Papers
3
Total Citations
72
H-Index
3
About
Vineet Gandhi is a computer vision and robotics researcher whose work spans depth sensing, autonomous navigation, and visual attention modeling. His most influential contribution, "High-Resolution Depth Maps Based on TOF-Stereo Fusion" (2012), addresses a fundamental challenge in robotic perception — combining the complementary strengths of time-of-flight range sensors and color cameras to produce rich, detailed depth maps. This work has proven broadly impactful across robot navigation, semantic perception, manipulation, and telepresence applications, accumulating 64 citations and establishing Gandhi as a credible voice in sensor fusion research. Beyond depth estimation, Gandhi has pursued the challenge of detecting small road obstacles using stereo vision, tackling a practically critical yet underexplored problem for autonomous ground vehicles, where conventional point cloud methods frequently fail to register low-profile hazards like rocks or bricks. He has also contributed to computational saliency research, working to streamline deep learning architectures for visual attention prediction in his 2020 paper "Tidying Deep Saliency Prediction Architectures," reflecting an ambition to bring machine perception closer to human visual cognition. Across these threads, Gandhi's research consistently bridges theoretical computer vision with real-world robotic applications.
Research Focus
Key Achievements
Top Papers
- 1High-resolution depth maps based on TOF-stereo fusion64 citations · 2012
- 2Tidying Deep Saliency Prediction Architectures4 citations · 2020
- 3