mlsanityData to 14 Oct 2026

TADP: Task-Aware Deformable Prediction for Single-Stage 3D Object Detection

arXiv 2608.27282 ↗First posted 27 Aug 2026cs.CV cs.AI cs.ROcited by 0

Not on the map. Why?

Abstract (arXiv)

Most single-stage 3D object detectors complete different tasks with the same extracted features. Nevertheless, it is impossible to project features into a common space that is adaptive for all the tasks. We present a novel task-aware deformable prediction (TADP) method for single-stage 3D object detection to solve this problem. Firstly, a triple feature refinement aggregation module is designed to extract three-level features adaptively. Additionally, we design the multi-scale feature aggregation block to fuse multi-scale features in a scale-aware manner. Finally, the prediction of each task is deformed with the designed plug-and-play task-aware deformation head. It can percept the emphasis and interaction of each task. We also designed three different deformation modules. The experimental results demonstrate that the proposed deformation head shows good results on other detection methods. The experimental results on the KITTI dataset demonstrate that the car mAP is 80.91%, surpassing many state-of-the-art methods on the KITTI benchmark.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 24 of its 31 references that are in the map. First posted on arXiv 27 Aug 2026.

Builds on

24 of 31 references.

References · 24

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  3. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,715
  4. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,368
  5. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  6. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 941
  7. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 748
  8. 2018Deformable ConvNets v2: More Deformable, Better Resultscited by 670
  9. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
  10. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 410
  11. 2017Joint 3D Proposal Generation and Object Detection from View Aggregationcited by 326
  12. 2020Deep Continuous Fusion for Multi-Sensor 3D Object Detectioncited by 263
12 more
  1. 2021Voxel Transformer for 3D Object Detectioncited by 247
  2. 20203D Object Detection with Pointformercited by 194
  3. 2021Embracing Single Stride 3D Object Detector with Sparse Transformercited by 193
  4. 20203D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detectioncited by 176
  5. 2022Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Cloudscited by 131
  6. 2019Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detectioncited by 124
  7. 2019TANet: Robust 3D Object Detection from Point Clouds with Triple Attentioncited by 108
  8. 2020CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloudcited by 107
  9. 2021Involution: Inverting the Inherence of Convolution for Visual Recognitioncited by 99
  10. 2019PI-RCNN: An Efficient Multi-sensor 3D Object Detector with Point-based Attentive Cont-conv Fusion Modulecited by 56
  11. 2021HVPR: Hybrid Voxel-Point Representation for Single-stage 3D Object Detectioncited by 47
  12. 2021Anchor-free 3D Single Stage Detector with Mask-Guided Attention for Point Cloudcited by 13

Built on by

Not cited yet.