My research focus spans the domains of 3D Comupter Vision, Self-Supervised Learning, and Continual Learning, with the penultimate aim of bestowing robots with a human-like perception.
Beyond by academic endeavors, I serve as an external collaborator to distinguised scholars including Prof. Chandra Kambhamettu @ VIMS Lab | University of Delaware and Dr. Dena Bazazian @ University of Plymouth.
I did my Bachelor’s degree in Electronics and Communication at KLE Technological University, India where I was advised by Prof. Uma Mudenagudi and worked on Self-Supervised geometric methods for a DST funded project to Categorize Crowdsourced data.
Our poster “Novel Class Discovery for Representation of Real-World Heritage Data as Neural Radiance Fields” is accepted @ AAAI 2024
Oct 15, 2023
Our first Dataset: “A Benchmark Grocery Dataset of Realworld Point Clouds from Single View” in collaboration with Prof. Chandra Kambhamettu, Director of VIMS lab | University of Delaware, is accepted @ IEEE 3DV 2024
In the realm of 3D-computer vision applications, point cloud few-shot learning plays a critical role. However, it poses an arduous challenge due to the sparsity, irregularity, and unordered nature of the data. Current methods rely on complex local geometric extraction techniques such as convolution, graph, and attention mechanisms, along with extensive data-driven pre-training tasks. These approaches contradict the fundamental goal of few-shot learning, which is to facilitate efficient learning. To address this issue, we propose GPr-Net (Geometric Prototypical Network), a lightweight and computationally efficient geometric prototypical network that captures the intrinsic topology of point clouds and achieves superior performance. Our proposed method, IGI++(Intrinsic Geometry Interpreter++) employs vector-based hand-crafted intrinsic geometry interpreters and Laplace vectors to extract and evaluate point cloud morphology, resulting in improved representations for FSL (Few-Shot Learning). Additionally, Laplace vectors enable the extraction of valuable features from point clouds with fewer points. To tackle the distribution drift challenge in few-shot metric learning, we leverage hyperbolic space and demonstrate that our approach handles intra and inter-class variance better than existing point cloud few-shot learning methods. Experimental results on the ModelNet40 dataset show that GPr-Net outperforms state-of-the-art methods in few-shot learning on point clouds, achieving utmost computational efficiency that is 170x better than all existing works. The code is publicly available at https://github. com/TejasAnvekar/GPr-Net.
@inproceedings{Anvekar_2023_CVPR,author={Anvekar, Tejas and Bazazian, Dena},title={GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning},booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},month=jun,year={2023},pages={4178-4187},bibtex_show=true,selected=true,}
CVPR-W
VG-VAE: A Venatus Geometry Point-Cloud Variational Auto-Encoder
Tejas Anvekar, Ramesh Ashok Tabib, Dikshit Hegde, and Uma Mudengudi
In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Jun 2022
In this paper, we propose VG-VAE: Venatus Geometric Variational Auto-Encoder for capturing unsupervised hierarchical local and global geometric signatures in pointcloud. Recent research emphasises the significance of the underlying intrinsic geometry for pointcloud processing. Our contribution is to extract and analyse the morphology of the pointcloud using the proposed Geometric Proximity Correlator (GPC) and variational sampling of the latent. The extraction of local geometric signatures is facilitated by the GPC, whereas the extraction of global geometry is facilitated by variational sampling. Furthermore, we apply a naive mix of vector algebra and 3D geometry to extract the basic per-point geometric signature, which assists the unsupervised hypothesis. We provide statistical analyses of local and global geometric signatures. The impacts of our geometric features are demonstrated on pointcloud classification as downstream task using the classic pointcloud feature extractor PointNet. We demonstrate our analysis on ModelNet40 a benchmark dataset, and compare with state-of-the-art techniques.
@inproceedings{Anvekar_2022_CVPR,author={Anvekar, Tejas and Tabib, Ramesh Ashok and Hegde, Dikshit and Mudengudi, Uma},title={VG-VAE: A Venatus Geometry Point-Cloud Variational Auto-Encoder},booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},month=jun,year={2022},pages={2978-2985},selected=true,bibtex_show=true,}
ICCV-W
ASUR3D: Arbitrary Scale Upsampling and Refinement of 3D Point Clouds Using Local Occupancy Fields
Akash Kumbar, Tejas Anvekar, Ramesh Ashok Tabib, and Uma Mudenagudi
In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, Oct 2023
In this paper, we introduce ASUR3D, a novel methodology for the arbitrary-scale upsampling of 3D point clouds employing Local Occupancy Representation. Our proposed implicit occupancy representation enables efficient point classification, effectively discerning points belonging to the surface from non-surface points. Learning an implicit representation of open surfaces, enables one to capture the better local neighbourhood representation, leading to finer refinement and reconstruction with enhanced preservation of intricate geometric details. Leveraging this capability, we can accurately sample an arbitrary number of points on the surface, facilitating precise and flexible upsampling. We demonstrate the effectiveness of ASUR3D on PUGAN and PU1K benchmark datasets. Our proposed method achieves state-of-the-art results on all benchmarks and for all evaluation metrics. Additionally, we demonstrate the efficacy of our methodology on self-proposed heritage data generated through photogrammetry, further confirming its effectiveness in diverse scenarios. The code is publicly available at https://github. com/Akash-Kumbar/ASUR3D
@inproceedings{Kumbar_2023_ICCV,author={Kumbar, Akash and Anvekar, Tejas and Tabib, Ramesh Ashok and Mudenagudi, Uma},title={ASUR3D: Arbitrary Scale Upsampling and Refinement of 3D Point Clouds Using Local Occupancy Fields},booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops},month=oct,year={2023},pages={1652-1661},selected=true,bibtex_show=true,}