Co-Fusion4D: Spatio-temporal Collaborative Fusion for Robust 3D Object Detection

• URL: http://arxiv.org/abs/2605.20301v1
• Date: Tue, 19 May 2026 12:36:09 GMT
• Title: Co-Fusion4D: Spatio-temporal Collaborative Fusion for Robust 3D Object Detection
• Abstract summary: In 3D object detection, object and ego-motion inconsistencies often cross-frame inconsistencies in BE-based detectors.<n>We propose Co-Fusion4D, a framework that unifies cross-frame consistency and temporal drift feature drift.<n>Co-Fusion4D achieves state-of-the-art performance with 74.9% mAP and 75.6% NDS, without relying on test-time augmentation or external data.
• Score: 11.282817014403198
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: In autonomous driving, 3D object detection is essential for accurate perception and reliable decision-making. However, object motion and ego-motion often induce cross-frame spatiotemporal inconsistencies in BEV-based detectors, leading to temporal BEV feature misalignment and degraded spatiotemporal consistency. To address these challenges, we propose Co-Fusion4D, a unified framework that explicitly preserves cross-frame spatiotemporal consistency and suppresses temporal feature drift. Co-Fusion4D adopts a current-frame-centric strategy, treating the current frame as the primary source of information while selectively incorporating historical frames after spatiotemporal filtering and alignment. This dominant-complementary mechanism effectively mitigates cumulative alignment errors, suppresses noisy feature propagation, and exploits reliable temporal cues for a more consistent BEV representation. In addition, Co-Fusion4D integrates a Dual Attention Fusion (DAF) module to further enhance spatiotemporal feature interaction. DAF jointly leverages intra-frame spatial attention and inter-frame temporal attention to adaptively align and fuse multi-frame features, emphasizing motion-consistent regions while suppressing spurious correlations. By departing from conventional uniform fusion paradigms, this design substantially improves the temporal stability and discriminative capability of BEV representations. Extensive experiments on the nuScenes benchmark demonstrate that Co-Fusion4D achieves state-of-the-art performance, with 74.9% mAP and 75.6% NDS, without relying on test-time augmentation or external data.

