Papers
5
Total Citations
70
H-Index
3
About
N. Dinesh Reddy is a computer vision researcher whose work centers on the intersection of semantic scene understanding, motion segmentation, and 3D reconstruction, with a particular focus on dynamic environments. His most influential contribution, "Dynamic Body VSLAM with Semantic Constraints" (2015, 40 citations), tackled one of the field's persistent challenges: reconstructing urban scenes in the presence of dynamic objects, a problem that most large-scale SLAM approaches sidestep by assuming static scenes. By integrating semantic constraints into visual SLAM, Reddy advanced the robustness of 3D reconstruction pipelines in real-world settings. Complementing this work, his research on semantic motion segmentation — explored through dense CRF formulations (2014, 22 citations) and later deep convolutional networks (2017) — demonstrated how jointly modeling appearance and motion cues yields richer scene understanding than either signal alone. His 2018 work extended these ideas into the temporal domain using spatio-temporal optimization. Additional contributions to multi-plane detection further reflect his broad engagement with geometric scene analysis. Collectively, Reddy's research has helped lay groundwork for robust outdoor robotic navigation and autonomous perception systems operating in complex, dynamic environments.
Research Focus
Key Achievements
Top Papers
- 1Dynamic body VSLAM with semantic constraints40 citations · 2015
- 2Semantic Motion Segmentation Using Dense CRF Formulation22 citations · 2014
- 3Temporal Semantic Motion Segmentation Using Spatio Temporal Optimization4 citations · 2018
- 4Top Down Approach to Detect Multiple Planes from Pair of Images2 citations · 2014
- 5