FR

EN

Homepage Inria website
  • Inria login
  • The Inria's Research Teams produce an annual Activity Report presenting their activities and their results of the year. These reports include the team members, the scientific program, the software developed by the team and the new results of the year. The report also describes the grants, contracts and the activities of dissemination and teaching. Finally, the report gives the list of publications of the year.

  • Legal notice
  • Cookie management
  • Personal data
  • Cookies


Section: New Results

Digital storytelling

Film Editing Patterns: Thinking like a Director

Participant : Marc Christie [contact] .

We have introduced Film Editing Patterns (FEP), a language to formalize film editing practices and stylistic choices found in movies. FEP constructs are constraints expressed over one or more shots from a movie sequence [29] that characterize changes in cinematographic visual properties such as shot size, region, angle of on-screen actors.

We have designed the elements of the FEP language, then introduced its usage in annotated film data, and described how it can support users in the creative design of film sequences in 3D. More specifically: (i) we proposed the design of a tool to craft edited filmic sequences from 3D animated scenes that uses FEPs to support the user in selecting camera framings and editing choices that follow certain best practices used in cinema; (ii) we conducted an evaluation of the application with professional and non-professional filmmakers. The evaluation suggested that users generally appreciate the idea of FEP, and that it can effectively help novice and medium experienced users in crafting film sequences with little training and satisfying results.

Directing Cinematographic Drones

Participants : Marc Christie [contact] , Quentin Galvane.

We have designed a set of high-level tools for filming dynamic targets with quadrotor drones. To this end, we proposed a specific camera parameter space (the Drone Toric space) together with interactive on-screen viewpoint manipulators compatible with the physical constraints of a drone. We then designed a real-time path planning approach in dynamic environments which ensures both cinematographic properties in viewpoints along the path and ensures the feasibility of the path by a quadrotor drone. We finally have demonstrated how the Drone Toric Space can be combined with our path planning technique to coordinate positions and motions of multiple drones around dynamic targets to ensure the coverture of cinematographic distinct viewpoints. The proposed research prototypes have been evaluation by an experienced drone pilot and filmmaker, as well as by non-experts users. Not only does the tool demonstrate it's benefit in rehearsing complex camera moves for the film and documentary industries, but it demonstrates it's usability for everyday recording of aesthetic camera motions. The work was published in the Transactions on Graphics journal and was accepted for presentation at SIGGRAPH [18].

In addition we have focused on full automated and non-reactive path-planning for cinematographic drones. Most existing tools typically require the user to specify and edit the camera path, for example by providing a complete and ordered sequence of key viewpoints. In our contribution, we propose a higher level tool designed to enable even novice users to easily capture compelling aerial videos of large-scale outdoor scenes. Using a coarse 2.5D model of a scene, the user is only expected to specify starting and ending viewpoints and designate a set of landmarks, with or without a particular order. Our system automatically generates a diverse set of candidate local camera moves for observing each landmark, which are collision-free, smooth, and adapted to the shape of the landmark. These moves are guided by a landmark-centric view quality field, which combines visual interest and frame composition. An optimal global camera trajectory is then constructed that chains together a sequence of local camera moves, by choosing one move for each landmark and connecting them with suitable transition trajectories. This task is formulated and solved as an instance of the Set Traveling Salesman Problem. The work was published and presented at SIGGRAPH [30].

Automated Virtual Staging

Participants : Marc Christie [contact] , Quentin Galvane, Fabrice Lamarche, Amaury Louarn.

While the topic of virtual cinematography has essentially focused on the problem of computing the best viewpoint in a virtual environment given a number of objects placed beforehand, the question of how to place the objects in the environment with relation to the camera (referred to as staging in the film industry) has received little attention. This work first proposes a staging language for both characters and cameras that extends existing cinematography languages with multiple cameras and character staging. Second, we propose techniques to operationalize and solve staging specifications given a 3D virtual environment. The novelty holds in the idea of exploring how to position the characters and the cameras simultaneously while maintaining a number of spatial relationships specific to cinematography. We demonstrate the relevance of our approach through a number of simple and complex examples [45].

VR Staging and Cinematography

Participants : Marc Christie [contact] , Quentin Galvane.

Creatives in animation and film productions have forever been exploring the use of new means to prototype their visual sequences before realizing them, by relying on hand-drawn storyboards, physical mockups or more recently 3D modelling and animation tools. However these 3D tools are designed in mind for dedicated animators rather than creatives such as film directors or directors of photography and remain complex to control and master. In this work we propose a VR authoring system which provides intuitive ways of crafting visual sequences, both for expert animators and expert creatives in the animation and film industry. The proposed system is designed to reflect the traditional process through (i) a storyboarding mode that enables rapid creation of annotated still images, (ii) a previsualisation mode that enables the animation of the characters, objects and cameras, and (iii) a technical mode that enables the placement and animation of complex camera rigs (such as cameras cranes) and light rigs. Our methodology strongly relies on the benefits of VR manipulations to re-think how content creation can be performed in this specific context, typically how to animate contents in space and time. As a result, the proposed system is complimentary to existing tools, and provides a seamless back-and-forth process between all stages of previsualisation. We evaluated the tool with professional users to gather experts' perspectives on the specific benefits of VR in 3D content creation [37].

Improving Camera tracking technologies

Participants : Marc Christie [contact] , Xi Wang.

Robustness of indirect SLAM techniques to light changing conditions remains a central issue in the robotics community. With the change in the illumination of a scene, feature points are either not extracted properly due to low contrasts, or not matched due to large differences in descriptors. In this work, we propose a multi-layered image representation (MLI) in which each layer holds a contrast enhanced version of the current image in the tracking process in order to improve detection and matching. We show how Mutual Information can be used to compute dynamic contrast enhancements on each layer. We demonstrate how this approach dramatically improves the robustness in dynamic light changing conditions on both synthetic and real environments compared to default ORB-SLAM. This work focalises on the specific case of SLAM relocalisation in which a first pass on a reference video constructs a map, and a second pass with a light changed condition relocalizes the camera in the map [41], [40].