Dynamic Spatial Propagation Network for Depth Completion
원문 초록
Image-guided depth completion aims to generate dense depth maps with sparse depth measurements and corresponding RGB images. Currently, spatial propagation networks (SPNs) are the most popular affinity-based methods in depth completion, but they still suffer from the representation limitation of the fixed affinity and the over smoothing during iterations. Our solution is to estimate independent affinity matrices in each SPN iteration, but it is over-parameterized and heavy calculation. This paper introduces an efficient model that learns the affinity among neighboring pixels with an attention-based, dynamic approach. Specifically, the Dynamic Spatial Propagation Network (DySPN) we proposed makes use of a non-linear propagation model (NLPM). It decouples the neighborhood into parts regarding to different distances and recursively generates independent attention maps to refine these parts into adaptive affinity matrices. Furthermore, we adopt a diffusion suppression (DS) operation so that the model converges at an early stage to prevent over-smoothing of dense depth. Finally, in order to decrease the computational cost required, we also introduce three variations that reduce the amount of neighbors and attentions needed while still retaining similar accuracy. In practice, our method requires less iteration to match the performance of other SPNs and yields better results overall. DySPN outperforms other state-of-the-art (SoTA) methods on KITTI Depth Completion (DC) evaluation by the time of submission and is able to yield SoTA performance in NYU Depth v2 dataset as well.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
PacGDC: Label-Efficient Generalizable Depth Completion with Projection Ambiguity and Consistency
DEPTHOR: Depth Enhancement from a Practical Light-Weight dToF Sensor and RGB Image
Vanishing Depth: A Depth Adapter with Positional Depth Encoding for Generalized Image Encoders
SVDC: Consistent Direct Time-of-Flight Video Depth Completion with Frequency Selective Fusion
TranSplat: Surface Embedding-guided 3D Gaussian Splatting for Transparent Object Manipulation
TDCNet: Transparent Objects Depth Completion with CNN-Transformer Dual-Branch Parallel Network
토론
이 논문과 연결된 포럼 글이 아직 없습니다.