We propose SparseDC, a model for Depth Completion of Sparse and non-uniform
depth inputs. Unlike previous methods focusing on completing fixed
distributions on benchmark datasets (e.g., NYU with 500 points, KITTI with 64
lines), SparseDC is specifically designed to handle depth maps with poor
quality in real usage. The key contributions of SparseDC are two-fold. First,
we design a simple strategy, called SFFM, to improve the robustness under
sparse input by explicitly filling the unstable depth features with stable
image features. Second, we propose a two-branch feature embedder to predict
both the precise local geometry of regions with available depth values and
accurate structures in regions with no depth. The key of the embedder is an
uncertainty-based fusion module called UFFM to balance the local and long-term
information extracted by CNNs and ViTs. Extensive indoor and outdoor
experiments demonstrate the robustness of our framework when facing sparse and
non-uniform input depths. The pre-trained model and code are available at
this https URL

SparseDC 模型用于完成稀疏和非均匀的深度输入补全。该模型通过 SFFM 策略填充不稳定的深度特征和稳定的图像特征，使用两个分支的特征嵌入器预测有深度值的区域的准确局部几何和无深度的区域的准确结构，关键在于通过 UFFM 模块平衡 CNN 和 ViT 提取的局部和长期信息。经过室内外广泛实验证明了该框架在面对稀疏和非均匀深度输入时的稳健性。