One Day Meeting: BMVA Symposium on 3D Vision

Wednesday 26 February 2025

Chairs: Will Rowan (University of York), Nick Pears (University of York)

Queries? contact the Meeting's Organiser Andrew Gilbert here

Invited Speakers

• Oisin Mac Aodha, Reader in Computer Vision, University of Edinburgh
• Neill Campbell, Director of CAMERA, University of Bath
• Lourdes Agapito, Professor of 3D Vision, UCL and Co-founder of Synthesia.

Overview of the Meeting

We are bringing together a diverse range of researchers and engineers in 3D Vision, across all career stages. This event is a great opportunity to learn and network – even if you are new to the field! If you still need convincing, lunch is included.

Presentations will be either published work, or ongoing research, in areas similar to below

• 3D from X
• 3D shape modelling and processing
• Applications of 3D Vision in film, television, and games
• Computational photography and photogrammetry
• RGB-D sensors and analytics
• Scene analysis and understanding
• Segmentation, grouping, and shape analysis
• 3D vision and graphics
• 3D acquisition
• 4D dynamic shapes
• Human-related 3D (face, gestures, pose, and body movement)
• Generative and morphable models
• 3D motion modelling
• Inverse rendering

Programme

Accepted Talks

3D Scenes

Stan Szymanowicz, University of Oxford: Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Image

Yifan Xing, University of Bristol: Object-based SLAM Using Superquadrics

James Gardner, University of York: The Sky’s the Limit: Relightable Outdoor Scenes via a Sky-Pixel Constrained Illumination Prior and Outside-In Visibility

3D Humans

Eugene Valassakis, Synthesia (work carried out at Niantic): Camera-Space Hand Mesh Prediction with Differentiable Global Positioning

Jakub Zadrozny, University of Edinburgh: Generalized Animatable Human NeRFs from Few Views

Maksym Ivashechkin, University of Surrey: SignSplat: Rendering Sign Language via Gaussian Splatting

3D in Industry

Patrik Huber, Mimetrik: Computer Vision Meets Dentistry: The Digital Facebow

Georg Glatz, Contillo: Building Construction Progress Monitoring through Scan-vs-BIM

Michael Firman, Niantic: Depth Estimation in AR: From Research to Applications

Posters

Tianxiang Yang, University of Surrey: Decomposition of Compound Facial Expressions into FACS-Based Blendshapes

Umar Farooq, University of Surrey: Efficient 3D Gaussian Splatting with Coarse-to-Fine Optimization

Danny Roberts, University of York: Building a Multi-spectral Lightstage on a Budget

Narges Tabatabaey, University of Dundee: 3D Face Reconstruction Model for the 3Dface@Home Project

Zhening Huang, University of Cambridge: One Shot Simulation: 3D Simulation Ready Reconstruction from RGBD Scans

Jack Saunders, University of Bath: Dubbing for Everyone: Data-Efficient Visual Dubbing using Neural Rendering Priors

Yifu Tao, University of Oxford: LiDAR-Visual Reconstruction with Neural Radiance Field in Large-scale Outdoor Environments

Christina Kassab, University of Oxford: The Bare Necessities: Designing Simple, Effective Open-Vocabulary Scene Graphs

Edward Rosten, King’s College London: Inferring High Quality Parametric 3D models from Microscopy Data

Ayushi Dutta, University of Surrey: Model Free Reconstruction of Human-Object Interactions

Chenyuan Qu, University of Birmingham: 360+x : A Panoptic Multi-modal Scene Understanding Dataset

Meeting Location

The meeting will take place at:

British Computer Society (BCS), 25 Copthall Avenue, London EC2R 7BP

Registration

We keep the cost of attending these events as low as possible to ensure no barriers from the whole computer vision community attending. The registration costs are as follows

• All Attendees: £30 Including lunch and refreshments for the day