π’ We release the Public Dataset comprising 1,622 scenes, 5,197 rooms, and 44,445 object-query pairs.
π’ Team Registration is Now Closed!
π¦ The private dataset and submission guidelines have been sent to all registered participants.
π Out of 18 incredible participants, the top 5 have been selected based on performance. Check out the leaderboard to see who made it to the top. Congratulations to all!Β
The ROOMELSA Grand Challenge presents a novel and impactful task set in 3D environments: retrieving a masked object in a 3D scene using only a natural language description and spatial context.
By framing this retrieval task within a 3D spatial setting, ROOMELSA advances research at the intersection of scene understanding, cross-modal retrieval, and spatial-language alignment. It challenges participants to build intelligent, context-aware systems capable of reasoning across modalities in complex, real-world-like environments.
Weβre excited to share the final leaderboard for this challenge! Out of 18 talented participants, the top 5 have emerged based on performance metrics. Congratulations to all who took part - your efforts made this a truly competitive and inspiring event!
For questions, please contact the organizers at ntthuan@selab.hcmus.edu.vn.
University of Science,
VNU-HCM, Vietnam
Tam V. Nguyen
University of Dayton,
Ohio, USA
University of Science,
VNU-HCM, Vietnam
Viet-Tham Huynh
University of Science,
VNU-HCM, Vietnam
Quang-Thuc Nguyen
University of Science,
VNU-HCM, Vietnam
Hoang-Phuc Nguyen
University of Science,
VNU-HCM, Vietnam
π₯ Registration Opened: 30 March 2025
π Public Data Released: 03 April 2025
π Registration Closed: 15 April 2025
π Private Data Released: 15 April 2025
π’ Notification of Results: 23 April 2025
π Technical Report Submission: 28 April 2025
Β© Copyright Software Engineering Laboratory, University of Science, VNU-HCM, Vietnam