Related papers

• ASTRA: Asynchronous Spatio-Temporal Reconstruction via Trajectory Alignment [86.35109211408489]
  We propose ASTRA, a framework that introduces 2D motion trajectories as explicit, texture-agnostic supervision for asynchronous dynamic reconstruction.<n>ASTRA preserves high-frequency spatial details and sustains strong robustness even under severe asynchrony with up to 25-frame offsets, achieving approximately 1.4 dB PSNR improvement, reducing temporal-offset MAE by 54.0%, and nearly quadrupling the synchronization success rate.
  arXiv  Detail & Related papers  (2026-08-03T10:06:45Z)
• Deformable Gaussian Occupancy: Decoupling Rigid and Nonrigid Motion with Factorized Distillation [81.44955493339835]
  DeGO is a deformable Gaussian occupancy framework that unifies decoupled Gaussian deformation with factorized 4D foundation-model distillation.<n> Experiments on the Occ3D-NuScenes benchmark demonstrate that our method achieves state-of-the-art performance under weak supervision.
  arXiv  Detail & Related papers  (2026-05-27T15:09:55Z)
• Towards Physically Consistent 4D Scene Reconstruction for Closed-loop Autonomous Driving Simulation [19.055975606481635]
  High-fidelity street scene reconstruction is pivotal for end-to-end autonomous driving simulation.<n>Existing 3DGS methods and their 4D extensions fail to simultaneously achieve both.<n>We propose Orthogonal Projected Gradient (OPG) to restore spatial identifiability.
  arXiv  Detail & Related papers  (2026-05-20T11:09:53Z)
• RAFT-MSF++: Temporal Geometry-Motion Feature Fusion for Self-Supervised Monocular Scene Flow [51.43025173196566]
  Monocular scene flow estimation aims to recover dense 3D motion from image sequences.<n>We propose RAFT-MSF++, a self-supervised multi-frame framework that fuses temporal features to jointly estimate depth and scene flow.<n>Experiments show that RAFT-MSF++ achieves 24.14% SF-all on the KITTI Scene Flow benchmark, with a 30.99% improvement over the baseline and better robustness in occluded regions.
  arXiv  Detail & Related papers  (2026-04-21T11:32:49Z)
• MambaFusion: Adaptive State-Space Fusion for Multimodal 3D Object Detection [6.350460753267439]
  MambaFusion is a unified multi-modal detection framework that achieves efficient, adaptive, and physically grounded 3D perception.<n>A structure-conditioned diffusion head integrates graph-based reasoning with uncertainty-aware denoising, enforcing physical plausibility, and calibrated confidence.<n>The framework demonstrates that coupling SSM-based efficiency with reliability-driven fusion yields robust, temporally stable, and interpretable 3D perception for real-world autonomous driving systems.
  arXiv  Detail & Related papers  (2026-02-08T21:10:46Z)
• Diffusion-Based Restoration for Multi-Modal 3D Object Detection in Adverse Weather [15.57759675028067]
  DiffFusion is a novel framework designed to enhance robustness in challenging weather.<n>Our key insight is that diffusion models possess strong capabilities for denoising and generating data.<n> implementation of our DiffFusion will be released as open-source.
  arXiv  Detail & Related papers  (2025-12-15T09:03:46Z)
• DVLO4D: Deep Visual-Lidar Odometry with Sparse Spatial-temporal Fusion [28.146811420532455]
  We introduce DVLO4D, a novel visual-LiDAR odometry framework that leverages sparse spatial-temporal fusion to enhance accuracy and robustness.<n>Our method has high efficiency, with an inference time of 82 ms, possessing the potential for the real-time deployment.
  arXiv  Detail & Related papers  (2025-09-07T11:43:11Z)
• Adaptive Dual Uncertainty Optimization: Boosting Monocular 3D Object Detection under Test-Time Shifts [80.32933059529135]
  Test-Time Adaptation (TTA) methods have emerged to adapt to target distributions during inference.<n>We propose Dual Uncertainty Optimization (DUO), the first TTA framework designed to jointly minimize both uncertainties for robust M3OD.<n>In parallel, we design a semantic-aware normal field constraint that preserves geometric coherence in regions with clear semantic cues.
  arXiv  Detail & Related papers  (2025-08-28T07:09:21Z)
• Cross-modal Offset-guided Dynamic Alignment and Fusion for Weakly Aligned UAV Object Detection [0.0]
  Unmanned aerial vehicle (UAV) object detection plays a vital role in applications such as environmental monitoring and urban security.<n>Due to UAV platform motion and asynchronous imaging, spatial misalignment frequently occurs between modalities, leading to weak alignment.<n>We propose Cross-modal Offset-guided Dynamic Alignment and Fusion (CoDAF) to address these issues.
  arXiv  Detail & Related papers  (2025-06-20T04:11:39Z)
• Rethinking Temporal Fusion with a Unified Gradient Descent View for 3D Semantic Occupancy Prediction [62.69089767730514]
  We present GDFusion, a temporal fusion method for vision-based 3D semantic occupancy prediction (VisionOcc)<n>It opens up the underexplored aspects of temporal fusion within the VisionOcc framework, focusing on both temporal cues and fusion strategies.
  arXiv  Detail & Related papers  (2025-04-17T14:05:33Z)
• Learning to Align and Refine: A Foundation-to-Diffusion Framework for Occlusion-Robust Two-Hand Reconstruction [50.952228546326516]
  Two-hand reconstruction from monocular images faces persistent challenges due to complex and dynamic hand postures.<n>Existing approaches struggle with such alignment issues, often resulting in misalignment and penetration artifacts.<n>We propose a dual-stage Foundation-to-Diffusion framework that precisely align 2D prior guidance from vision foundation models.
  arXiv  Detail & Related papers  (2025-03-22T14:42:27Z)
• Decoupling and Recoupling Spatiotemporal Representation for RGB-D-based Motion Recognition [62.46544616232238]
  Previous motion recognition methods have achieved promising performance through the tightly coupled multi-temporal representation. We propose to decouple and recouple caused caused representation for RGB-D-based motion recognition.
  arXiv  Detail & Related papers  (2021-12-16T18:59:47Z)

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.