DTU
Emerging9papers using it
2021first seen
The DTU dataset is a benchmark used to evaluate Multi-View Stereo (MVS) methods, containing a collection of multi-view images and corresponding ground truth depth maps for assessing 3D reconstruction performance.
Papers using DTU (9)
- G$^2$SR: Geometric Methods for Fast and Memory-Efficient Gaussian-based Surface ReconstructionSparse-View Surface Reconstruction using Gaussian Splatting through High-Confidence Depth Propagation with Normal PriorsLightweight and Accurate Multi-View Stereo with Confidence-Aware Diffusion ModelIA-MVS: Instance-Focused Adaptive Depth Sampling for Multi-View StereoDepth-Guided Bundle Sampling for Efficient Generalizable Neural Radiance Field ReconstructionBoosting Multi-View Stereo with Depth Foundation Model in the Absence of
Real-World LabelsICG-MVSNet: Learning Intra-view and Cross-view Relationships for
Guidance in Multi-View StereoDetail-aware multi-view stereo network for depth estimationMulti-View Stereo with Transformer