SplatPose & Detect: Pose-Agnostic 3D Anomaly Detection
- URL: http://arxiv.org/abs/2404.06832v1
- Date: Wed, 10 Apr 2024 08:48:09 GMT
- Title: SplatPose & Detect: Pose-Agnostic 3D Anomaly Detection
- Authors: Mathis Kruse, Marco Rudolph, Dominik Woiwode, Bodo Rosenhahn,
- Abstract summary: State-of-the-art algorithms are able to detect defects in increasingly difficult settings and data modalities.
We propose the novel 3D Gaussian splatting-based framework SplatPose which accurately estimates the pose of unseen views in a differentiable manner.
We achieve state-of-the-art results in both training and inference speed, and detection performance, even when using less training data than competing methods.
- Score: 18.796625355398252
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Detecting anomalies in images has become a well-explored problem in both academia and industry. State-of-the-art algorithms are able to detect defects in increasingly difficult settings and data modalities. However, most current methods are not suited to address 3D objects captured from differing poses. While solutions using Neural Radiance Fields (NeRFs) have been proposed, they suffer from excessive computation requirements, which hinder real-world usability. For this reason, we propose the novel 3D Gaussian splatting-based framework SplatPose which, given multi-view images of a 3D object, accurately estimates the pose of unseen views in a differentiable manner, and detects anomalies in them. We achieve state-of-the-art results in both training and inference speed, and detection performance, even when using less training data than competing methods. We thoroughly evaluate our framework using the recently proposed Pose-agnostic Anomaly Detection benchmark and its multi-pose anomaly detection (MAD) data set.
Related papers
- Towards Zero-shot 3D Anomaly Localization [58.62650061201283]
3DzAL is a novel patch-level contrastive learning framework for 3D anomaly detection and localization.
We show that 3DzAL outperforms the state-of-the-art anomaly detection and localization performance.
arXiv Detail & Related papers (2024-12-05T16:25:27Z) - RIGI: Rectifying Image-to-3D Generation Inconsistency via Uncertainty-aware Learning [27.4552892119823]
inconsistencies in multi-view snapshots frequently introduce noise and artifacts along object boundaries, undermining the 3D reconstruction process.
We leverage 3D Gaussian Splatting (3DGS) for 3D reconstruction, and explicitly integrate uncertainty-aware learning into the reconstruction process.
We apply adaptive pixel-wise loss weighting to regularize the models, reducing reconstruction intensity in high-uncertainty regions.
arXiv Detail & Related papers (2024-11-28T02:19:28Z) - PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting [54.7468067660037]
PF3plat sets a new state-of-the-art across all benchmarks, supported by comprehensive ablation studies validating our design choices.
Our framework capitalizes on fast speed, scalability, and high-quality 3D reconstruction and view synthesis capabilities of 3DGS.
arXiv Detail & Related papers (2024-10-29T15:28:15Z) - CatFree3D: Category-agnostic 3D Object Detection with Diffusion [63.75470913278591]
We introduce a novel pipeline that decouples 3D detection from 2D detection and depth prediction.
We also introduce the Normalised Hungarian Distance (NHD) metric for an accurate evaluation of 3D detection results.
arXiv Detail & Related papers (2024-08-22T22:05:57Z) - PAD: A Dataset and Benchmark for Pose-agnostic Anomaly Detection [28.973078719467516]
We develop Multi-pose Anomaly Detection dataset and Pose-agnostic Anomaly Detection benchmark.
Specifically, we build MAD using 20 complex-shaped LEGO toys with various poses, and high-quality and diverse 3D anomalies in both simulated and real environments.
We also propose a novel method OmniposeAD, trained using MAD, specifically designed for pose-agnostic anomaly detection.
arXiv Detail & Related papers (2023-10-11T17:59:56Z) - Predict to Detect: Prediction-guided 3D Object Detection using
Sequential Images [15.51093009875854]
We propose a novel 3D object detection model, P2D (Predict to Detect), that integrates a prediction scheme into a detection framework.
P2D predicts object information in the current frame using solely past frames to learn temporal motion features.
We then introduce a novel temporal feature aggregation method that attentively exploits Bird's-Eye-View (BEV) features based on predicted object information.
arXiv Detail & Related papers (2023-06-14T14:22:56Z) - PONet: Robust 3D Human Pose Estimation via Learning Orientations Only [116.1502793612437]
We propose a novel Pose Orientation Net (PONet) that is able to robustly estimate 3D pose by learning orientations only.
PONet estimates the 3D orientation of these limbs by taking advantage of the local image evidence to recover the 3D pose.
We evaluate our method on multiple datasets, including Human3.6M, MPII, MPI-INF-3DHP, and 3DPW.
arXiv Detail & Related papers (2021-12-21T12:48:48Z) - Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation [14.413034040734477]
We present a novel skeletal GNN learning solution for hard poses with depth ambiguity, self-occlusion, and complex poses.
Experimental results on the Human3.6M dataset show that our solution achieves 10.3% average prediction accuracy improvement.
arXiv Detail & Related papers (2021-08-16T15:42:09Z) - 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) - Delving into Localization Errors for Monocular 3D Object Detection [85.77319416168362]
Estimating 3D bounding boxes from monocular images is an essential component in autonomous driving.
In this work, we quantify the impact introduced by each sub-task and find the localization error' is the vital factor in restricting monocular 3D detection.
arXiv Detail & Related papers (2021-03-30T10:38:01Z)
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.