub-interval and the total number of released sub-intervals. We first present lower bounds on the competitive ratio for the settings concerned in this paper, respectively. For the offline problem where the sequence of all the released sub-intervals is known in advance to the decision-maker, we propose a dynamic-programming-based optimal approach as the benchmark. For the online problem, we first propose a single-threshold-based deterministic algorithm SOA by adding a sub-interval if the added length exceeds a certain threshold, achieving competitive ratios close to the lower bounds, respectively. Then, we extend to a double-thresholds-based algorithm DOA, by using the first threshold for exploration and the second threshold (larger than the first one) for exploitation. With the two thresholds solved by our proposed program, we show that DOA improves SOA in the worst-case performance. Moreover, we prove that a deterministic algorithm that accepts sub-intervals by multi non-increasing thresholds cannot outperform even SOA.

cs.DS↗