DC-Scene: Data-Centric Learning for 3D Scene Understanding

• URL: http://arxiv.org/abs/2505.15232v1
• Date: Wed, 21 May 2025 08:05:27 GMT
• Title: DC-Scene: Data-Centric Learning for 3D Scene Understanding
• Authors: Ting Huang, Zeyu Zhang, Ruicheng Zhang, Yang Zhao,
• Abstract summary: 3D scene understanding plays a fundamental role in vision applications such as robotics, autonomous driving, and augmented reality.<n>We propose DC-Scene, a data-centric framework tailored for 3D scene understanding.<n>We introduce a CLIP-driven dual-indicator quality (DIQ) filter, combining vision-language alignment scores with caption-loss perplexity, along with a curriculum scheduler.
• Score: 11.204526527127094
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 3D scene understanding plays a fundamental role in vision applications such as robotics, autonomous driving, and augmented reality. However, advancing learning-based 3D scene understanding remains challenging due to two key limitations: (1) the large scale and complexity of 3D scenes lead to higher computational costs and slower training compared to 2D counterparts; and (2) high-quality annotated 3D datasets are significantly scarcer than those available for 2D vision. These challenges underscore the need for more efficient learning paradigms. In this work, we propose DC-Scene, a data-centric framework tailored for 3D scene understanding, which emphasizes enhancing data quality and training efficiency. Specifically, we introduce a CLIP-driven dual-indicator quality (DIQ) filter, combining vision-language alignment scores with caption-loss perplexity, along with a curriculum scheduler that progressively expands the training pool from the top 25% to 75% of scene-caption pairs. This strategy filters out noisy samples and significantly reduces dependence on large-scale labeled 3D data. Extensive experiments on ScanRefer and Nr3D demonstrate that DC-Scene achieves state-of-the-art performance (86.1 CIDEr with the top-75% subset vs. 85.4 with the full dataset) while reducing training cost by approximately two-thirds, confirming that a compact set of high-quality samples can outperform exhaustive training. Code will be available at https://github.com/AIGeeksGroup/DC-Scene.

Related papers

• 3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding [11.069512983766783]
  Large vision-language models (VLMs) have made significant strides in 2D visual understanding tasks.<n>We propose 3D-R1, a foundation model that enhances the reasoning capabilities of 3D VLMs.<n>Extensive experiments demonstrate that 3D-R1 delivers an average improvement of 10% across various 3D scene benchmarks.
  arXiv  Detail & Related papers  (2025-07-31T11:59:06Z)
• SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language Pretraining [100.23919762298227]
  We introduce SceneSplat, the first large-scale 3D indoor scene understanding approach that operates on 3DGS.<n>We also propose a self-supervised learning scheme that unlocks rich 3D feature learning from unlabeled scenes.<n>SceneSplat-7K is the first large-scale 3DGS dataset for indoor scenes, comprising of 6868 scenes.
  arXiv  Detail & Related papers  (2025-03-23T12:50:25Z)
• Semi-supervised 3D Semantic Scene Completion with 2D Vision Foundation Model Guidance [8.07701188057789]
  We introduce a novel semi-supervised framework to alleviate the dependency on densely annotated data.<n>Our approach leverages 2D foundation models to generate essential 3D scene geometric and semantic cues.<n>Our method achieves up to 85% of the fully-supervised performance using only 10% labeled data.
  arXiv  Detail & Related papers  (2024-08-21T12:13:18Z)
• P3P: Pseudo-3D Pre-training for Scaling 3D Voxel-based Masked Autoencoders [34.64343313442465]
  We introduce a novel self-supervised pre-training framework that incorporates millions of images into 3D pre-training corpora.<n>Our method achieves state-of-the-art performance in 3D classification, few-shot learning, and 3D segmentation.
  arXiv  Detail & Related papers  (2024-08-19T13:59:53Z)
• Implicit-Zoo: A Large-Scale Dataset of Neural Implicit Functions for 2D Images and 3D Scenes [65.22070581594426]
  "Implicit-Zoo" is a large-scale dataset requiring thousands of GPU training days to facilitate research and development in this field. We showcase two immediate benefits as it enables to: (1) learn token locations for transformer models; (2) directly regress 3D cameras poses of 2D images with respect to NeRF models. This in turn leads to an improved performance in all three task of image classification, semantic segmentation, and 3D pose regression, thereby unlocking new avenues for research.
  arXiv  Detail & Related papers  (2024-06-25T10:20:44Z)
• Enhancing Generalizability of Representation Learning for Data-Efficient 3D Scene Understanding [50.448520056844885]
  We propose a generative Bayesian network to produce diverse synthetic scenes with real-world patterns. A series of experiments robustly display our method's consistent superiority over existing state-of-the-art pre-training approaches.
  arXiv  Detail & Related papers  (2024-06-17T07:43:53Z)
• Cross-Modal Self-Training: Aligning Images and Pointclouds to Learn Classification without Labels [69.55622471172941]
  Large-scale vision 2D vision language models, such as CLIP can be aligned with a 3D encoder to learn generalizable (open-vocabulary) 3D vision models. We propose an optimization framework: Cross-MoST: Cross-Modal Self-Training, to improve the label-free classification performance of a zero-shot 3D vision model.
  arXiv  Detail & Related papers  (2024-04-15T21:30:50Z)
• ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding [96.95120198412395]
  We introduce tri-modal pre-training framework that automatically generates holistic language descriptions for 3D shapes. It only needs 3D data as input, eliminating the need for any manual 3D annotations, and is therefore scalable to large datasets. We conduct experiments on two large-scale 3D datasets, NN and ShapeNet, and augment them with tri-modal datasets of 3D point clouds, captioning, and language for training. Experiments show that NN-2 demonstrates substantial benefits in three downstream tasks: zero-shot 3D classification, standard 3D classification with finetuning, and 3D (3D
  arXiv  Detail & Related papers  (2023-05-14T23:14:09Z)
• Data Augmented 3D Semantic Scene Completion with 2D Segmentation Priors [1.0973642726108543]
  We present SPAwN, a novel lightweight multimodal 3D deep CNN. A crucial difficulty in this field is the lack of fully labeled real-world 3D datasets. We introduce the use of a 3D data augmentation strategy that can be applied to multimodal SSC networks.
  arXiv  Detail & Related papers  (2021-11-26T04:08:34Z)
• PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding [107.02479689909164]
  In this work, we aim at facilitating research on 3D representation learning. We measure the effect of unsupervised pre-training on a large source set of 3D scenes.
  arXiv  Detail & Related papers  (2020-07-21T17:59:22Z)
• 2.75D: Boosting learning by representing 3D Medical imaging to 2D features for small data [54.223614679807994]
  3D convolutional neural networks (CNNs) have started to show superior performance to 2D CNNs in numerous deep learning tasks. Applying transfer learning on 3D CNN is challenging due to a lack of publicly available pre-trained 3D models. In this work, we proposed a novel 2D strategical representation of volumetric data, namely 2.75D. As a result, 2D CNN networks can also be used to learn volumetric information.
  arXiv  Detail & Related papers  (2020-02-11T08:24:19Z)

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.