Research Scientist 3D Reconstruction and Novel View Synthesis
SpAItialVisit SpAItial website
SpAItial is a London AI company developing physically grounded world models that generate and reason about explorable 3D environments.
London, United Kingdom
Funding history
About SpAItial
SpAItial develops the Echo model family and an app/API for generating, editing, exploring, sharing, and exporting persistent 3D Gaussian Splat worlds from text, images, and panoramas.
Skills
About the Role
You will advance 3D reconstruction and novel view synthesis through research and working methods. You will develop approaches for geometry, appearance, materials, lighting, dynamics, and incomplete observations. You will design losses, priors, and optimization strategies, rigorously evaluate results, and help transition successful methods into production systems.
Requirements
- PhD in computer vision, graphics, or a related field
- Publications at top venues including CVPR, ICCV, ECCV, SIGGRAPH, or NeurIPS
- Hands-on knowledge of modern scene representations, including Gaussian splats and radiance fields
- Research experience with reconstruction methods from per-scene optimization to feed-forward models
- Understanding of multi-view geometry, camera models, and rendering
- Experience with deep learning frameworks
Responsibilities
- Advance 3D reconstruction from research ideas to working methods
- Develop reconstruction and novel view synthesis methods for geometry, appearance, materials, lighting, dynamics, and incomplete observations
- Design losses, priors, and optimization strategies
- Build rigorous evaluations using public and internal benchmarks
- Bring successful methods into production systems