Research map / Point clouds / Point cloud classification
AircraftVerse: A Large-Scale Multimodal Dataset of Aerial Vehicle Designs
Adam D. Cobb, Anirban Roy, Daniel Elenius, Frederick Michael Heim, Brian Swenson, Sydney Whittington, James D Walker, Theodore Bapty, Joseph Hite, Karthik Ramani, Christopher McComb, Susmit Jha
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use transformer encoder instead of LSTM on design sequences | Sequence baseline · Hover prediction | accuracy: 0.8838 -> 0.9004 | Improved |
| use transformer encoder instead of LSTM | Sequence baseline · Hover time | R2: 0.6189 -> 0.6778 | Improved |
| use transformer encoder instead of LSTM | Sequence baseline · Flight distance | R2: 0.3467 -> 0.6900 | Improved |
| use transformer encoder instead of LSTM | Sequence baseline · Mass | R2: 0.9974 -> 0.9964 | No clear effect |
| use transformer encoder instead of LSTM | Sequence baseline · Interference | F1 score: 0.8184 -> 0.8270 | No clear effect |
| use point cloud GCNN instead of sequence transformer | Baseline models · Interference | F1 score: 0.8270 -> 0.9758 | Improved |
| use point cloud GCNN instead of sequence transformer | Baseline models · Hover | accuracy: 0.9004 -> 0.8380 | Hurt |
| use point cloud GCNN instead of sequence transformer | Baseline models · Mass | R2: 0.9964 -> 0.8888 | Hurt |
| use point cloud GCNN instead of sequence transformer | Baseline models · Hover time | R2: 0.6778 -> 0.3936 | Hurt |
| use point cloud GCNN instead of LSTM | Baseline models · Flight distance | R2: 0.3467 -> 0.4486 | Improved |
Closest papers by meaning
- EngiBench: A Framework for Data-Driven Engineering Design Research (NeurIPS 2025 · similarity 0.87)
- AFBench: A Large-scale Benchmark for Airfoil Design (NeurIPS 2024 · similarity 0.86)
- NeuralPlane: An Efficiently Parallelizable Platform for Fixed-wing Aircraft Control with Reinforcement Learning (NeurIPS 2024 · similarity 0.84)
- DrivAerNet++: A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarks (NeurIPS 2024 · similarity 0.84)
- 3DID: Direct 3D Inverse Design for Aerodynamics with Physics-Aware Optimization (NeurIPS 2025 · similarity 0.83)
- Compositional Generative Inverse Design (ICLR 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
