PruNeRF: Segment-Centric Dataset Pruning via 3D Spatial Consistency
- URL: http://arxiv.org/abs/2406.00798v1
- Date: Sun, 2 Jun 2024 16:49:05 GMT
- Title: PruNeRF: Segment-Centric Dataset Pruning via 3D Spatial Consistency
- Authors: Yeonsung Jung, Heecheol Yun, Joonhyung Park, Jin-Hwa Kim, Eunho Yang,
- Abstract summary: PruNeRF is a segment-centric dataset pruning framework via 3D spatial consistency.
Our experiments on benchmark datasets demonstrate that PruNeRF consistently outperforms state-of-the-art methods in robustness against distractors.
- Score: 33.68948881727943
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Neural Radiance Fields (NeRF) have shown remarkable performance in learning 3D scenes. However, NeRF exhibits vulnerability when confronted with distractors in the training images -- unexpected objects are present only within specific views, such as moving entities like pedestrians or birds. Excluding distractors during dataset construction is a straightforward solution, but without prior knowledge of their types and quantities, it becomes prohibitively expensive. In this paper, we propose PruNeRF, a segment-centric dataset pruning framework via 3D spatial consistency, that effectively identifies and prunes the distractors. We first examine existing metrics for measuring pixel-wise distraction and introduce Influence Functions for more accurate measurements. Then, we assess 3D spatial consistency using a depth-based reprojection technique to obtain 3D-aware distraction. Furthermore, we incorporate segmentation for pixel-to-segment refinement, enabling more precise identification. Our experiments on benchmark datasets demonstrate that PruNeRF consistently outperforms state-of-the-art methods in robustness against distractors.
Related papers
- The Devil is in the Details: Simple Remedies for Image-to-LiDAR Representation Learning [21.088879084249328]
We focus on overlooked design choices along the spatial and temporal axes.
We find that fundamental design elements, e.g., the LiDAR coordinate system, quantization according to the existing input interface, are more critical than developing loss functions.
arXiv Detail & Related papers (2025-01-16T11:44:29Z) - FILP-3D: Enhancing 3D Few-shot Class-incremental Learning with Pre-trained Vision-Language Models [59.13757801286343]
Few-shot class-incremental learning aims to mitigate the catastrophic forgetting issue when a model is incrementally trained on limited data.
We introduce the FILP-3D framework with two novel components: the Redundant Feature Eliminator (RFE) for feature space misalignment and the Spatial Noise Compensator (SNC) for significant noise.
arXiv Detail & Related papers (2023-12-28T14:52:07Z) - NeRF-Det: Learning Geometry-Aware Volumetric Representation for
Multi-View 3D Object Detection [65.02633277884911]
We present NeRF-Det, a novel method for indoor 3D detection with posed RGB images as input.
Our method makes use of NeRF in an end-to-end manner to explicitly estimate 3D geometry, thereby improving 3D detection performance.
arXiv Detail & Related papers (2023-07-27T04:36:16Z) - On the Importance of Accurate Geometry Data for Dense 3D Vision Tasks [61.74608497496841]
Training on inaccurate or corrupt data induces model bias and hampers generalisation capabilities.
This paper investigates the effect of sensor errors for the dense 3D vision tasks of depth estimation and reconstruction.
arXiv Detail & Related papers (2023-03-26T22:32:44Z) - AGO-Net: Association-Guided 3D Point Cloud Object Detection Network [86.10213302724085]
We propose a novel 3D detection framework that associates intact features for objects via domain adaptation.
We achieve new state-of-the-art performance on the KITTI 3D detection benchmark in both accuracy and speed.
arXiv Detail & Related papers (2022-08-24T16:54:38Z) - Shape Prior Non-Uniform Sampling Guided Real-time Stereo 3D Object
Detection [59.765645791588454]
Recently introduced RTS3D builds an efficient 4D Feature-Consistency Embedding space for the intermediate representation of object without depth supervision.
We propose a shape prior non-uniform sampling strategy that performs dense sampling in outer region and sparse sampling in inner region.
Our proposed method has 2.57% improvement on AP3d almost without extra network parameters.
arXiv Detail & Related papers (2021-06-18T09:14:55Z) - SESS: Self-Ensembling Semi-Supervised 3D Object Detection [138.80825169240302]
We propose SESS, a self-ensembling semi-supervised 3D object detection framework. Specifically, we design a thorough perturbation scheme to enhance generalization of the network on unlabeled and new unseen data.
Our SESS achieves competitive performance compared to the state-of-the-art fully-supervised method by using only 50% labeled data.
arXiv Detail & Related papers (2019-12-26T08:48:04Z)
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.