用生成模型合成伪图像，让深度补全无需真实照片也能精准推断语义。
Depth-to-Image Synthesis-Driven Generative Unguided Depth Completion
- 通过控制网络从稀疏深度图生成伪图像，实现无真实图像的语义引导补全。
- 在KITTI和NYUv2上优于现有方法，深度补全精度显著提升。
- 适合做自动驾驶或机器人视觉的深度感知研究者参考。
有监督深度补全依赖高质量且对齐的RGB图像，而无监督方法因缺乏显式视觉线索常精度受限。本文提出一种新范式GUDC：利用ControlNet强大的深度条件生成能力，直接从稀疏深度图合成伪图像，将原无监督设置转化为语义引导的补全任务。为缓解深度稀疏导致的图像-深度错位问题，设计多层级密集到稀疏特征蒸馏策略，以密集深度特征作为教师信号，指导稀疏输入的结构一致性学习。此外，在伪图像引导补全阶段引入伪图像语义注意力融合模块，自适应提取有效语义信息并抑制纹理幻觉等伪影。在KITTI与NYUv2数据集上的大量实验表明，GUDC在准确性和鲁棒性上均优于现有方法。
原文摘要 · Abstract (English)
Guided depth completion methods heavily depend on RGB quality and alignment, while unguided ones often suffer from limited precision due to the absence of explicit visual cues. In this paper, we present Depth-to-Image Synthesis-Driven Generative Unguided Depth Completion (GUDC), a new completion paradigm that innovatively bridges advanced 2D generative models with unguided depth completion, enabling semantics-aware depth inference without real RGB inputs. Our key idea is to exploit ControlNet's powerful depth-conditioned generation capability to synthesize pseudo-images directly from sparse depth, effectively converting the original unguided setting into a semantics-guided one. To address the potential image-depth misalignment caused by depth sparsity, we propose a multi-level dense-to-sparse representation distillation strategy for ControlNet fine-tuning, where dense-depth features act as teacher signals to distill consistent structural representations for sparse-depth inputs. Furthermore, during pseudo-image-guided completion, we propose a pseudo-image semantic attention fusion module to adaptively extract informative semantic cues from pseudo-images while suppressing artifacts (e.g., texture hallucinations). Extensive experiments on KITTI and NYUv2 validate that our GUDC achieves superior accuracy and robustness over existing methods.
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。