Distill3R: A Pipeline for Democratizing 3D Foundation Models on Commodity Hardware

arXiv:2602.00865 · cs.CV · Submitted 2026-01-31 · Read on arXiv

cs.CV

Submitted: 2026-01-31

Updated: 2026-10-13

Comments: Published in the Canadian Conference on Robotics and Vision (CRV)

Journal ref: Proceedings of the 23rd Conference on Robots and Vision, 2026

DOI: 10.21428/d82e957c.68efb4ef

Code: https://github.com/TheFourthKaramazov/Distill3R

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Foundation Model — 4× in this paper · explained in 3 episodes
• Foundation Models — 4× in this paper · explained in 7 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Edge Deployment — 1× in this paper · explained in 2 episodes

Sources

• Language Models are Few-Shot Learners
• DINOv3
• GPT-4 Technical Report
• Scaling Laws for Neural Language Models
• Training Compute-Optimal Large Language Models
• $\pi^3$: Permutation-Equivariant Visual Geometry Learning
• AVGGT: Rethinking Global Attention for Accelerating VGGT
• Block-Sparse Global Attention for Efficient Multi-View Geometry Transformers
• FastVGGT: Training-Free Acceleration of Visual Geometry Transformer
• Quantized Visual Geometry Grounded Transformer
• Distilling the Knowledge in a Neural Network
• BA-Net: Dense Bundle Adjustment Network
• DeepV2D: Video to Depth with Differentiable Structure from Motion
• Depth Anything V2
• Understanding Multi-View Transformers

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models