只优化解码器的低秩子空间，实现快速零样本深度补全
Efficient Test-Time Optimization for Depth Completion via Low-Rank Decoder Adaptation
- 仅更新解码器中的低秩子空间，减少计算开销
- 在五个数据集上达到新最优性能，精度与效率双赢
- 适合需要快速部署的自动驾驶等实时场景
零样本深度补全因其无需特定传感器数据集或重训练即可跨环境泛化而受到关注。然而，现有方法多依赖基于扩散模型的测试时优化，因迭代去噪导致计算成本高昂。近期视觉提示方法虽降低训练成本，但仍需对完整冻结网络进行多次前向-反向传播以优化输入级提示，造成推理缓慢。本文发现，深度基础模型中深度相关的信息集中于低维解码器子空间，仅适配该子空间即可实现有效测试时优化。基于此，我们提出一种轻量级测试时适应方法，仅通过稀疏深度监督更新这一低维子空间。实验在五个室内与室外数据集上验证了该方法的优越性，建立了精度与效率的新帕累托前沿，显著提升了零样本深度补全的实际应用价值。
原文摘要 · Abstract (English)
Zero-shot depth completion has gained attention for its ability to generalize across environments without sensor-specific datasets or retraining. However, most existing approaches rely on diffusion-based test-time optimization, which is computationally expensive due to iterative denoising. Recent visual-prompt-based methods reduce training cost but still require repeated forward--backward passes through the full frozen network to optimize input-level prompts, resulting in slow inference. In this work, we show that adapting only the decoder is sufficient for effective test-time optimization, as depth foundation models concentrate depth-relevant information within a low-dimensional decoder subspace. Based on this insight, we propose a lightweight test-time adaptation method that updates only this low-dimensional subspace using sparse depth supervision. Our approach achieves state-of-the-art performance, establishing a new Pareto frontier between accuracy and efficiency for test-time adaptation. Extensive experiments on five indoor and outdoor datasets demonstrate consistent improvements over prior methods, highlighting the practicality of fast zero-shot depth completion.
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。