Vasco Mota
Papers
1
Total Citations
7
H-Index
1
About
Vasco Mota is a researcher in computer vision and 3D reconstruction, with a focus on leveraging geometric constraints to enhance the accuracy and efficiency of spatial modeling. His work centers on the development of parallelized algorithms for dense stereo reconstruction, particularly through the innovative use of symmetry to refine slanted 3D models. In his most-cited paper, "Parallel refinement of slanted 3D reconstruction using dense stereo induced from symmetry" (2016), Mota introduced a method that exploits symmetry cues to improve depth estimation and reduce computational overhead, achieving high-fidelity 3D outputs. This contribution addresses key challenges in real-time reconstruction, such as handling textureless regions and irregular surfaces, by integrating parallel processing techniques. While his citation count of 7 reflects a focused but emerging impact, his work is notable for bridging theoretical symmetry principles with practical stereo vision applications. Mota’s research is particularly relevant for fields like autonomous navigation, augmented reality, and cultural heritage digitization, where robust 3D reconstruction is critical. His approach exemplifies how geometric priors can streamline complex vision tasks, offering a scalable pathway for future advancements in dense 3D modeling.
Research Focus
Key Achievements
Top Papers
- 1