SPAN: Spatial-Projection Alignment for Monocular 3D Object Detection

• URL: http://arxiv.org/abs/2511.06702v1
• Date: Mon, 10 Nov 2025 04:48:48 GMT
• Title: SPAN: Spatial-Projection Alignment for Monocular 3D Object Detection
• Abstract summary: Existing monocular 3D detectors typically tame the pronounced nonlinear regression of 3D bounding box through decoupled prediction paradigm.<n>We propose novel Spatial-Projection Alignment (SPAN) with two pivotal components.<n>SPAN enforces an explicit global spatial constraint between the predicted and ground-truth 3D bounding boxes, thereby rectifying spatial drift caused by decoupled attribute regression.<n>3D-2D Projection Alignment ensures that the projected 3D box is aligned tightly within its corresponding 2D detection bounding box on the image plane, mitigating projection misalignment overlooked in previous works.
• Score: 49.12928389918159
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Existing monocular 3D detectors typically tame the pronounced nonlinear regression of 3D bounding box through decoupled prediction paradigm, which employs multiple branches to estimate geometric center, depth, dimensions, and rotation angle separately. Although this decoupling strategy simplifies the learning process, it inherently ignores the geometric collaborative constraints between different attributes, resulting in the lack of geometric consistency prior, thereby leading to suboptimal performance. To address this issue, we propose novel Spatial-Projection Alignment (SPAN) with two pivotal components: (i). Spatial Point Alignment enforces an explicit global spatial constraint between the predicted and ground-truth 3D bounding boxes, thereby rectifying spatial drift caused by decoupled attribute regression. (ii). 3D-2D Projection Alignment ensures that the projected 3D box is aligned tightly within its corresponding 2D detection bounding box on the image plane, mitigating projection misalignment overlooked in previous works. To ensure training stability, we further introduce a Hierarchical Task Learning strategy that progressively incorporates spatial-projection alignment as 3D attribute predictions refine, preventing early stage error propagation across attributes. Extensive experiments demonstrate that the proposed method can be easily integrated into any established monocular 3D detector and delivers significant performance improvements.

