From the 1 of 6 linked papers with an AI index.
6 papers
PixelLoop: Shortcut Topological Navigation with Pixel-Level Loops
Sarthak Chittawar, Vansh Garg, Aditya Vadali +4
PixelLoop adds loop closures directly in pixel space to create dense topological shortcuts for visual navigation, enabling more reliable any-point-to-any-point planning and improvi…
MASt3R-Nav: WayPixel Navigation in Relative 3D Maps
Vansh Garg, Rohit Jayanti, Krish Pandya +5
Visual navigation ability is strongly tied to its underlying representation of the world. Unlike classical 3D maps that require globally-consistent geometry, image- or object-relat…
SegMASt3R: Geometry Grounded Segment Matching
Rohit Jayanti, Swayam Agrawal, Vansh Garg +4
Segment matching is an important intermediate task in computer vision that establishes correspondences between semantically or geometrically coherent regions across images. Unlike…
ObjectReact: Learning Object-Relative Control for Visual Navigation
Sourav Garg, Dustin Craggs, Vineeth Bhat +5
Visual navigation using only a single camera and a topological map has recently become an appealing alternative to methods that require additional sensors and 3D maps. This is typi…
Keypoint Aware Masked Image Modelling
Madhava Krishna, A V Subramanyam
SimMIM is a widely used method for pretraining vision transformers using masked image modeling. However, despite its success in fine-tuning performance, it has been shown to perfor…
QueSTMaps: Queryable Semantic Topological Maps for 3D Scene Understanding
Yash Mehan, Kumaraditya Gupta, Rohit Jayanti +3
Robotic tasks such as planning and navigation require a hierarchical semantic understanding of a scene, which could include multiple floors and rooms. Current methods primarily foc…