# Scalable Adaptation of 3D Geometric Foundation Models via Weak Supervision from Internet Video

arXiv: https://arxiv.org/abs/2602.07891 · HTML: https://mlsanity.com/paper/2602.07891/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 39 references that are in the map.
- First posted on arXiv 8 Feb 2026.

## Builds on (most cited first, 24 of 24)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [MVSNet: Depth Inference for Unstructured Multi-view Stereo](https://mlsanity.com/paper/1804.02505/) (2018)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction](https://mlsanity.com/paper/2312.12337/) (2023)
- [MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images](https://mlsanity.com/paper/2403.14627/) (2024)
- [Continuous 3D Perception Model with Persistent State](https://mlsanity.com/paper/2501.12387/) (2025)
- [DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision](https://mlsanity.com/paper/2312.16256/) (2023)
- [Habitat 2.0: Training Home Assistants to Rearrange their Habitat](https://mlsanity.com/paper/2106.14405/) (2021)
- [Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass](https://mlsanity.com/paper/2501.13928/) (2025)
- [DepthSplat: Connecting Gaussian Splatting and Depth](https://mlsanity.com/paper/2410.13862/) (2024)
- [3D Reconstruction with Spatial Memory](https://mlsanity.com/paper/2408.16061/) (2024)
- [Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video](https://mlsanity.com/paper/1908.10553/) (2019)
- [Visual Geometry Grounded Deep Structure From Motion](https://mlsanity.com/paper/2312.04563/) (2023)
- [Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs](https://mlsanity.com/paper/2408.13912/) (2024)
- [CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion](https://mlsanity.com/paper/2210.10716/) (2022)
- [MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds](https://mlsanity.com/paper/2412.06974/) (2024)
- [latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction](https://mlsanity.com/paper/2403.16292/) (2024)
- [MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views](https://mlsanity.com/paper/2411.04924/) (2024)
- [Depth Any Video with Scalable Synthetic Data](https://mlsanity.com/paper/2410.10815/) (2024)

## Abstract (arXiv)

Geometric foundation models show promise in 3D reconstruction, yet their progress is severely constrained by the scarcity of diverse, large-scale 3D annotations. While Internet videos offer virtually unlimited raw data, utilizing them as a scaling source for geometric learning is challenging due to the absence of ground-truth geometry and the presence of observational noise. To address this, we propose SAGE, a framework for Scalable Adaptation of GEometric foundation models from raw video streams. SAGE leverages a hierarchical mining pipeline to transform videos into training trajectories and hybrid supervision: (1) Informative training trajectory selection; (2) Sparse Geometric Anchoring via SfM point clouds for global structural guidance; and (3) Dense Differentiable Consistency via 3D Gaussian rendering for multi-view constraints. To prevent catastrophic forgetting, we introduce a regularization strategy using anchor data. Extensive experiments show that SAGE significantly enhances zero-shot generalization, reducing Chamfer Distance by 20-42% on unseen benchmarks (7Scenes, TUM-RGBD, Matterport3D) compared to state-of-the-art baselines. To our knowledge, SAGE pioneers the adaptation of geometric foundation models via Internet video, establishing a scalable paradigm for general-purpose 3D learning.