FreqPDE: Rethinking Positional Depth Embedding for Multi-View 3D Object Detection Transformers

• URL: http://arxiv.org/abs/2510.15385v1
• Date: Fri, 17 Oct 2025 07:36:54 GMT
• Title: FreqPDE: Rethinking Positional Depth Embedding for Multi-View 3D Object Detection Transformers
• Authors: Haisheng Su, Junjie Zhang, Feixiang Song, Sanping Zhou, Wei Wu, Nanning Zheng, Junchi Yan,
• Abstract summary: We introduce Frequency-aware Positional Depth Embedding (FreqPDE) to equip 2D image features with spatial information for 3D detection transformer decoder.<n>FreqPDE combines the 2D image features and 3D position embeddings to generate 3D depth-aware features for query decoding.
• Score: 91.59069344768858
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Detecting 3D objects accurately from multi-view 2D images is a challenging yet essential task in the field of autonomous driving. Current methods resort to integrating depth prediction to recover the spatial information for object query decoding, which necessitates explicit supervision from LiDAR points during the training phase. However, the predicted depth quality is still unsatisfactory such as depth discontinuity of object boundaries and indistinction of small objects, which are mainly caused by the sparse supervision of projected points and the use of high-level image features for depth prediction. Besides, cross-view consistency and scale invariance are also overlooked in previous methods. In this paper, we introduce Frequency-aware Positional Depth Embedding (FreqPDE) to equip 2D image features with spatial information for 3D detection transformer decoder, which can be obtained through three main modules. Specifically, the Frequency-aware Spatial Pyramid Encoder (FSPE) constructs a feature pyramid by combining high-frequency edge clues and low-frequency semantics from different levels respectively. Then the Cross-view Scale-invariant Depth Predictor (CSDP) estimates the pixel-level depth distribution with cross-view and efficient channel attention mechanism. Finally, the Positional Depth Encoder (PDE) combines the 2D image features and 3D position embeddings to generate the 3D depth-aware features for query decoding. Additionally, hybrid depth supervision is adopted for complementary depth learning from both metric and distribution aspects. Extensive experiments conducted on the nuScenes dataset demonstrate the effectiveness and superiority of our proposed method.

Related papers

• OPEN: Object-wise Position Embedding for Multi-view 3D Object Detection [102.0744303467713]
  We propose a new multi-view 3D object detector named OPEN. Our main idea is to effectively inject object-wise depth information into the network through our proposed object-wise position embedding. OPEN achieves a new state-of-the-art performance with 64.4% NDS and 56.7% mAP on the nuScenes test benchmark.
  arXiv  Detail & Related papers  (2024-07-15T14:29:15Z)
• Toward Accurate Camera-based 3D Object Detection via Cascade Depth Estimation and Calibration [20.82054596017465]
  Recent camera-based 3D object detection is limited by the precision of transforming from image to 3D feature spaces. This paper aims to address such a fundamental problem of camera-based 3D object detection: How to effectively learn depth information for accurate feature lifting and object localization.
  arXiv  Detail & Related papers  (2024-02-07T14:21:26Z)
• Perspective-aware Convolution for Monocular 3D Object Detection [2.33877878310217]
  We propose a novel perspective-aware convolutional layer that captures long-range dependencies in images. By enforcing convolutional kernels to extract features along the depth axis of every image pixel, we incorporates perspective information into network architecture. We demonstrate improved performance on the KITTI3D dataset, achieving a 23.9% average precision in the easy benchmark.
  arXiv  Detail & Related papers  (2023-08-24T17:25:36Z)
• MonoPGC: Monocular 3D Object Detection with Pixel Geometry Contexts [6.639648061168067]
  We propose MonoPGC, a novel end-to-end Monocular 3D object detection framework with rich Pixel Geometry Contexts. We introduce the pixel depth estimation as our auxiliary task and design depth cross-attention pyramid module (DCPM) to inject local and global depth geometry knowledge into visual features. In addition, we present the depth-space-aware transformer (DSAT) to integrate 3D space position and depth-aware features efficiently.
  arXiv  Detail & Related papers  (2023-02-21T09:21:58Z)
• OA-DET3D: Embedding Object Awareness as a General Plug-in for Multi-Camera 3D Object Detection [77.43427778037203]
  We introduce OA-DET3D, a plug-in module that improves 3D object detection.<n> OA-DET3D boosts the representation of objects by leveraging object-centric depth information and foreground pseudo points.<n>We conduct extensive experiments on the nuScenes dataset and Argoverse 2 dataset to validate the merits of OA-DET3D.
  arXiv  Detail & Related papers  (2023-01-13T06:02:31Z)
• Boosting Monocular 3D Object Detection with Object-Centric Auxiliary Depth Supervision [13.593246617391266]
  We propose a method to boost the RGB image-based 3D detector by jointly training the detection network with a depth prediction loss analogous to the depth estimation task. Our novel object-centric depth prediction loss focuses on depth around foreground objects, which is important for 3D object detection. Our depth regression model is further trained to predict the uncertainty of depth to represent the 3D confidence of objects.
  arXiv  Detail & Related papers  (2022-10-29T11:32:28Z)
• MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection [57.969536140562674]
  We introduce the first DETR framework for Monocular DEtection with a depth-guided TRansformer, named MonoDETR.<n>We formulate 3D object candidates as learnable queries and propose a depth-guided decoder to conduct object-scene depth interactions.<n>On KITTI benchmark with monocular images as input, MonoDETR achieves state-of-the-art performance and requires no extra dense depth annotations.
  arXiv  Detail & Related papers  (2022-03-24T19:28:54Z)
• Joint Learning of Salient Object Detection, Depth Estimation and Contour Extraction [91.43066633305662]
  We propose a novel multi-task and multi-modal filtered transformer (MMFT) network for RGB-D salient object detection (SOD) Specifically, we unify three complementary tasks: depth estimation, salient object detection and contour estimation. The multi-task mechanism promotes the model to learn the task-aware features from the auxiliary tasks. Experiments show that it not only significantly surpasses the depth-based RGB-D SOD methods on multiple datasets, but also precisely predicts a high-quality depth map and salient contour at the same time.
  arXiv  Detail & Related papers  (2022-03-09T17:20:18Z)
• M3DSSD: Monocular 3D Single Stage Object Detector [82.25793227026443]
  We propose a Monocular 3D Single Stage object Detector (M3DSSD) with feature alignment and asymmetric non-local attention. The proposed M3DSSD achieves significantly better performance than the monocular 3D object detection methods on the KITTI dataset.
  arXiv  Detail & Related papers  (2021-03-24T13:09:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.