Lintong Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Lintong Zhang has a total of 43 co-authors. Here are the top co-authors by number of shared publications:
- Maurice Fallon
University of Oxford
5 shared publications - David Wisth
Oxford Robotics Institute, University of Oxford
3 shared publications - Marco Camurri
Facolt di Ingegneria, Libera Universit di Bolzano, Bolzano, Italy
3 shared publications - Matías Mattamala
University of Edinburgh
2 shared publications Adrien Briod
University of California, Berkeley
1 shared publicationBenoit Casseau
Oxford Robotics Institute, University of Oxford
1 shared publication
Latest Publications
- Top Cited PapersOpen Access
- 20 September 2025
- Published by SAGE Publications in The International Journal of Robotics Research
- Vol. 45 (6) , 839-857
The Oxford Spires Dataset: Benchmarking large-scale LiDAR-visual localisation, reconstruction and radiance field methods
This paper introduces a large-scale multi-modal dataset captured in and around well-known landmarks in Oxford using a custom-built multi-sensor perception unit as well as a millimetre-accurate map from a Terrestrial LiDAR Scanner (TLS). The perception unit includes three synchronised global shutter colour cameras, an automotive 3D LiDAR scanner, and an inertial sensor – all precisely calibrated. We also establish benchmarks for tasks involving localisation, reconstruction, and novel-view synthesis, which enable the evaluation of Simultaneous Localisation and Mapping (SLAM) methods, Structure-from-Motion (SfM) and Multi-view Stereo (MVS) methods as well as radiance field methods such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting. To evaluate 3D reconstruction, the TLS 3D models are used as ground truth. Localisation ground truth is computed by registering the mobile LiDAR scans to the TLS 3D models. Radiance field methods are evaluated not only with poses sampled from the input trajectory, but also from viewpoints that are from trajectories which are distant from the training poses. Our evaluation demonstrates a key limitation of state-of-the-art radiance field methods: we show that they tend to overfit to the training poses/images and do not generalise well to out-of-sequence poses. They also underperform in 3D reconstruction compared to MVS systems using the same visual inputs. Our dataset and benchmarks are intended to facilitate better integration of radiance field methods and SLAM systems. The raw and processed data, along with software for parsing and evaluation, can be accessed at https://dynamic.robots.ox.ac.uk/datasets/oxford-spires/ .
- 20 September 2025
- Published by SAGE Publications in The International Journal of Robotics Research
- Vol. 45 (6) , 839-857
Top Cited PapersOpen AccessThe Oxford Spires Dataset: Benchmarking large-scale LiDAR-visual localisation, reconstruction and radiance field methods
This paper introduces a large-scale multi-modal dataset captured in and around well-known landmarks in Oxford using a custom-built multi-sensor perception unit as well as a millimetre-accurate map from a Terrestrial LiDAR Scanner (TLS). The perception unit includes three synchronised global shutter colour cameras, an automotive 3D LiDAR scanner, and an inertial sensor – all precisely calibrated. We also establish benchmarks for tasks involving localisation, reconstruction, and novel-view synthesis, which enable the evaluation of Simultaneous Localisation and Mapping (SLAM) methods, Structure-from-Motion (SfM) and Multi-view Stereo (MVS) methods as well as radiance field methods such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting. To evaluate 3D reconstruction, the TLS 3D models are used as ground truth. Localisation ground truth is computed by registering the mobile LiDAR scans to the TLS 3D models. Radiance field methods are evaluated not only with poses sampled from the input trajectory, but also from viewpoints that are from trajectories which are distant from the training poses. Our evaluation demonstrates a key limitation of state-of-the-art radiance field methods: we show that they tend to overfit to the training poses/images and do not generalise well to out-of-sequence poses. They also underperform in 3D reconstruction compared to MVS systems using the same visual inputs. Our dataset and benchmarks are intended to facilitate better integration of radiance field methods and SLAM systems. The raw and processed data, along with software for parsing and evaluation, can be accessed at https://dynamic.robots.ox.ac.uk/datasets/oxford-spires/ .
