soumyadip
3D Gaussian splatting (3DGS) has recently gained recognition as a groundbreaking approach in radiance fields and computer graphics. It stands out as a jack of all trades, addressing challenges that
3D Gaussian Splatting (3DGS) is redefining the landscape of 3D computer graphics and vision — but here’s a catch: it achieves groundbreaking results without relying on any neural networks, not
In recent years, the field of 3D from multi-view has become one of the most popular topics in computer vision conferences, with a high number of submitted papers each year.
The NVIDIA AI Summit 2024, held from October 23 to 25 at the Jio World Convention Centre in Mumbai, marked a significant milestone in India’s journey toward becoming a global
DINO is a self-supervised learning (SSL) framework that uses the Vision Transformer (ViT) as it’s core architecture. While SSL initially gained popularity through its use in natural language processing (NLP)
Robotics, once a specialized and niche field, has surged into the mainstream with the rapid development of autonomous vehicles, quadruped robots, and humanoids. What’s fueling this revolution? The drive to
LiDAR SLAM is a crucial component in robotics perception, widely used in both industry and academia for its efficiency and robustness in localization and mapping. In robotics perception research, LiDAR
ROS (Robot Operating System) is more than a decade old open-source robotics middleware software, initially developed by two PhD students from Stanford University. Fast-forward to 2024, ROS has evolved into
Introduction to Monocular SLAM: Have you ever wondered how Tesla’s Autonomous Vehicle views its surroundings and understands its position, and makes smart decisions to reach its target location? Well, the
In the preceding article, YOLO Loss Functions Part 1, we focused exclusively on SIoU and Focal Loss as the primary loss functions used in the YOLO series of models. In