PanopticNeRF-360: Panoramic 3D-to-2D Label Transfer in Urban Scenes

• URL: http://arxiv.org/abs/2309.10815v2
• Date: Tue, 03 Dec 2024 21:21:58 GMT
• Title: PanopticNeRF-360: Panoramic 3D-to-2D Label Transfer in Urban Scenes
• Authors: Xiao Fu, Tianrun Chen, Yichong Lu, Xiaowei Zhou, Andreas Geiger, Yiyi Liao,
• Abstract summary: We present PanopticNeRF-360, a novel approach that combines coarse 3D annotations with noisy 2D semantic cues to generate high-quality panoptic labels. Our experiments demonstrate PanopticNeRF-360's state-of-the-art performance over label transfer methods on the KITTI-360 dataset.
• Score: 54.49897326605168
• License:
• Abstract: Training perception systems for self-driving cars requires substantial 2D annotations that are labor-intensive to manual label. While existing datasets provide rich annotations on pre-recorded sequences, they fall short in labeling rarely encountered viewpoints, potentially hampering the generalization ability for perception models. In this paper, we present PanopticNeRF-360, a novel approach that combines coarse 3D annotations with noisy 2D semantic cues to generate high-quality panoptic labels and images from any viewpoint. Our key insight lies in exploiting the complementarity of 3D and 2D priors to mutually enhance geometry and semantics. Specifically, we propose to leverage coarse 3D bounding primitives and noisy 2D semantic and instance predictions to guide geometry optimization, by encouraging predicted labels to match panoptic pseudo ground truth. Simultaneously, the improved geometry assists in filtering 3D&2D annotation noise by fusing semantics in 3D space via a learned semantic field. To further enhance appearance, we combine MLP and hash grids to yield hybrid scene features, striking a balance between high-frequency appearance and contiguous semantics. Our experiments demonstrate PanopticNeRF-360's state-of-the-art performance over label transfer methods on the challenging urban scenes of the KITTI-360 dataset. Moreover, PanopticNeRF-360 enables omnidirectional rendering of high-fidelity, multi-view and spatiotemporally consistent appearance, semantic and instance labels. We make our code and data available at https://github.com/fuxiao0719/PanopticNeRF

Related papers

• LeAP: Consistent multi-domain 3D labeling using Foundation Models [0.7919810878571297]
  This work introduces Label Any Pointcloud (LeAP), leveraging 2D VFMs to automatically label 3D data with any set of classes in any kind of application. We show that our method can generate high-quality 3D semantic labels across diverse fields without any manual labeling.
  arXiv  Detail & Related papers  (2025-02-06T09:24:47Z)
• Bootstraping Clustering of Gaussians for View-consistent 3D Scene Understanding [59.51535163599723]
  FreeGS is an unsupervised semantic-embedded 3DGS framework that achieves view-consistent 3D scene understanding without the need for 2D labels. We show that FreeGS performs comparably to state-of-the-art methods while avoiding the complex data preprocessing workload.
  arXiv  Detail & Related papers  (2024-11-29T08:52:32Z)
• HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting [53.6394928681237]
  holistic understanding of urban scenes based on RGB images is a challenging yet important problem. Our main idea involves the joint optimization of geometry, appearance, semantics, and motion using a combination of static and dynamic 3D Gaussians. Our approach offers the ability to render new viewpoints in real-time, yielding 2D and 3D semantic information with high accuracy.
  arXiv  Detail & Related papers  (2024-03-19T13:39:05Z)
• DatasetNeRF: Efficient 3D-aware Data Factory with Generative Radiance Fields [68.94868475824575]
  This paper introduces a novel approach capable of generating infinite, high-quality 3D-consistent 2D annotations alongside 3D point cloud segmentations. We leverage the strong semantic prior within a 3D generative model to train a semantic decoder. Once trained, the decoder efficiently generalizes across the latent space, enabling the generation of infinite data.
  arXiv  Detail & Related papers  (2023-11-18T21:58:28Z)
• RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervision [36.15913507034939]
  We present RenderOcc, a novel paradigm for training 3D occupancy models only using 2D labels. Specifically, we extract a NeRF-style 3D volume representation from multi-view images. We employ volume rendering techniques to establish 2D renderings, thus enabling direct 3D supervision from 2D semantics and depth labels.
  arXiv  Detail & Related papers  (2023-09-18T06:08:15Z)
• SSR-2D: Semantic 3D Scene Reconstruction from 2D Images [54.46126685716471]
  In this work, we explore a central 3D scene modeling task, namely, semantic scene reconstruction without using any 3D annotations. The key idea of our approach is to design a trainable model that employs both incomplete 3D reconstructions and their corresponding source RGB-D images. Our method achieves the state-of-the-art performance of semantic scene completion on two large-scale benchmark datasets MatterPort3D and ScanNet.
  arXiv  Detail & Related papers  (2023-02-07T17:47:52Z)
• Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation [48.677336052620895]
  We present a novel 3D-to-2D label transfer method, Panoptic NeRF, which aims for obtaining per-pixel 2D semantic and instance labels. By inferring in 3D space and rendering to 2D labels, our 2D semantic and instance labels are multi-view consistent by design.
  arXiv  Detail & Related papers  (2022-03-29T04:16:40Z)

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.