基于几何蒸馏的3D感知视觉语言模型微调
3D-Aware Vision-Language Models Fine-Tuning with Geometric Distillation
AI总结：
针对现有视觉语言模型3D空间理解能力不足的问题，提出无需标注的轻量几何蒸馏微调框架，从3D基础模型蒸馏三类几何信息增强模型表征，以更低计算成本实现更优的3D推理性能。
摘要：
视觉语言模型（VLMs）在各类视觉与语言任务上表现出色，但本质上仍存在3D空间结构理解能力不足的局限。本文提出Geometric Distillation（几何蒸馏），这是一种轻量、无需标注的微调框架，可在不改动预训练VLM架构的前提下，将受人类感知启发的几何线索注入模型。该方法通过从现成3D基础模型（如MASt3R、VGGT）中蒸馏三类信息：(1)稀疏对应关系、(2)相对深度关系、(3)稠密代价体，让模型表征具备几何感知能力，同时保持对自然图文输入的兼容性。在3D视觉语言推理与3D感知基准上的大量评测显示，该方法性能持续优于现有方案，能以更低的计算成本提升3D空间推理能力。本研究为弥合2D训练的VLM与3D理解之间的鸿沟提供了可扩展的高效路径，可拓展空间接地多模态任务的应用场景。
英文摘要：
Vision-Language Models (VLMs) have shown remarkable performance on diverse visual and linguistic tasks, yet they remain fundamentally limited in their understanding of 3D spatial structures. We propose Geometric Distillation, a lightweight, annotation-free fine-tuning framework that injects human-inspired geometric cues into pretrained VLMs without modifying their architecture. By distilling (1) sparse correspondences, (2) relative depth relations, and (3) dense cost volumes from off-the-shelf 3D foundation models (e.g., MASt3R, VGGT), our method shapes representations to be geometry-aware while remaining compatible with natural image-text inputs. Through extensive evaluations on 3D vision-language reasoning and 3D perception benchmarks, our method consistently outperforms prior approaches, achieving improved 3D spatial reasoning with significantly lower computational cost. Our work demonstrates a scalable and efficient path to bridge 2D-trained VLMs with 3D understanding, opening up wider use in spatially grounded multimodal tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