- Open Access
- 13 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 15988-15994
Language-EXtended Indoor SLAM (LEXIS): A Versatile System for Real-time Visual Scene Understanding
Versatile and adaptive semantic understanding would enable autonomous systems to comprehend and interact with their surroundings. Existing fixed-class models limit the adaptability of indoor mobile and assistive autonomous systems. In this work, we introduce LEXIS, a real-time indoor Simultaneous Localization and Mapping (SLAM) system that harnesses the open-vocabulary nature of Large Language Models (LLMs) to create a unified approach to scene understanding and place recognition. The approach first builds a topological SLAM graph of the environment (using visual-inertial odometry) and embeds Contrastive Language-Image Pretraining (CLIP) features in the graph nodes. We use this representation for flexible room classification and segmentation, serving as a basis for room-centric place recognition. This allows loop closure searches to be directed towards semantically relevant places. Our proposed system is evaluated using both public, simulated data and real-world data, covering office and home environments. It successfully categorizes rooms with varying layouts and dimensions and outperforms the state-of-the-art (SOTA). For place recognition and trajectory estimation tasks we achieve equivalent performance to the SOTA, all also utilizing the same pre-trained model. Lastly, we demonstrate the system’s potential for planning. Video at: https://youtu.be/gRqF3euDfX8
- 13 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 15988-15994
Open AccessLanguage-EXtended Indoor SLAM (LEXIS): A Versatile System for Real-time Visual Scene Understanding
Versatile and adaptive semantic understanding would enable autonomous systems to comprehend and interact with their surroundings. Existing fixed-class models limit the adaptability of indoor mobile and assistive autonomous systems. In this work, we introduce LEXIS, a real-time indoor Simultaneous Localization and Mapping (SLAM) system that harnesses the open-vocabulary nature of Large Language Models (LLMs) to create a unified approach to scene understanding and place recognition. The approach first builds a topological SLAM graph of the environment (using visual-inertial odometry) and embeds Contrastive Language-Image Pretraining (CLIP) features in the graph nodes. We use this representation for flexible room classification and segmentation, serving as a basis for room-centric place recognition. This allows loop closure searches to be directed towards semantically relevant places. Our proposed system is evaluated using both public, simulated data and real-world data, covering office and home environments. It successfully categorizes rooms with varying layouts and dimensions and outperforms the state-of-the-art (SOTA). For place recognition and trajectory estimation tasks we achieve equivalent performance to the SOTA, all also utilizing the same pre-trained model. Lastly, we demonstrate the system’s potential for planning. Video at: https://youtu.be/gRqF3euDfX8
- Open Access
- 1 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Field Robotics
- Vol. 4, 249-312
Team CERBERUS Wins the DARPA Subterranean Challenge: Technical Overview and Lessons Learned
- 1 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Field Robotics
- Vol. 4, 249-312
Open AccessTeam CERBERUS Wins the DARPA Subterranean Challenge: Technical Overview and Lessons Learned
- Top Cited Papers
- 1 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 8 (1) , 408-415
Hilti-Oxford Dataset: A Millimeter-Accurate Benchmark for Simultaneous Localization and Mapping
Simultaneous Localization and Mapping (SLAM) is being deployed in real-world applications, however many state-of-the-art solutions still struggle in many common scenarios. A key necessity in progressing SLAM research is the availability of high-quality datasets and fair and transparent benchmarking. To this end, we have created the Hilti-Oxford Dataset, to push state-of-the-art SLAM systems to their limits. The dataset has a variety of challenges ranging from sparse and regular construction sites to a 17th century neoclassical building with fine details and curved surfaces. To encourage multi-modal SLAM approaches, we designed a data collection platform featuring a lidar, five cameras, and an IMU (Inertial Measurement Unit). With the goal of benchmarking SLAM algorithms for tasks where accuracy and robustness are paramount, we implemented a novel ground truth collection method that enables our dataset to accurately measure SLAM pose errors with millimeter accuracy. To further ensure accuracy, the extrinsics of our platform were verified with a micrometer-accurate scanner, and temporal calibration was managed online using hardware time synchronization. The multi-modality and diversity of our dataset attracted a large field of academic and industrial researchers to enter the second edition of the Hilti SLAM challenge, which concluded in June 2022. The results of the challenge show that while the top three teams could achieve an accuracy of 2 cm or better for some sequences, the performance dropped off in more difficult sequences.
