Cues3D: Unleashing the Power of Sole NeRF for Consistent and Unique Instances in Open-Vocabulary 3D Panoptic Segmentation

• URL: http://arxiv.org/abs/2505.00378v1
• Date: Thu, 01 May 2025 08:12:03 GMT
• Title: Cues3D: Unleashing the Power of Sole NeRF for Consistent and Unique Instances in Open-Vocabulary 3D Panoptic Segmentation
• Authors: Feng Xue, Wenzhuang Xu, Guofeng Zhong, Anlong Minga, Nicu Sebe,
• Abstract summary: Open-vocabulary 3D panoptic segmentation has recently emerged as a significant trend.<n>We present Cues3D, a compact approach that relies solely on Neural Radiance Field (NeRF) instead of pre-associations.<n>Our experiments are conducted on ScanNet v2, ScanNet200, ScanNet++, and Replica datasets for 3D instance, panoptic, and semantic segmentation tasks.
• Score: 48.231573110948
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Open-vocabulary 3D panoptic segmentation has recently emerged as a significant trend. Top-performing methods currently integrate 2D segmentation with geometry-aware 3D primitives. However, the advantage would be lost without high-fidelity 3D point clouds, such as methods based on Neural Radiance Field (NeRF). These methods are limited by the insufficient capacity to maintain consistency across partial observations. To address this, recent works have utilized contrastive loss or cross-view association pre-processing for view consensus. In contrast to them, we present Cues3D, a compact approach that relies solely on NeRF instead of pre-associations. The core idea is that NeRF's implicit 3D field inherently establishes a globally consistent geometry, enabling effective object distinction without explicit cross-view supervision. We propose a three-phase training framework for NeRF, initialization-disambiguation-refinement, whereby the instance IDs are corrected using the initially-learned knowledge. Additionally, an instance disambiguation method is proposed to match NeRF-rendered 3D masks and ensure globally unique 3D instance identities. With the aid of Cues3D, we obtain highly consistent and unique 3D instance ID for each object across views with a balanced version of NeRF. Our experiments are conducted on ScanNet v2, ScanNet200, ScanNet++, and Replica datasets for 3D instance, panoptic, and semantic segmentation tasks. Cues3D outperforms other 2D image-based methods and competes with the latest 2D-3D merging based methods, while even surpassing them when using additional 3D point clouds. The code link could be found in the appendix and will be released on \href{https://github.com/mRobotit/Cues3D}{github}

Related papers

• NeuraLoc: Visual Localization in Neural Implicit Map with Dual Complementary Features [50.212836834889146]
  We propose an efficient and novel visual localization approach based on the neural implicit map with complementary features. Specifically, to enforce geometric constraints and reduce storage requirements, we implicitly learn a 3D keypoint descriptor field. To further address the semantic ambiguity of descriptors, we introduce additional semantic contextual feature fields.
  arXiv  Detail & Related papers  (2025-03-08T08:04:27Z)
• DCSEG: Decoupled 3D Open-Set Segmentation using Gaussian Splatting [0.0]
  We present a decoupled 3D segmentation pipeline to ensure modularity and adaptability to novel 3D representations.<n>We evaluate on synthetic and real-world indoor datasets, demonstrating improved performance over comparable NeRF-based pipelines.
  arXiv  Detail & Related papers  (2024-12-14T21:26:44Z)
• OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary Understanding [54.981605111365056]
  This paper introduces OpenGaussian, a method based on 3D Gaussian Splatting (3DGS) capable of 3D point-level open vocabulary understanding.<n>Our primary motivation stems from observing that existing 3DGS-based open vocabulary methods mainly focus on 2D pixel-level parsing.
  arXiv  Detail & Related papers  (2024-06-04T07:42:33Z)
• Free3D: Consistent Novel View Synthesis without 3D Representation [63.931920010054064]
  Free3D is a simple accurate method for monocular open-set novel view synthesis (NVS) Compared to other works that took a similar approach, we obtain significant improvements without resorting to an explicit 3D representation.
  arXiv  Detail & Related papers  (2023-12-07T18:59:18Z)
• Points-to-3D: Bridging the Gap between Sparse Points and Shape-Controllable Text-to-3D Generation [16.232803881159022]
  We propose a flexible framework of Points-to-3D to bridge the gap between sparse yet freely available 3D points and realistic shape-controllable 3D generation. The core idea of Points-to-3D is to introduce controllable sparse 3D points to guide the text-to-3D generation.
  arXiv  Detail & Related papers  (2023-07-26T02:16:55Z)
• Asymmetric 3D Context Fusion for Universal Lesion Detection [55.61873234187917]
  3D networks are strong in 3D context yet lack supervised pretraining. Existing 3D context fusion operators are designed to be spatially symmetric, performing identical operations on each 2D slice like convolutions. We propose a novel asymmetric 3D context fusion operator (A3D), which uses different weights to fuse 3D context from different 2D slices.
  arXiv  Detail & Related papers  (2021-09-17T16:25:10Z)
• Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perception [122.53774221136193]
  State-of-the-art methods for driving-scene LiDAR-based perception often project the point clouds to 2D space and then process them via 2D convolution. A natural remedy is to utilize the 3D voxelization and 3D convolution network. We propose a new framework for the outdoor LiDAR segmentation, where cylindrical partition and asymmetrical 3D convolution networks are designed to explore the 3D geometric pattern.
  arXiv  Detail & Related papers  (2021-09-12T06:25:11Z)
• Multi-Modality Task Cascade for 3D Object Detection [22.131228757850373]
  Many methods train two models in isolation and use simple feature concatenation to represent 3D sensor data. We propose a novel Multi-Modality Task Cascade network (MTC-RCNN) that leverages 3D box proposals to improve 2D segmentation predictions. We show that including a 2D network between two stages of 3D modules significantly improves both 2D and 3D task performance.
  arXiv  Detail & Related papers  (2021-07-08T17:55:01Z)

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.