Institution profile

University of Birmingham

Academic institutioneurope · gb
Official website
Research library477linked papers
Opportunities0open roles
Selected work

Representative Papers

CL-MVSNet: Unsupervised Multi-view Stereo with Dual-level Contrastive Learning

Oct 01, 2023IEEE International Conference on Computer Vision

To address incomplete and brittle depth estimation in unsupervised multi-view stereo (MVS) caused by low-texture regions and view-dependent effects (e.g., reflections), this paper proposes a two-level contrastive learning framework: image-level and scene-level contrastive branches are jointly optimized to enhance contextual awareness and feature representation robustness. Additionally, we introduce an L₀.₅ photometric consistency loss that selectively emphasizes high-confidence correspondences, mitigating the over-penalization of low-gradient regions inherent in conventional L₁/L₂ losses. The method is fully unsupervised—requiring no ground-truth depth annotations. Evaluated on DTU and Tanks & Temples benchmarks, it achieves state-of-the-art performance among unsupervised MVS approaches and surpasses leading supervised methods without fine-tuning. Our core contributions are the first-ever dual-granularity contrastive mechanism for MVS and an L₀.₅ norm-driven photometric constraint, jointly advancing robustness and accuracy in texture-deficient and view-dependent scenarios.

7 citations2 influentialRead paper

Rewriting modulo traced comonoid structure

Feb 19, 2023International Conference on Formal Structures for Computation and Deduction

This paper addresses the modeling challenge of string diagram rewriting in traced monoidal categories—categories supporting multi-output branching and input-output feedback connections. Methodologically: (1) it introduces and proves the hypergraph completeness of traced comonoid categories; (2) it adapts double-pushout (DPO) rewriting to traced string diagram grammars, ensuring locality and well-formedness of feedback operations; and (3) it axiomatizes traced structure to uniformly handle branching, merging, and cyclic connections. The contributions are threefold: (i) it establishes a unified formal foundation—combining equational theory and operational semantics—for dataflow and sequential circuits; (ii) every syntactic expression corresponds uniquely (up to isomorphism) to a hypergraph; and (iii) all rewrites preserve consistency with the traced axioms. This yields the first complete, hypergraph-based rewriting framework for traced monoidal structure.

4 citationsRead paper

Detecting LLM-Generated Text with Performance Guarantees

Jan 10, 2026arXiv.org

The proliferation of highly realistic text generated by large language models has intensified risks related to misinformation and academic misconduct, underscoring the urgent need for reliable detection methods. This work proposes an online classifier that distinguishes human- from model-generated text without relying on watermarks or prior knowledge of the generative model, operating efficiently on CPU alone. By integrating statistical learning with computationally efficient feature modeling, the method introduces, for the first time, controllable statistical inference guarantees that rigorously bound Type I error while achieving high statistical power, superior classification accuracy, and strong computational efficiency. Empirical evaluations demonstrate that the proposed detector significantly outperforms existing approaches across multiple benchmarks.

2 citationsRead paper

Surface-SOS: Self-Supervised Object Segmentation via Neural Surface Representation

Mar 12, 2024IEEE Transactions on Image Processing

This paper addresses unsupervised object surface recognition and segmentation from unlabeled multi-view images. We propose a self-supervised neural surface representation method. Our approach introduces, for the first time, NeRF-enhanced signed distance function (SDF) modeling into self-supervised segmentation, employing a dual-module scene representation that explicitly decouples geometry from appearance. Training is fully unsupervised, leveraging multi-view geometric and texture consistency constraints. Additionally, we design a coarse-mask-guided single-view refinement mechanism to improve segmentation precision. Crucially, our method requires no static background assumptions, temporal video sequences, or human annotations. Extensive experiments on benchmarks—including LLFF and CO3D—as well as real-world scenes demonstrate substantial improvements over NeRF-based baselines and supervised single-view methods, yielding finer-grained, more accurate, and robust segmentation masks.

2 citationsRead paper

Quantitative Verification With Neural Networks For Probabilistic Programs and Stochastic Systems

Jan 15, 2023International Conference on Concurrency Theory

This work addresses the quantitative verification of probabilistic programs and stochastic dynamical systems, specifically aiming to rigorously infer upper bounds on the probability that a stochastic process reaches a target condition within a finite number of steps. We propose a neuro-symbolic approach: supermartingale certificates are parameterized using differentiable neural networks; training employs stochastic optimization, while formal verification leverages SMT solvers (e.g., Z3); and an counterexample-guided inductive synthesis (CEGIS) framework enables iterative refinement. To our knowledge, this is the first method to embed neural networks directly into supermartingale construction—balancing expressive power with formal verifiability—and thereby significantly improves bound tightness and reliability. Evaluated on diverse benchmarks, our computed probability bounds match or surpass those of state-of-the-art techniques. Notably, we successfully verify high-dimensional, nonlinear stochastic models that defy analysis by conventional symbolic methods.

2 citationsRead paper
Recent publications

Latest Papers

Learning Metastable Dynamics

Sep 13, 2026

为解决物理系统中识别和分析亚稳态现象的挑战，提出了一种基于Koopman理论的新框架，通过学习系统的动态表示来提前预测亚稳态行为。

0 citationsRead paper