PatchMatch based Multiview Stereo with Local Quadric Window

Song, H. C.; Park, Jae-Seong; Heo, Suwoong; Kang, Jiwoo; Lee, Sanghoon

doi:10.1145/3394171.3413966

Cited by 4 publications

(2 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These methods require the point-to-point correspondences between 3D shapes and require a high computational cost. On the other hand, fast and efficient tracking methods for image alignment by seeking the point correspondences between the images have been addressed by a local Patch-Match method [13,14,15,16]. Zhou et.…”

Section: Introductionmentioning

confidence: 99%

“…We address the spatially-varying warps on depth maps by extending the patch-based alignment scheme [13,14,15,16] to the 3D surface. In this paper, we propose a novel multiview surface fusion method, WarpingFusion, where an accurate 3D shape from multi-view depth maps is robustly reconstructed against sensor noise and spatial mismatches among depth maps.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

WarpingFusion: Accurate Multi-View TSDF Fusion with Local Perspective Warp

Kang

Lee

Jang

et al. 2021

2021 IEEE International Conference on Image Processing (ICIP)

Self Cite

View full text Add to dashboard Cite

In this paper, we propose the novel 3D reconstruction framework, where the surface of a target object is reconstructed accurately and robustly from multi-view depth maps. A depth map of a moving object tends to have the spatiallyvarying perspective warps due to motion blur and rolling shutter artifacts. Incorporating those misaligned points from the views into the world coordinate leads to significant artifacts in the reconstructed shape. We address the mismatches by the patch-based depth-to-surface alignment using implicit surface-based distance measurement. The patch-based minimization finds spatial warps on the depth map fast and accurately with the global transformation preserved. The proposed framework efficiently optimizes the local alignments against depth occlusions and local variants thanks to the point to surface distance based on an implicit representation. The proposed method shows significant improvements over the other reconstruction methods, demonstrating efficiency and benefits of our method in the multi-view reconstruction.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%