# YouTube-Occ: Learning Indoor 3D Semantic Occupancy Prediction from YouTube Videos

arXiv: https://arxiv.org/abs/2506.18266 · HTML: https://mlsanity.com/paper/2506.18266/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 61 of its 71 references that are in the map.
- First posted on arXiv 23 Jun 2025.

## Builds on (most cited first, 30 of 61)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View](https://mlsanity.com/paper/2112.11790/) (2021)
- [LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action](https://mlsanity.com/paper/2207.04429/) (2022)
- [Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2302.07817/) (2023)
- [MonoScene: Monocular 3D Semantic Scene Completion](https://mlsanity.com/paper/2112.00726/) (2021)
- [SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving](https://mlsanity.com/paper/2303.09551/) (2023)
- [VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion](https://mlsanity.com/paper/2302.12251/) (2023)
- [BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision](https://mlsanity.com/paper/2211.10439/) (2022)
- [Side Adapter Network for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2302.12242/) (2023)
- [OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2304.05316/) (2023)
- [OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving](https://mlsanity.com/paper/2311.16038/) (2023)
- [CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding](https://mlsanity.com/paper/2203.00680/) (2022)
- [LMSCNet: Lightweight Multiscale 3D Semantic Completion](https://mlsanity.com/paper/2008.10559/) (2020)
- [FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformation](https://mlsanity.com/paper/2307.01492/) (2023)
- [GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2405.17429/) (2024)
- [Scan2CAD: Learning CAD Model Alignment in RGB-D Scans](https://mlsanity.com/paper/1811.11187/) (2018)
- [SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction](https://mlsanity.com/paper/2311.12754/) (2023)
- [Anisotropic Convolutional Networks for 3D Semantic Scene Completion](https://mlsanity.com/paper/2004.02122/) (2020)
- [3D Sketch-aware Semantic Scene Completion via Semi-supervised Structure Prior](https://mlsanity.com/paper/2003.14052/) (2020)
- [Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Data](https://mlsanity.com/paper/2203.16258/) (2022)

## Built on by (most cited first, 1 of 1)

- [Human Motion Synthesis in 3D Scenes via Unified Scene Semantic Occupancy](https://mlsanity.com/paper/2511.07819/) (2025)

## Abstract (arXiv)

3D semantic occupancy prediction is crucial for fine-grained scene understanding, yet its advancement in privacy-sensitive indoor environments is fundamentally hindered by the scarcity of large-scale annotated 3D data. To overcome this limitation, we explore learning indoor 3D semantic occupancy prediction from abundant, uncalibrated in-the-wild internet videos while simultaneously bypassing the extensive manual annotation. Specifically, we introduce textitYouTube-Occ, including an automated data pipeline that leverages 2D and 3D foundation models to process raw web videos, estimating camera geometry, reconstructing scene point clouds, and enriching them with dense semantic pseudo-labels. However, these plausible pseudo-labels fail to yield performance gains under naive supervision. To address this impasse, we further propose a pre-training framework driven by feature distillation with a dual-alignment strategy. Within it, an intra-frame alignment utilizes a voxel-anchored Gaussianization module to align 3D features with corresponding 2D priors, whereas a cross-scene alignment achieves global semantic consistency via class-prototype distillation. Empirically, YouTube-Occ delivers consistent gains across three mainstream architectures on the NYUv2 and Occ-ScanNet benchmarks, especially under limited-data conditions. We will publicly release our code and data, hoping to inspire future research.