# DC-Scene: Data-Centric Learning for 3D Scene Understanding arXiv: https://arxiv.org/abs/2505.15232 ยท HTML: https://mlsanity.com/paper/2505.15232/ ## Key facts - Cited by 15 papers in the map (data through 14 Oct 2026). - Builds on 26 of its 40 references that are in the map. - First posted on arXiv 21 May 2025. ## Builds on (most cited first, 26 of 26) - [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017) - [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014) - [ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language](https://mlsanity.com/paper/1912.08830/) (2019) - [ScanQA: 3D Question Answering for Spatial Scene Understanding](https://mlsanity.com/paper/2112.10482/) (2021) - [SQA3D: Situated Question Answering in 3D Scenes](https://mlsanity.com/paper/2210.07474/) (2022) - [Curriculum Learning: A Survey](https://mlsanity.com/paper/2101.10382/) (2021) - [Scan2Cap: Context-aware Dense Captioning in RGB-D Scans](https://mlsanity.com/paper/2012.02206/) (2020) - [SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding](https://mlsanity.com/paper/2401.09340/) (2024) - [End-to-End 3D Dense Captioning with Vote2Cap-DETR](https://mlsanity.com/paper/2301.02508/) (2023) - [D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding](https://mlsanity.com/paper/2112.01551/) (2021) - [MORE: Multi-Order RElation Mining for Dense Captioning in 3D Scenes](https://mlsanity.com/paper/2203.05203/) (2022) - [SportsCap: Monocular 3D Human Motion Capture and Fine-grained Understanding in Challenging Sports Videos](https://mlsanity.com/paper/2104.11452/) (2021) - [Spatiality-guided Transformer for 3D Dense Captioning on Point Clouds](https://mlsanity.com/paper/2204.10688/) (2022) - [TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes](https://mlsanity.com/paper/2403.19589/) (2024) - [Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning](https://mlsanity.com/paper/2309.02999/) (2023) - [View Selection for 3D Captioning via Diffusion Ranking](https://mlsanity.com/paper/2404.07984/) (2024) - [TightCap: 3D Human Shape Capture with Clothing Tightness Field](https://mlsanity.com/paper/1904.02601/) (2019) - [Open Vocabulary 3D Scene Understanding via Geometry Guided Self-Distillation](https://mlsanity.com/paper/2407.13362/) (2024) - [Dense Multimodal Alignment for Open-Vocabulary 3D Scene Understanding](https://mlsanity.com/paper/2407.09781/) (2024) - [Point Cloud Instance Segmentation with Semi-supervised Bounding-Box Mining](https://mlsanity.com/paper/2111.15210/) (2021) - [MSDet: Receptive Field Enhanced Multiscale Detection for Tiny Pulmonary Nodule](https://mlsanity.com/paper/2409.14028/) (2024) - [3D CoCa: Contrastive Learners are 3D Captioners](https://mlsanity.com/paper/2504.09518/) (2025) - [Curricular Object Manipulation in LiDAR-based Object Detection](https://mlsanity.com/paper/2304.04248/) (2023) - [Duoduo CLIP: Efficient 3D Understanding with Multi-View Images](https://mlsanity.com/paper/2406.11579/) (2024) - [MedDet: Generative Adversarial Distillation for Efficient Cervical Disc Herniation Detection](https://mlsanity.com/paper/2409.00204/) (2024) - [PedDet: Adaptive Spectral Optimization for Multimodal Pedestrian Detection](https://mlsanity.com/paper/2502.14063/) (2025) ## Built on by (most cited first, 15 of 15) - [3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding](https://mlsanity.com/paper/2507.23478/) (2025) - [VLA-R1: Enhancing Reasoning in Vision-Language-Action Models](https://mlsanity.com/paper/2510.01623/) (2025) - [MobileVLA-R1: Reinforcing Vision-Language-Action for Mobile Robots](https://mlsanity.com/paper/2511.17889/) (2025) - [EvoVLA: Self-Evolving Vision-Language-Action Model](https://mlsanity.com/paper/2511.16166/) (2025) - [StereoAdapter: Adapting Stereo Depth Estimation to Underwater Scenes](https://mlsanity.com/paper/2509.16415/) (2025) - [CoV: Chain-of-View Prompting for Spatial Reasoning](https://mlsanity.com/paper/2601.05172/) (2026) - [EgoLCD: Egocentric Video Generation with Long Context Diffusion](https://mlsanity.com/paper/2512.04515/) (2025) - [AnyDepth: Depth Estimation Made Easy](https://mlsanity.com/paper/2601.02760/) (2026) - [VaseVQA-3D: Benchmarking 3D VLMs on Ancient Greek Pottery](https://mlsanity.com/paper/2510.04479/) (2025) - [3D CoCa v2: Contrastive Learners with Test-Time Search for Generalizable Spatial Intelligence](https://mlsanity.com/paper/2601.06496/) (2026) - [UniMesh: Unifying 3D Mesh Understanding and Generation](https://mlsanity.com/paper/2604.17472/) (2026) - [PhysEditWorld: A Large-Scale Dataset Toward Physics-Editable World Models](https://mlsanity.com/paper/2606.26694/) (2026) - [RPD-Diff: Region-Adaptive Physics-Guided Diffusion Model for Visibility Enhancement under Dense and Non-Uniform Haze](https://mlsanity.com/paper/2508.16956/) (2025) - [ConsiSpace: Learning Geometric Consistency Matters for Video Spatial Reasoning](https://mlsanity.com/paper/2607.17599/) (2026) - [MobileVLA-R1 2.0: RL-Enhanced Reasoning for Mobile Robot Control](https://mlsanity.com/paper/2609.06251/) (2026) ## Abstract (arXiv) 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.