The main focus of this job is to research and develop novel algorithms for reconstructing the 3D geometry of the environments from the captured imagery by extending multi-view geometry/photogrammetry techniques to handle dynamic 360° environments. Alongside the standard duties of performing research, and its dissemination through publications and presentations, the candidate will also be expected to be involved in the supervision of PhD students and may have some teaching duties at undergraduate or graduate level
PhD in Computer Vision, Computer Graphics, Robotics or a strongly related discipline. Excellent background knowledge of standard computer vision, graphics and geometry approaches. Evidence of published research in high-quality peer-reviewed journals and/or conferences. Track record of production of clean and robust research code. Demonstrated significant depth and breadth of specialist knowledge of subject matter (structure-from-motion, multi-view geometry and stereo, geometry processing, and/or SLAM). Strong programming skills in C++ and/or Python. Strong mathematical ability (particularly linear algebra). Excellent oral, interpersonal and written communication skills. Ability to conduct individual research work. Ability to organise and prioritise own workload. Ability to write research reports and to effectively disseminate outcomes. Innovation and developing creative solutions. Commitment to excellence in research. Enthusiasm and self-motivation. Able to plan and deliver work to meet required deadlines. Working to achieve own and team objectives and to overcome obstacles. Ability to work independently and as an effective team member
Research Associate (Fixed Term) in Static and Dynamic 3D Environment Reconstruction Computer Science Salary: Starting from £33,199, rising to £39,609 Placed On: Friday 07 September 2018 Closing Date: Sunday 14 October 2018 Interview Date: Tuesday 30 October 2018 Reference: CA6136 To feel truly immersed in virtual reality, one needs to be able to freely look around within a virtual environment and see it from the viewpoints of one’s own eyes. Immersion requires ‘freedom of motion’ in six degrees-of-freedom (‘6-DoF’), so that viewers see the correct views of an environment. As viewers move their heads, the objects they see should move relative to each other, with different speeds depending on their distance to the viewer. This is called motion parallax and is a vital depth cue for the human visual system that is entirely missing from existing 360° VR video. To achieve 6-DoF VR video that enables photorealistic exploration of dynamic real environments in 360° virtual reality, this project will develop novel video-based capture, 3D reconstruction and rendering techniques. We first explore different approaches for capturing static and dynamic 360° environments, which are more challenging, including using 360° cameras and multi-camera rigs. We start with 6-DoF 360° VR photographs (i.e. static scenes) and then extend our approach to 6-DoF VR videos. The main focus of this job is to research and develop novel algorithms for reconstructing the 3D geometry of the environments from the captured imagery by extending multi-view geometry/photogrammetry techniques to handle dynamic 360° environments. Extending image-based rendering to 360° environments will then enable 6-DoF motion within a photorealistic 360° environment with high visual fidelity, and will result in detailed 360° environments covering all possible viewing directions. Our aim is to publish the resulting research and results in leading computer vision and computer graphics venues, specifically CVPR/ICCV/ECCV, IJCV and/or SIGGRAPH (Asia)/Transactions on Graphics. You will join the vibrant Visual Computing group at Bath, which comprises around 30 doctoral students, 5 post-doctoral researchers and 8 academics, and presents many opportunities for collaborative work and shared publications. This role is offered on a 32-month fixed-term contract. Informal enquiries should be directed to Dr Christian Richardt (email@example.com).
Please click here, if the Job didn't load correctly.
Please wait. You are being redirected to the Job in 3 seconds.