Dikshit Hegde

 

I am a Research Assistant at CEVI under the advised by Prof. Uma Mudenagudi and Ramesh Ashok Tabib where I work on Understanding and Learning Representation of 3D Point Clouds. I am interested in understanding the data in unsupervised manner.

I did my Bachelors in Electronics and Communication from KLE Technological University, Hubballi. I majorly worked on Categorization of Crowdsourced data, data encryption, and 3d data creation advised by Prof Uma Mudenagudi and Ramesh Ashok Tabib.

Currently looking for a full Time PhD opportunity.

Recent Updates

  • April 2024: Our work on Affordance Detection in pointclouds got Accepted in DLGC Workshop @ CVPR 2024 with paper title LGAfford-Net: A Local Geometry Aware Affordance Detection Network for 3D Point Clouds.
  • August 2023: Our work on Detection and filling of holes in pointclouds got Accepted in e-Heritage Workshop @ ICCV 2023 with paper title DeFi: Detection and Filling of Holes in Point Clouds Towards Restoration of Digitized Cultural Heritage Models.
  • April 2023: Our work on Decomposition of pointclouds got Accepted in StruCo3D Workshop @ CVPR 2023 with paper title IPD-Net: SO(3) Invariant Primitive Decompositional Network for 3D Point Clouds.
  • Dec 2022: Our work on Topological understanding of pointclouds got Accepted in SIGGRAPH Asia 2022 Posters with poster title Metric-KNN is All You Needs.
  • April 2022: Our work on Decomposition of pointclouds got Accepted in DLGC Workshop @ CVPR 2022 with paper title VG-VAE: A Venatus Geometry Point-Cloud Variational Auto-Encoder.
  • April 2022: Our work on Categorization of Images got Accepted in IMW Workshop @ CVPR 2022 with paper title DA-AE: Disparity-Alleviation Auto-Encoder Towards Categorization of Heritage Images for Aggrandized 3D Reconstruction.

Email  /  CV /  Google Scholar  /  GitHub  /  LinkedIn

 

Research Interests

My primary research area is 3D Computer Vision (Unsupervised Learning, Learning Representation, Categorization Point Cloud Analysis, Geometric Deep Learning, and Incremental Learning).

Selected Works

LGAfford-Net: A Local Geometry Aware Affordance Detection Network for 3D Point Clouds
Ramesh Ashok Tabib, Dikshit Hegde, Uma Mudenagudi
DLGC|CVPR 2024.
[video] [pdf]

DeFi: Detection and Filling of Holes in Point Clouds Towards Restoration of Digitized Cultural Heritage Models
Ramesh Ashok Tabib, Dikshit Hegde, Tejas Anvekar, Uma Mudenagudi
e-Heritage|ICCV 2023.
[video] [pdf]

IPD-Net: SO(3) Invariant Primitive Decompositional Network for 3D Point Clouds
Ramesh Ashok Tabib, Nitishkumar Upasi, Tejas Anvekar, Dikshit Hegde, Uma Mudenagudi
StruCo3D, CVPR 2023.
[video] [pdf]

Metric-KNN is All You Need
Tejas Anvekar, Ramesh Ashok Tabib, Dikshit Hegde, Uma Mudenagudi
SIGGRAPH Asia Posters 2022
[video] [pdf]

VG-VAE: A Venatus Geometry Point-Cloud Variational Auto-Encoder
Tejas Anvekar, Ramesh Ashok Tabib, Dikshit Hegde, Uma Mudenagudi
DLGC, CVPR 2022
[video] [pdf]

DA-AE: Disparity-Alleviation Auto-Encoder Towards Categorization of Heritage Images for Aggrandized 3D Reconstruction
Dikshit Hegde, Tejas Anvekar, Ramesh Ashok Tabib, Uma Mudenagudi
IMW, CVPR 2022
[video] [pdf]

Modeling Nuisance Classifier Towards Class-Incremental Learning of Crowd-Sourced Data
Ramesh Ashok Tabib, T Santoshkumar, Dikshit Hegde, Adarsh Jamadandi, Uma Mudenagudi
ICVGIP 2021

Deep Features for Categorization of Heritage Images Towards 3D Reconstruction
Ramesh Ashok Tabib, Dikshit Hegde, T Santoshkumar, Srikar HI, Mutturaj Harage, Chaitra Desai, Ujwala Patil, Uma Mudenagudi
VisionNet, CoCoNet 2020