用少量参数动态调整3D模型，让稀疏深度图变完整。
Depth Completion as Parameter-Efficient Test-Time Adaptation
- 仅更新极少量参数，利用推理时的稀疏数据实时优化模型。
- 在室内外数据集上均达到当前最佳效果，尤其对不规则缺失场景有效。
- 适合需要快速适配新场景的自动驾驶与机器人视觉任务。
我们提出CAPA，一种参数高效的测试时优化框架，用于将预训练的3D基础模型（FMs）适配到深度补全任务中，仅依赖稀疏几何线索。与以往需为辅助输入训练专用编码器的方法不同，CAPA冻结了基础模型主干，仅通过参数高效微调（如LoRA或VPT）更新极少量参数，并利用推理时可获得的稀疏观测直接计算梯度。该方法有效将基础模型的几何先验与具体场景测量对齐，修正畸变和错位结构。针对视频序列，CAPA引入帧间参数共享机制，联合优化所有帧以利用时间相关性、提升鲁棒性并保证多帧一致性。CAPA具有模型无关性，兼容任意基于ViT的基础模型，在室内与室外数据集上对多种条件模式均取得当前最优性能。项目页面：research.nvidia.com/labs/dvl/projects/capa。
原文摘要 · Abstract (English)
We introduce CAPA, a parameter-efficient test-time optimization framework that adapts pre-trained 3D foundation models (FMs) for depth completion, using sparse geometric cues. Unlike prior methods that train task-specific encoders for auxiliary inputs, which often overfit and generalize poorly, CAPA freezes the FM backbone. Instead, it updates only a minimal set of parameters using Parameter-Efficient Fine-Tuning (e.g. LoRA or VPT), guided by gradients calculated directly from the sparse observations available at inference time. This approach effectively grounds the foundation model's geometric prior in the scene-specific measurements, correcting distortions and misplaced structures. For videos, CAPA introduces sequence-level parameter sharing, jointly adapting all frames to exploit temporal correlations, improve robustness, and enforce multi-frame consistency. CAPA is model-agnostic, compatible with any ViT-based FM, and achieves state-of-the-art results across diverse condition patterns on both indoor and outdoor datasets. Project page: research.nvidia.com/labs/dvl/projects/capa.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。