SparseFormer: Attention-based Depth Completion Network
원문 초록
Most pipelines for Augmented and Virtual Reality estimate the ego-motion of the camera by creating a map of sparse 3D landmarks. In this paper, we tackle the problem of depth completion, that is, densifying this sparse 3D map using RGB images as guidance. This remains a challenging problem due to the low density, non-uniform and outlier-prone 3D landmarks produced by SfM and SLAM pipelines. We introduce a transformer block, SparseFormer, that fuses 3D landmarks with deep visual features to produce dense depth. The SparseFormer has a global receptive field, making the module especially effective for depth completion with low-density and non-uniform landmarks. To address the issue of depth outliers among the 3D landmarks, we introduce a trainable refinement module that filters outliers through attention between the sparse landmarks.
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.