- 1 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 8 (1) , 408-415
Top Cited PapersHilti-Oxford Dataset: A Millimeter-Accurate Benchmark for Simultaneous Localization and Mapping
Simultaneous Localization and Mapping (SLAM) is being deployed in real-world applications, however many state-of-the-art solutions still struggle in many common scenarios. A key necessity in progressing SLAM research is the availability of high-quality datasets and fair and transparent benchmarking. To this end, we have created the Hilti-Oxford Dataset, to push state-of-the-art SLAM systems to their limits. The dataset has a variety of challenges ranging from sparse and regular construction sites to a 17th century neoclassical building with fine details and curved surfaces. To encourage multi-modal SLAM approaches, we designed a data collection platform featuring a lidar, five cameras, and an IMU (Inertial Measurement Unit). With the goal of benchmarking SLAM algorithms for tasks where accuracy and robustness are paramount, we implemented a novel ground truth collection method that enables our dataset to accurately measure SLAM pose errors with millimeter accuracy. To further ensure accuracy, the extrinsics of our platform were verified with a micrometer-accurate scanner, and temporal calibration was managed online using hardware time synchronization. The multi-modality and diversity of our dataset attracted a large field of academic and industrial researchers to enter the second edition of the Hilti SLAM challenge, which concluded in June 2022. The results of the challenge show that while the top three teams could achieve an accuracy of 2 cm or better for some sequences, the performance dropped off in more difficult sequences.
- 23 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 7 (2) , 1182-1189
Balancing the Budget: Feature Selection and Tracking for Multi-Camera Visual-Inertial Odometry
We present a multi-camera visual-inertial odometry system based on factor graph optimization which estimates motion by using all cameras simultaneously while retaining a fixed overall feature budget. We focus on motion tracking in challenging environments, such as narrow corridors, dark spaces with aggressive motions, and abrupt lighting changes. These scenarios cause traditional monocular or stereo odometry to fail. While tracking motion with extra cameras should theoretically prevent failures, it leads to additional complexity and computational burden. To overcome these challenges, we introduce two novel methods to improve multi-camera feature tracking. First, instead of tracking features separately in each camera, we track features continuously as they move from one camera to another. This increases accuracy and achieves a more compact factor graph representation. Second, we select a fixed budget of tracked features across the cameras to reduce back-end optimization time. We have found that using a smaller set of informative features can maintain the same tracking accuracy. Our proposed method was extensively tested using a hardware-synchronized device consisting of an IMU and four cameras (a front stereo pair and two lateral) in scenarios including: an underground mine, large open spaces, and building interiors with narrow stairs and corridors. Compared to stereo-only state-of-the-art visual-inertial odometry methods, our approach reduces the drift rate, relative pose error, by up to 80% in translation and 39% in rotation.
- 23 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 7 (2) , 1182-1189
Balancing the Budget: Feature Selection and Tracking for Multi-Camera Visual-Inertial Odometry
We present a multi-camera visual-inertial odometry system based on factor graph optimization which estimates motion by using all cameras simultaneously while retaining a fixed overall feature budget. We focus on motion tracking in challenging environments, such as narrow corridors, dark spaces with aggressive motions, and abrupt lighting changes. These scenarios cause traditional monocular or stereo odometry to fail. While tracking motion with extra cameras should theoretically prevent failures, it leads to additional complexity and computational burden. To overcome these challenges, we introduce two novel methods to improve multi-camera feature tracking. First, instead of tracking features separately in each camera, we track features continuously as they move from one camera to another. This increases accuracy and achieves a more compact factor graph representation. Second, we select a fixed budget of tracked features across the cameras to reduce back-end optimization time. We have found that using a smaller set of informative features can maintain the same tracking accuracy. Our proposed method was extensively tested using a hardware-synchronized device consisting of an IMU and four cameras (a front stereo pair and two lateral) in scenarios including: an underground mine, large open spaces, and building interiors with narrow stairs and corridors. Compared to stereo-only state-of-the-art visual-inertial odometry methods, our approach reduces the drift rate, relative pose error, by up to 80% in translation and 39% in rotation.