BEV-Denoise: Learning Intrinsic Noise for Accurate Bird's-Eye-View Semantic Segmentation

• URL: http://arxiv.org/abs/2606.22931v1
• Date: Mon, 22 Jun 2026 07:06:46 GMT
• Title: BEV-Denoise: Learning Intrinsic Noise for Accurate Bird's-Eye-View Semantic Segmentation
• Abstract summary: We present a framework dubbed textbfBEV-Denoise that estimates and removes intrinsic noise from Bird's-Eye-View (BEV) features to achieve accurate BEV semantic segmentation.<n>Inspired by the noise estimation capability of Denoising Diffusion Probabilistic Models (DDPM), we design a UNet-based noise estimation module that learns to estimate the noise from the learned BEV features.<n>The estimated noise is then subtracted from the BEV features and fed to BEV map decoders for the final prediction results.
• Score: 3.568466510804539
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we present a framework dubbed \textbf{BEV-Denoise} that estimates and removes intrinsic noise from learned Bird's-Eye-View (BEV) features to achieve accurate BEV semantic segmentation. Inspired by the noise estimation capability of Denoising Diffusion Probabilistic Models (DDPM), we design a UNet-based noise estimation module that learns to estimate the noise from the learned BEV features. The estimated noise is then subtracted from the BEV features and fed to BEV map decoders for the final prediction results. To facilitate supervision for the noise estimation module, we follow a sequential learning paradigm called Task Decomposition (TD) where a pre-trained BEV map autoencoder is employed to train a view transformation (VT) encoder. We share three key insights learned from our intensive experiments that are critical for improved performance. We apply our framework to four existing models, encompassing the three major VT paradigms. Experimental results on a large-scale real-world dataset, nuScenes, demonstrate the effectiveness of our framework.

Related papers

• NoiseRater: Meta-Learned Noise Valuation for Diffusion Model Training [81.58321000203712]
  NoiseRater is a meta-learning framework for instance-level noise valuation in diffusion model training.<n>NoiseRater assigns importance scores to individual noise realizations conditioned on data and timestep.<n>Experiments on FFHQ and ImageNet demonstrate that not all noise samples contribute equally.
  arXiv  Detail & Related papers  (2026-05-02T19:43:16Z)
• BEVCon: Advancing Bird's Eye View Perception with Contrastive Learning [39.8617381331589]
  We present BEVCon, a contrastive learning framework designed to improve Bird's Eye View (BEV) perception in autonomous driving.<n>BEVCon achieves consistent performance gains, achieving up to +2.4% mAP improvement over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-08-06T17:59:37Z)
• NRSeg: Noise-Resilient Learning for BEV Semantic Segmentation via Driving World Models [24.239522252881336]
  Birds' Eye View (BEV) semantic segmentation is an indispensable perception task in end-to-end autonomous driving systems.<n>Unsupervised and semi-supervised learning for BEV tasks underperform due to the homogeneous distribution of the labeled data.<n>This paper proposes NRSeg, a noise-resilient learning framework for BEV semantic segmentation.
  arXiv  Detail & Related papers  (2025-07-05T11:05:43Z)
• BEVDiffuser: Plug-and-Play Diffusion Model for BEV Denoising with Ground-Truth Guidance [14.315057684079397]
  Bird's-eye-view (BEV) representations play a crucial role in autonomous driving tasks.<n> inherent noise, stemming from sensor limitations and the learning process, remains largely unaddressed.<n>We propose BEVDiffuser, a novel diffusion model that effectively denoises BEV feature maps using the ground-truth object layout as guidance.
  arXiv  Detail & Related papers  (2025-02-27T02:11:29Z)
• Enhance Vision-Language Alignment with Noise [59.2608298578913]
  We investigate whether the frozen model can be fine-tuned by customized noise.<n>We propose Positive-incentive Noise (PiNI) which can fine-tune CLIP via injecting noise into both visual and text encoders.
  arXiv  Detail & Related papers  (2024-12-14T12:58:15Z)
• Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Driving [55.93813178692077]
  We present RoboBEV, an extensive benchmark suite designed to evaluate the resilience of BEV algorithms.<n>We assess 33 state-of-the-art BEV-based perception models spanning tasks like detection, map segmentation, depth estimation, and occupancy prediction.<n>Our experimental results also underline the efficacy of strategies like pre-training and depth-free BEV transformations in enhancing robustness against out-of-distribution data.
  arXiv  Detail & Related papers  (2024-05-27T17:59:39Z)
• Impact of Noisy Supervision in Foundation Model Learning [91.56591923244943]
  This paper is the first work to comprehensively understand and analyze the nature of noise in pre-training datasets.<n>We propose a tuning method (NMTune) to affine the feature space to mitigate the malignant effect of noise and improve generalization.
  arXiv  Detail & Related papers  (2024-03-11T16:22:41Z)
• RadOcc: Learning Cross-Modality Occupancy Knowledge through Rendering Assisted Distillation [50.35403070279804]
  3D occupancy prediction is an emerging task that aims to estimate the occupancy states and semantics of 3D scenes using multi-view images. We propose RadOcc, a Rendering assisted distillation paradigm for 3D Occupancy prediction.
  arXiv  Detail & Related papers  (2023-12-19T03:39:56Z)
• Diffusion-Based Particle-DETR for BEV Perception [94.88305708174796]
  Bird-Eye-View (BEV) is one of the most widely-used scene representations for visual perception in Autonomous Vehicles (AVs) Recent diffusion-based methods offer a promising approach to uncertainty modeling for visual perception but fail to effectively detect small objects in the large coverage of the BEV. Here, we address this problem by combining the diffusion paradigm with current state-of-the-art 3D object detectors in BEV.
  arXiv  Detail & Related papers  (2023-12-18T09:52:14Z)
• BEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detection [47.7933708173225]
  Recently, the rise of query-based Transformer decoders is reshaping camera-based 3D object detection. This paper introduces a "modernized" dense BEV framework dubbed BEVNeXt. On the nuScenes benchmark, BEVNeXt outperforms both BEV-based and query-based frameworks.
  arXiv  Detail & Related papers  (2023-12-04T07:35:02Z)
• DiffBEV: Conditional Diffusion Model for Bird's Eye View Perception [14.968177102647783]
  We propose an end-to-end framework, named DiffBEV, to exploit the potential of diffusion model to generate a more comprehensive BEV representation. In practice, we design three types of conditions to guide the training of the diffusion model which denoises the coarse samples and refines the semantic feature. We show that DiffBEV achieves a 25.9% mIoU on the nuScenes dataset, which is 6.2% higher than the best-performing existing approach.
  arXiv  Detail & Related papers  (2023-03-15T02:42:48Z)

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.