Related papers

• TDFNet: Tri-projection Deformable Fusion Network for Panoramic Salient Object Detection [13.394581946335949]
  We propose TDFNet, the first Tri-projection Deformable Fusion Network for panoramic salient object detection.<n>We exploit complementary projection representations to alleviate geometric distortions and improve detection performance.<n>TDFNet simultaneously preserves global spatial continuity, local geometric details, and fine-grained boundary information.
  arXiv  Detail & Related papers  (2026-08-26T13:54:44Z)
• SeeSE3: Emergence of 3D Space in Vision Features [54.140615953727355]
  We investigate the relation between the structure of the space of visual features and the group of Euclidean transformations $SE(3)$.<n>We show that self-supervised vision models, which, in principle, have not been trained with direct 3D supervision or active agency, possess latent subspaces that are remarkably strongly correlated with 3D Euclidean space, when probed correctly.<n>We propose a new class of "Latent-Space Navigation" techniques that perform visual odometry and localization purely in the latent space, bypassing the need for explicit 3D reconstruction.
  arXiv  Detail & Related papers  (2026-07-15T18:00:31Z)
• SpatialFly: Geometry-Guided Representation Alignment for UAV Vision-and-Language Navigation in Urban Environments [49.966170814478915]
  We propose a geometry-guided spatial representation framework for UAV VLN.<n>Running on RGB observations without explicit 3D reconstruction, SpatialFly introduces a geometry-guided 2D representation alignment mechanism.<n> Experimental results show that SpatialFly consistently outperforms state-of-the-art UAV VLN baselines across both seen and unseen environments.
  arXiv  Detail & Related papers  (2026-03-22T03:56:58Z)
• Interact3D: Compositional 3D Generation of Interactive Objects [31.12099147294145]
  We present a novel framework designed to generate physically plausible interacting 3D compositional objects.<n>Our approach first leverages advanced generative priors to curate high-quality individual assets.<n>To physically compose these assets, we then introduce a robust two-stage composition pipeline.
  arXiv  Detail & Related papers  (2026-03-17T03:21:06Z)
• Mono3DV: Monocular 3D Object Detection with 3D-Aware Bipartite Matching and Variational Query DeNoising [0.6423989407081764]
  Mono3DV is a novel Transformer-based framework for 3D object detection.<n>We develop a 3D-Aware Bipartite Matching strategy that directly incorporates 3D geometric information into the matching cost.<n>Second, it is important to stabilize the Bipartite Matching to resolve the instability occurring when integrating 3D attributes.
  arXiv  Detail & Related papers  (2026-01-03T02:06:28Z)
• RQR3D: Reparametrizing the regression targets for BEV-based 3D object detection [0.4604003661048266]
  Bird's-eye view (BEV)-based perception approaches have emerged as superior alternatives to perspective-based solutions.<n>We propose Restricted Quadrilateral Representation to define 3D regression targets.<n>RQR3D regresses the smallest horizontal bounding box encapsulating the oriented box, along with the offsets between the corners of these two boxes.
  arXiv  Detail & Related papers  (2025-05-23T10:52:34Z)
• NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Space [77.6067460464962]
  Monocular 3D Semantic Scene Completion (SSC) has garnered significant attention in recent years due to its potential to predict complex semantics and geometry shapes from a single image, requiring no 3D inputs. We identify several critical issues in current state-of-the-art methods, including the Feature Ambiguity of projected 2D features in the ray to the 3D space, the Pose Ambiguity of the 3D convolution, and the Imbalance in the 3D convolution across different depth levels. We devise a novel Normalized Device Coordinates scene completion network (NDC-Scene) that directly extends the 2
  arXiv  Detail & Related papers  (2023-09-26T02:09:52Z)
• OriCon3D: Effective 3D Object Detection using Orientation and Confidence [0.0]
  We propose an advanced methodology for the detection of 3D objects from a single image. We use a deep convolutional neural network-based 3D object weighted orientation regression paradigm. Our approach significantly improves the accuracy of 3D object pose determination, surpassing baseline methodologies.
  arXiv  Detail & Related papers  (2023-04-27T19:52:47Z)
• OPA-3D: Occlusion-Aware Pixel-Wise Aggregation for Monocular 3D Object Detection [51.153003057515754]
  OPA-3D is a single-stage, end-to-end, Occlusion-Aware Pixel-Wise Aggregation network. It jointly estimates dense scene depth with depth-bounding box residuals and object bounding boxes. It outperforms state-of-the-art methods on the main Car category.
  arXiv  Detail & Related papers  (2022-11-02T14:19:13Z)
• Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perception [122.53774221136193]
  State-of-the-art methods for driving-scene LiDAR-based perception often project the point clouds to 2D space and then process them via 2D convolution. A natural remedy is to utilize the 3D voxelization and 3D convolution network. We propose a new framework for the outdoor LiDAR segmentation, where cylindrical partition and asymmetrical 3D convolution networks are designed to explore the 3D geometric pattern.
  arXiv  Detail & Related papers  (2021-09-12T06:25:11Z)
• MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagation [4.202461384355329]
  We propose MonoRUn, a novel 3D object detection framework that learns dense correspondences and geometry in a self-supervised manner. Our proposed approach outperforms current state-of-the-art methods on KITTI benchmark.
  arXiv  Detail & Related papers  (2021-03-23T15:03:08Z)
• Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation [81.02742110604161]
  State-of-the-art methods for large-scale driving-scene LiDAR segmentation often project the point clouds to 2D space and then process them via 2D convolution. We propose a new framework for the outdoor LiDAR segmentation, where cylindrical partition and asymmetrical 3D convolution networks are designed to explore the 3D geometric pat-tern. Our method achieves the 1st place in the leaderboard of Semantic KITTI and outperforms existing methods on nuScenes with a noticeable margin, about 4%.
  arXiv  Detail & Related papers  (2020-11-19T18:53:11Z)
• Reinforced Axial Refinement Network for Monocular 3D Object Detection [160.34246529816085]
  Monocular 3D object detection aims to extract the 3D position and properties of objects from a 2D input image. Conventional approaches sample 3D bounding boxes from the space and infer the relationship between the target object and each of them, however, the probability of effective samples is relatively small in the 3D space. We propose to start with an initial prediction and refine it gradually towards the ground truth, with only one 3d parameter changed in each step. This requires designing a policy which gets a reward after several steps, and thus we adopt reinforcement learning to optimize it.
  arXiv  Detail & Related papers  (2020-08-31T17:10:48Z)

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.