4 papers · 1 filter
Improving Neural Surface Reconstruction with Feature Priors from Multi-View Image
Xinlin Ren, Chenjie Cao, Yanwei Fu +1
Recent advancements in Neural Surface Reconstruction (NSR) have significantly improved multi-view reconstruction when coupled with volume rendering. However, relying solely on phot…
MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo
Chenjie Cao, Xinlin Ren, Yanwei Fu
Recent advancements in learning-based Multi-View Stereo (MVS) methods have prominently featured transformer-based models with attention mechanisms. However, existing approaches hav…
Rethinking the Multi-view Stereo from the Perspective of Rendering-based Augmentation
Chenjie Cao, Xinlin Ren, Xiangyang Xue +1
GigaMVS presents several challenges to existing Multi-View Stereo (MVS) algorithms for its large scale, complex occlusions, and gigapixel images. To address these problems, we firs…
Density-preserving Deep Point Cloud Compression
Yun He, Xinlin Ren, Danhang Tang +3
Local density of point clouds is crucial for representing local details, but has been overlooked by existing point cloud compression methods. To address this, we propose a novel de…