# Efficient Multi-View 3D Object Detection by Dynamic Token Selection and Fine-Tuning

arXiv: https://arxiv.org/abs/2604.13586 · HTML: https://mlsanity.com/paper/2604.13586/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 37 references that are in the map.
- First posted on arXiv 15 Apr 2026.

## Builds on (most cited first, 30 of 32)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D](https://mlsanity.com/paper/2008.05711/) (2020)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View](https://mlsanity.com/paper/2112.11790/) (2021)
- [DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries](https://mlsanity.com/paper/2110.06922/) (2021)
- [BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection](https://mlsanity.com/paper/2206.10092/) (2022)
- [PETR: Position Embedding Transformation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2203.05625/) (2022)
- [EVA-02: A Visual Representation for Neon Genesis](https://mlsanity.com/paper/2303.11331/) (2023)
- [Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection](https://mlsanity.com/paper/2303.11926/) (2023)
- [BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision](https://mlsanity.com/paper/2211.10439/) (2022)
- [Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detection](https://mlsanity.com/paper/2210.02443/) (2022)
- [Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer](https://mlsanity.com/paper/2108.01390/) (2021)
- [Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusion](https://mlsanity.com/paper/2211.10581/) (2022)
- [SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videos](https://mlsanity.com/paper/2308.09244/) (2023)
- [Sparse4D v2: Recurrent Temporal Fusion with Sparse Model](https://mlsanity.com/paper/2305.14018/) (2023)
- [vid-TLDR: Training Free Token merging for Light-weight Video Transformer](https://mlsanity.com/paper/2403.13347/) (2024)
- [Ray Denoising: Depth-aware Hard Negative Sampling for Multi-view 3D Object Detection](https://mlsanity.com/paper/2402.03634/) (2024)
- [BEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detection](https://mlsanity.com/paper/2312.01696/) (2023)
- [Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation](https://mlsanity.com/paper/2403.11808/) (2024)
- [M-BEV: Masked BEV Perception for Robust Autonomous Driving](https://mlsanity.com/paper/2312.12144/) (2023)
- [URGENT Challenge: Universality, Robustness, and Generalizability For Speech Enhancement](https://mlsanity.com/paper/2406.04660/) (2024)
- [OPEN: Object-wise Position Embedding for Multi-view 3D Object Detection](https://mlsanity.com/paper/2407.10753/) (2024)
- [Interspeech 2025 URGENT Speech Enhancement Challenge](https://mlsanity.com/paper/2505.23212/) (2025)
- [Make Your ViT-based Multi-view 3D Detectors Faster via Token Compression](https://mlsanity.com/paper/2409.00633/) (2024)

## Abstract (arXiv)

Existing multi-view three-dimensional (3D) object detection approaches widely adopt large-scale pre-trained vision transformer (ViT)-based foundation models as backbones, being computationally complex. To address this problem, current state-of-the-art (SOTA) textttToC3D for efficient multi-view ViT-based 3D object detection employs ego-motion-based relevant token selection. However, there are two key limitations: (1) The fixed layer-individual token selection ratios limit computational efficiency during both training and inference. (2) Full end-to-end retraining of the ViT backbone is required for the multi-view 3D object detection method. In this work, we propose an image token compensator combined with a token selection for ViT backbones to accelerate multi-view 3D object detection. Unlike textttToC3D, our approach enables dynamic layer-wise token selection within the ViT backbone. Furthermore, we introduce a parameter-efficient fine-tuning strategy, which trains only the proposed modules, thereby reducing the number of fine-tuned parameters from more than 300 million (M) to only 1.6 M. Experiments on the large-scale NuScenes dataset across three multi-view 3D object detection approaches demonstrate that our proposed method decreases computational complexity (GFLOPs) by 48% ... 55%, inference latency (on an textttNVIDIA-GV100 GPU) by 9% ... 25%, while still improving mean average precision by 1.0% ... 2.8% absolute and NuScenes detection score by 0.4% ... 1.2% absolute compared to so-far SOTA textttToC3D.