Research map / Detection and segmentation / 3D detection and driving
Multi-Modal Fusion Transformer for End-to-End Autonomous Driving
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 attention-based multi-scale image–LiDAR fusion instead of geometric feature projection | End-to-end driving policy · Town05 Long | Driving Score: 25.30 ± 4.08 -> 33.15 ± 4.04 | Helped |
| Use attention-based multi-scale image–LiDAR fusion instead of late fusion | End-to-end driving policy · Town05 Long | Driving Score: 31.30 ± 5.53 -> 33.15 ± 4.04 | Helped |
| Use 4 fusion scales rather than 1 (ablation) | TransFuser · Town05 Short | Driving Score: 41.94 -> 59.99 | Helped |
| Use 4 fusion scales rather than 2 (ablation) | TransFuser · Town05 Short | Driving Score: 52.82 -> 59.99 | Helped |
| Use 4 fusion scales rather than 3 (ablation) | TransFuser · Town05 Short | Driving Score: 52.41 -> 59.99 | Helped |
| Use separate transformer parameters at each scale rather than sharing them (ablation) | TransFuser · Town05 Short | Driving Score: 55.36 -> 59.99 | Helped |
| Use 8 attention layers rather than 1 (ablation) | TransFuser · Town05 Short | Driving Score: 50.46 -> 59.99 | Helped |
| Use 8 attention layers rather than 4 (ablation) | TransFuser · Town05 Short | Driving Score: 51.38 -> 59.99 | Helped |
| Add learnable positional embeddings (ablation) | TransFuser · Town05 Short | Driving Score: 52.45 -> 59.99 | Helped |
Closest papers by meaning
- Knowledge Distillation from Single-Task Teachers to Multi-Task Student for End-to-End Autonomous Driving (AAAI 2024 · similarity 0.89)
- GaussianFusion: Gaussian-Based Multi-Sensor Fusion for End-to-End Autonomous Driving (NeurIPS 2025 · similarity 0.88)
- DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous Driving (ICLR 2025 · similarity 0.86)
- Layer-Wise Modality Decomposition for Interpretable Multimodal Sensor Fusion (NeurIPS 2025 · similarity 0.86)
- SGFormer: Semantic-Geometry Fusion Transformer for Multi-modal 3D Panoptic Segmentation (AAAI 2025 · similarity 0.86)
- The Road Ahead in Autonomous Driving: The KITScenes Multimodal Dataset (NeurIPS 2026 · similarity 0.85)
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.