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

Su Wang; Yaochen Li; Min Yang; Jiaohao Nie; Chang Liu; Yuehu Liu

cs.CVAug 27, 2026

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

Authors: Su Wang, Yaochen Li, Min Yang, Jiaohao Nie, Chang Liu, Yuehu Liu

Organizations: School of Software Engineering Xi’an Jiaotong University Xi’an, China · School of Electrical and Electronic Engineering Nanyang Technological University Singapore · CSSC Systems Engineering Research Institute Beijing, China

Abstract

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.

Figures & tables

Fig. 1: Visualization of detection in street scenes. It shows the different detection results of SECOND [ 5 ] and our TADP. We use red arrows to indicate the biased optimization of our method compared to SECOND detection.

Fig. 2: The figure shows the pipeline of our method TADP. (a) downsample and encode the point clouds. (b) show TFRA structure refine the three-scales features. (c) show the MSFA structure, scale maps Features and fused with SFA. (d) show the TADH, predict the deformation map, and deform the task prediction.

Fig. 3: The pipeline of TADH. The first branch of the features directly generates traditional task predictions through predict line. The second branch through P-Stack generates DMap. The upper features provide height attention. Finally, the deformation to the prediction result is generated through the Deform-line.

Fig. 4: The process and principle of PStack and DMap generating each task’s deformation. Below shows the raw point cloud and proposals. Above shows the process of task alignment

Fig. 5: Comparative experiments between different tasks and different deform modules. $Wei.$ , $dec.$ , $add.$ , and $null$ . We show how much the accuracy increases as a color chart. Based on the ‘ $null$ ’ color.

Fig. 6: Our 3D detection results on the KITTI validation set are visualized. The ground truth is the green box, and the prediction box is the red box. The 3D detection box is projected to an RGB image.

Type	Method	Sens	$AP_{3D}(\%)$
Type	Method	Sens	Easy	Mod	Hard
2-stage	AVOD(2018) [ 21 ]	LIDAR+RGB	83.07	71.76	65.73
	PI-RCNN(2020) [ 22 ]	LIDAR+RGB	84.37	74.82	70.03
	PointRCNN(2019)	LIDAR	86.96	75.64	70.70
	F-ConvNet(2019) [ 23 ]	LIDAR+RGB	87.36	76.39	66.69
	UberATG-MMF(2019)	LIDAR+RGB	88.40	77.43	70.22

TABLE I: AP11-based comparation with SOTA on KITTI dataset benchmark for car class detection

$TFRA$	$MSFA$	$TADH$	$TADH^{\dagger}$	$AP_{3D}(\%)$
$TFRA$	$MSFA$	$TADH$	$TADH^{\dagger}$	Easy	Mod	Hard
				87.52	77.21	74.36
✓				88.27	78.41	75.89
✓	✓			89.26	79.37	76.76
✓	✓	✓		89.71	79.95	77.31
✓	✓		✓	90.03	80.62	78.64

TABLE II: Ablation experiments of TFRA and MSFA and TADH in TADP on KITTI validation dataset.

	PointRCNN	Part-A2	MGAF-3DSSD	3D-CVF	Ours
time(ms)	643	80	80	85	40.53
mAP	77.67	79.7	80.51	80.79	80.91

TABLE III: Runtime (in milliseconds) and mAP (in AP11) compared to recent state-of-the-art secondary detectors

Stack_num	0	1	2	3	4	5	6
Improvement/ $AP_{3D}(\%)$	78.41	+0.11	+0.23	+0.38	+0.49	+0.58	+0.64

TABLE IV: Comparitive test of convolution layer parameter N in Percetion Stack

Method	$AP_{3D}$ (%)
Method	Easy	Mod	Hard
SECOND	83,52	73.63	67.21
SECOND+DH	84.44	74.25	67.61
Improvement	+0.92	+0.62	+0.40
VoxelNet	79.62	65.97	59.71
VoxelNet+DH	80.78	66.82	60.35

TABLE V: Comparative test of car class detection after TADH insertion in some one-stage networks.

3D Object Detection

3D object detection identifies objects and estimates their locations, sizes, and orientations from images, point clouds, radar, or fused sensors.

See all 183 papers

LOD-Net: Locality-Aware 3D Object Detection Using Multi-Scale Transformer Network
Apr 17, 2026Mustaqeem Khan, Aidana Nurakhmetova, Wail Gueaieb +13D ViTs Point Cloud Learning
College of Information Technology-United Arab Emirates University (UAEU), Al Ain, UAE · Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE · School of Elec. Eng. & Comp. Sc., University of Ottawa, Ottawa, ON, Canada
Shape-Prior-Based Point Cloud Completion for Single-Stage Fully Sparse 3D Object Detection
May 30, 2026Kaizheng Wang, Mingqian Ji, Jian Yang +1Point Cloud Completion 3D Reconstruction
School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China
Radar-Camera BEV Multi-Task Learning with Cross-Task Attention Bridge for Joint 3D Detection and Segmentation
Apr 14, 2026Ahmet İnanç, Özgür ErkentAutonomous Driving Perception Multi-Task Learning
Hacettepe University, Ankara, Turkey.

Apr 17, 2026J/K move · Enter open · S save

LOD-Net: Locality-Aware 3D Object Detection Using Multi-Scale Transformer Network

Mustaqeem Khan, Aidana Nurakhmetova, Wail Gueaieb, Abdulmotaleb El Saddik

College of Information Technology-United Arab Emirates University (UAEU), Al Ain, UAE · Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE · School of Elec. Eng. & Comp. Sc., University of Ottawa, Ottawa, ON, Canada

3D ViTs Point Cloud Learning Multi-Scale Feature Fusion 3D Object Detection

Open paper AskPDF arXiv

3D object detection in point cloud data remains a challenging task due to the sparsity and lack of global structure inherent in the input. In this work, we propose a novel Multi-Scale Attention (MSA) mechanism integrated into the 3DETR architecture to better capture both local geometry and global context. Our method introduces an upsampling operation that generates high-resolution feature maps, enabling the network to better detect smaller and semantically related objects. Experiments conducted on the ScanNetv2 dataset demonstrate that our 3DETR + MSA model improves detection performance, achieving a gain of almost 1% in mAP@25 and 4.78% in mAP@50 over the baseline. While applying MSA to the 3DETR-m variant shows limited improvement, our analysis reveals the importance of adapting the upsampling strategy for lightweight models. These results highlight the effectiveness of combining hierarchical feature extraction with attention mechanisms in enhancing 3D scene understanding.

Abstract

3D Object Detection

Explore similar work

LOD-Net: Locality-Aware 3D Object Detection Using Multi-Scale Transformer Network

Shape-Prior-Based Point Cloud Completion for Single-Stage Fully Sparse 3D Object Detection

Radar-Camera BEV Multi-Task Learning with Cross-Task Attention Bridge for Joint 3D Detection and Segmentation