# MM-BEV: Enhancing Timeliness by Computing Where and When it Matters

arXiv: https://arxiv.org/abs/2608.15437 · HTML: https://mlsanity.com/paper/2608.15437/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 38 references that are in the map.
- First posted on arXiv 15 Aug 2026.

## Builds on (most cited first, 24 of 24)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [Planning-oriented Autonomous Driving](https://mlsanity.com/paper/2212.10156/) (2022)
- [BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation](https://mlsanity.com/paper/2205.13542/) (2022)
- [Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting](https://mlsanity.com/paper/2301.00493/) (2023)
- [TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers](https://mlsanity.com/paper/2203.11496/) (2022)
- [BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework](https://mlsanity.com/paper/2205.13790/) (2022)
- [BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision](https://mlsanity.com/paper/2211.10439/) (2022)
- [One Thousand and One Hours: Self-driving Motion Prediction Dataset](https://mlsanity.com/paper/2006.14480/) (2020)
- [A2D2: Audi Autonomous Driving Dataset](https://mlsanity.com/paper/2004.06320/) (2020)
- [SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videos](https://mlsanity.com/paper/2308.09244/) (2023)
- [Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?](https://mlsanity.com/paper/2206.07959/) (2022)
- [Vision-Centric BEV Perception: A Survey](https://mlsanity.com/paper/2208.02797/) (2022)
- [Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe](https://mlsanity.com/paper/2209.05324/) (2022)
- [SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection](https://mlsanity.com/paper/2304.14340/) (2023)
- [Cross Modal Transformer: Towards Fast and Robust 3D Object Detection](https://mlsanity.com/paper/2301.01283/) (2023)
- [SBNet: Sparse Blocks Network for Fast Inference](https://mlsanity.com/paper/1801.02108/) (2018)
- [Detecting As Labeling: Rethinking LiDAR-camera Fusion in 3D Object Detection](https://mlsanity.com/paper/2311.07152/) (2023)
- [M-BEV: Masked BEV Perception for Robust Autonomous Driving](https://mlsanity.com/paper/2312.12144/) (2023)
- [Robust Long-Range Perception Against Sensor Misalignment in Autonomous Vehicles](https://mlsanity.com/paper/2408.11196/) (2024)
- [Timealign: A multi-modal object detection method for time misalignment fusing in autonomous driving](https://mlsanity.com/paper/2412.10033/) (2024)
- [MMEdge: Accelerating On-device Multimodal Inference via Pipelined Sensing and Encoding](https://mlsanity.com/paper/2510.25327/) (2025)

## Abstract (arXiv)

Multimodal bird's-eye-view (BEV) perception combines LiDAR depth accuracy with dense camera semantics, but its high computational cost and imperfect sensing conditions make real-time deployment challenging. Existing methods largely compress individual detectors and overlook three opportunities: structured sparsity within camera and LiDAR inputs, timing misalignment between modalities, and the fact that many detected objects do not affect the planner's immediate action. We present MM-BEV, a real-time multimodal BEV system guided by a simple principle: compute where and when it matters. MM-BEV divides perception into mandatory work for safety-critical objects within braking distance of the ego vehicle and with short time-to-collision (TTC), and optional work for less urgent regions. It prioritizes mandatory work and reduces or sheds optional work under tight compute budgets. MM-BEV integrates four mechanisms: (1) a criticality-ranked temporal ROI selector based on motion-extrapolated detections from prior frames; (2) sparse, ROI-aware feature extraction using shared-shape camera crops at context-adaptive resolution and ROI-aware LiDAR voxelization; (3) a latency-aware coordinator that adapts LiDAR sweeps, image resolution, and keyframes according to scene dynamics and TTC; and (4) an asynchronous scheduler that decouples sensing from inference and skips stale frames. On nuScenes, MM-BEV reduces inference latency by 1.96x and end-to-end latency by 2.93x, with no loss in geometry-critical recall and only a 0.2 percentage-point drop in safety-critical recall. On a Clearpath Husky A300 equipped with an Ouster-128 LiDAR, BEV cameras, and a Jetson AGX Orin, MM-BEV further reduces mean latency by 2.11x, demonstrating its potential for real-world autonomous systems.