Shreyas Hampali

Email  /  GitHub  /  Google Scholar  /  CV  


I am a third year PhD student working in the intersection of computer vision and machine learning. My research focus is on understanding the 3D world from one or more RGB images of the scene. Studying hand-object interaction excites me the most at this point and many of my projects are around this topic. I am advised by super-cool Prof. Vincent Lepetit at Computer Vision for Augmented Reality Lab at TU Graz, Austria .

Before starting PhD in 2018, I spent 3 years each at Qualcomm Research, Bangalore and Intel Technologies, Bangalore working on many projects in the area of camera hardware pipeline tuning, image and video processing solutions and their hardware implementations.


project image

Monte Carlo Scene Search for 3D Scene Understanding

Shreyas Hampali*, Sinisa Stekovic*, Sayan Deb Sarkar, Chetan Srinivasa Kumar, Friedrich Fraundorfer, Vincent Lepetit
Computer Vision and Pattern Recognition (CVPR), 2021
arxiv / project page / video / code /

We propose a Monte-Carlo Tree Search (MCTS) based analysis-by-synthesis method to recover complete scene (3D layout+objects) from a RGB-D scan of the environment. *Equal contribution

project image

General 3D Room Layout from a Single View by Render-and-Compare.

Sinisa Stekovic, Shreyas Hampali, Mahdi Rad, Sayan Deb Sarkar, Friedrich Fraundorfer, Vincent Lepetit
European Conference on Computer Vision (ECCV), 2020
arxiv / project page /

We propose an analysis-by-synthesis method to estimate a 3D layout of the room - walls, floors, ceilings - from a single perspective view. The method recovers complex non-cubiod layouts by solving a constrained discrete optimization problem.

project image

Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction

Anil Armagan, ..., Shreyas Hampali, ..., Vincent Lepetit
European Conference on Computer Vision (ECCV), 2020
arxiv /

We measure the generalization capabilities of several approaches during hand pose estimation tasks. Tasks include hand pose estimation from depth maps/RGB images with/without object interaction. Accuracy of the algorithms participating in HANDS 2019 challenge is analysed.

project image

HOnnotate: A method for 3D Annotation of Hand and Object Poses

Shreyas Hampali, Mahdi Rad, Markus Oberweger, Vincent Lepetit
Computer Vision and Pattern Recognition (CVPR), 2020
arxiv / project page / video / code /

We propose a method for automatically generation 3D pose annotations for hand and object during interaction. The resulting dataset, HO-3D is publicly available.

Design and source code from Jon Barron's website