NCGR: Noise-Conditional Gated Rectification for Camera Extrinsic Perturbations in BEV 3D Object Detection

• URL: http://arxiv.org/abs/2608.03895v1
• Date: Tue, 04 Aug 2026 16:26:57 GMT
• Title: NCGR: Noise-Conditional Gated Rectification for Camera Extrinsic Perturbations in BEV 3D Object Detection
• Abstract summary: Camera-based bird's-eye-view (BEV) 3D detection typically assumes accurate and fixed camera extrinsics.<n>In detectors using spatial cross-attention (SCA), extrinsic perturbations displace the image-plane projections of BEV reference points.<n>Noise-Conditional Gated Rectification (NCGR) is proposed to compensate for projection errors without explicitly estimating a full six-degree-of-freedom extrinsic correction.
• Score: 15.441348570437194
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Camera-based bird's-eye-view (BEV) 3D detection typically assumes accurate and fixed camera extrinsics. In detectors using spatial cross-attention (SCA), extrinsic perturbations displace the image-plane projections of BEV reference points, causing queries to sample features from incorrect regions and degrading detection performance. To address this failure mode, Noise-Conditional Gated Rectification (NCGR) is proposed to compensate for projection errors without explicitly estimating a full six-degree-of-freedom extrinsic correction. For each query-camera pair, a 2D rectification offset is predicted and modulated by a camera-level gate to rectify the base projection before native deformable sampling. During training, the perturbation-derived quantities used to construct the condition and gate are gradually replaced through scheduled interpolation by counterparts generated from an auxiliary scalar predicted from camera features. This transition enables blind inference without perturbation metadata. During training, a weight-shared clean-teacher/perturbed-student pair is used, and the rectification module is supervised by a BEV-consistency objective between the two branches. NCGR is evaluated on nuScenes with simulated dynamic and static extrinsic perturbations. In a five-camera dynamic stress test, NCGR achieves 39.69% NDS, compared with 28.00% for BEVFormer and 33.23% for CAPE. Under clean extrinsics, NCGR maintains performance comparable to that of BEVFormer.

Related papers

• RECO: Region-Aware Compensation for Extrinsic Perturbations in Roadside 3D Detection [13.05494342638977]
  Roadside 3D object detection provides wide-area perception crucial for traffic understanding, cooperative early warning, and safe autonomous driving.<n>Existing methods suffer from high sensitivity to camera extrinsics; even slight deviations can be amplified by projective geometry.<n>We propose RECO, a region-aware extrinsic compensation framework that corrects extrinsics using piecewise 6-DoF pose offsets.
  arXiv  Detail & Related papers  (2026-07-23T05:56:42Z)
• QVGGT: Post-Training Quantized Visual Geometry Grounded Transformer [5.7977296539841845]
  We introduce QVGGT, a tailored quantization framework designed to compress Visual Geometry Grounded Transformer (VGGT)<n>QVGGT achieves near-lossless W4A16 quantization, preserving the accuracy of all 3D prediction heads while delivering 3$sim$4.9$times$ memory reduction and up to 2.8$times$ real hardware speedup over FP32.<n>Our approach makes high-fidelity 3D perception feasible on edge devices, enabling practical deployment of feed-forward 3D reconstruction models in real-world constrained environments.
  arXiv  Detail & Related papers  (2026-05-29T10:32:52Z)
• 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)
• RaCFormer: Towards High-Quality 3D Object Detection via Query-based Radar-Camera Fusion [58.77329237533034]
  We propose a Radar-Camera fusion transformer (RaCFormer) to boost the accuracy of 3D object detection.<n>RaCFormer achieves superior results of 64.9% mAP and 70.2% on nuScenes datasets.
  arXiv  Detail & Related papers  (2024-12-17T09:47:48Z)
• Cameras as Rays: Pose Estimation via Ray Diffusion [54.098613859015856]
  Estimating camera poses is a fundamental task for 3D reconstruction and remains challenging given sparsely sampled views. We propose a distributed representation of camera pose that treats a camera as a bundle of rays. Our proposed methods, both regression- and diffusion-based, demonstrate state-of-the-art performance on camera pose estimation on CO3D.
  arXiv  Detail & Related papers  (2024-02-22T18:59:56Z)
• iComMa: Inverting 3D Gaussian Splatting for Camera Pose Estimation via Comparing and Matching [14.737266480464156]
  We present a method named iComMa to address the 6D camera pose estimation problem in computer vision. We propose an efficient method for accurate camera pose estimation by inverting 3D Gaussian Splatting (3DGS)
  arXiv  Detail & Related papers  (2023-12-14T15:31:33Z)
• SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videos [20.51396212498941]
  SparseBEV is a fully sparse 3D object detector that outperforms the dense counterparts. On the test split of nuScenes, SparseBEV achieves the state-of-the-art performance of 67.5 NDS.
  arXiv  Detail & Related papers  (2023-08-18T02:11:01Z)
• BEV-IO: Enhancing Bird's-Eye-View 3D Detection with Instance Occupancy [58.92659367605442]
  We present BEV-IO, a new 3D detection paradigm to enhance BEV representation with instance occupancy information. We show that BEV-IO can outperform state-of-the-art methods while only adding a negligible increase in parameters and computational overhead.
  arXiv  Detail & Related papers  (2023-05-26T11:16:12Z)
• NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimation [53.25973084799954]
  We present NIKI (Neural Inverse Kinematics with Invertible Neural Network), which models bi-directional errors. NIKI can learn from both the forward and inverse processes with invertible networks.
  arXiv  Detail & Related papers  (2023-05-15T12:13:24Z)
• Detecting Rotated Objects as Gaussian Distributions and Its 3-D Generalization [81.29406957201458]
  Existing detection methods commonly use a parameterized bounding box (BBox) to model and detect (horizontal) objects. We argue that such a mechanism has fundamental limitations in building an effective regression loss for rotation detection. We propose to model the rotated objects as Gaussian distributions. We extend our approach from 2-D to 3-D with a tailored algorithm design to handle the heading estimation.
  arXiv  Detail & Related papers  (2022-09-22T07:50:48Z)
• Uncertainty-Aware Camera Pose Estimation from Points and Lines [101.03675842534415]
  Perspective-n-Point-and-Line (Pn$PL) aims at fast, accurate and robust camera localizations with respect to a 3D model from 2D-3D feature coordinates.
  arXiv  Detail & Related papers  (2021-07-08T15:19:36Z)

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.