Papers › E.T. the Exceptional Trajectories: Text-to-camera-trajectory generation with character...

E.T. the Exceptional Trajectories: Text-to-camera-trajectory generation with character awareness

1 Jul 2024arXiv:2407.01516archive 2025-07-28

Robin Courant, Nicolas Dufour, Xi Wang, Marc Christie, Vicky Kalogeiton

Stories and emotions in movies emerge through the effect of well-thought-out directing decisions, in particular camera placement and movement over time. Crafting compelling camera trajectories remains a complex iterative process, even for skilful artists. To tackle this, in this paper, we propose a dataset called the Exceptional Trajectories (E.T.) with camera trajectories along with character information and textual captions encompassing descriptions of both camera and character. To our knowledge, this is the first dataset of its kind. To show the potential applications of the E.T. dataset, we propose a diffusion-based approach, named DIRECTOR, which generates complex camera trajectories from textual captions that describe the relation and synchronisation between the camera and characters. To ensure robust and accurate evaluations, we train on the E.T. dataset CLaTr, a Contrastive Language-Trajectory embedding for evaluation metrics. We posit that our proposed dataset and method significantly advance the democratization of cinematography, making it more accessible to common users.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

robincourant/DIRECTOR officialpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Generation

Datasets

Introduced by this paper, per the archive.

E.T. the Exceptional Trajectories

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Generation E.T. the Exceptional Trajectories DIRECTOR C ClaTr-Score 21.95 #1 of 4 Archive leaderboard report
3D Generation E.T. the Exceptional Trajectories DIRECTOR C Classifier-F1 0.48 #1 of 4 Archive leaderboard report
3D Generation E.T. the Exceptional Trajectories DIRECTOR C FD_ClaTr 3.76 #1 of 4 Archive leaderboard report
3D Generation E.T. the Exceptional Trajectories DIRECTOR A ClaTr-Score 20.76 #2 of 4 Archive leaderboard report
3D Generation E.T. the Exceptional Trajectories DIRECTOR A Classifier-F1 0.42 #2 of 4 Archive leaderboard report
3D Generation E.T. the Exceptional Trajectories DIRECTOR A FD_ClaTr 3.88 #2 of 4 Archive leaderboard report
3D Generation E.T. the Exceptional Trajectories DIRECTOR B ClaTr-Score 20.78 #3 of 4 Archive leaderboard report
3D Generation E.T. the Exceptional Trajectories DIRECTOR B Classifier-F1 0.39 #3 of 4 Archive leaderboard report
3D Generation E.T. the Exceptional Trajectories DIRECTOR B FD_ClaTr 6.10 #3 of 4 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections