no code implementations • 3 Dec 2024 • Kefan Chen, Chaerin Min, Linguang Zhang, Shreyas Hampali, Cem Keskin, Srinath Sridhar
We present FoundHand, a large-scale domain-specific diffusion model for synthesizing single and dual hand images.
no code implementations • 28 Nov 2024 • Prithviraj Banerjee, Sindi Shkodrani, Pierre Moulon, Shreyas Hampali, Shangchen Han, Fan Zhang, Linguang Zhang, Jade Fountain, Edward Miller, Selen Basol, Richard Newcombe, Robert Wang, Jakob Julian Engel, Tomas Hodan
We introduce HOT3D, a publicly available dataset for egocentric hand and object tracking in 3D.
no code implementations • 13 Jun 2024 • Prithviraj Banerjee, Sindi Shkodrani, Pierre Moulon, Shreyas Hampali, Fan Zhang, Jade Fountain, Edward Miller, Selen Basol, Richard Newcombe, Robert Wang, Jakob Julian Engel, Tomas Hodan
The dataset offers over 833 minutes (more than 3. 7M images) of multi-view RGB/monochrome image streams showing 19 subjects interacting with 33 diverse rigid objects, multi-modal signals such as eye gaze or scene point clouds, as well as comprehensive ground truth annotations including 3D poses of objects, hands, and cameras, and 3D models of hands and objects.
1 code implementation • 26 Mar 2024 • Chenhongyi Yang, Anastasia Tkach, Shreyas Hampali, Linguang Zhang, Elliot J. Crowley, Cem Keskin
We also show that our method can be seamlessly extended to monocular settings, which achieves state-of-the-art performance on the SceneEgo dataset, improving MPJPE by 25. 5mm (21% improvement) compared to the best existing method with only 60. 7% model parameters and 36. 4% FLOPs.
Ranked #1 on
Egocentric Pose Estimation
on UnrealEgo
no code implementations • 26 Mar 2024 • Sammy Christen, Shreyas Hampali, Fadime Sener, Edoardo Remelli, Tomas Hodan, Eric Sauser, Shugao Ma, Bugra Tekin
For the textual guidance, we contribute comprehensive text descriptions to the GRAB dataset and show that they enable our method to have more fine-grained control over hand-object interactions.
no code implementations • CVPR 2023 • Shreyas Hampali, Tomas Hodan, Luan Tran, Lingni Ma, Cem Keskin, Vincent Lepetit
As direct optimization over all shape and pose parameters is prone to fail without coarse-level initialization, we propose an incremental approach that starts by splitting the sequence into carefully selected overlapping segments within which the optimization is likely to succeed.
1 code implementation • 2 Jul 2021 • Shreyas Hampali, Sayan Deb Sarkar, Vincent Lepetit
HO-3D is a dataset providing image sequences of various hand-object interaction scenarios annotated with the 3D pose of the hand and the object and was originally introduced as HO-3D_v2.
1 code implementation • CVPR 2022 • Shreyas Hampali, Sayan Deb Sarkar, Mahdi Rad, Vincent Lepetit
We propose a robust and accurate method for estimating the 3D poses of two hands in close interaction from a single color image.
Ranked #4 on
hand-object pose
on HO-3D v2
2 code implementations • CVPR 2021 • Shreyas Hampali, Sinisa Stekovic, Sayan Deb Sarkar, Chetan Srinivasa Kumar, Friedrich Fraundorfer, Vincent Lepetit
We explore how a general AI algorithm can be used for 3D scene understanding to reduce the need for training data.
no code implementations • ECCV 2020 • Anil Armagan, Guillermo Garcia-Hernando, Seungryul Baek, Shreyas Hampali, Mahdi Rad, Zhaohui Zhang, Shipeng Xie, Mingxiu Chen, Boshen Zhang, Fu Xiong, Yang Xiao, Zhiguo Cao, Junsong Yuan, Pengfei Ren, Weiting Huang, Haifeng Sun, Marek Hrúz, Jakub Kanis, Zdeněk Krňoul, Qingfu Wan, Shile Li, Linlin Yang, Dongheui Lee, Angela Yao, Weiguo Zhou, Sijia Mei, Yun-hui Liu, Adrian Spurr, Umar Iqbal, Pavlo Molchanov, Philippe Weinzaepfel, Romain Brégier, Grégory Rogez, Vincent Lepetit, Tae-Kyun Kim
To address these issues, we designed a public challenge (HANDS'19) to evaluate the abilities of current 3D hand pose estimators (HPEs) to interpolate and extrapolate the poses of a training set.
1 code implementation • ECCV 2020 • Sinisa Stekovic, Shreyas Hampali, Mahdi Rad, Sayan Deb Sarkar, Friedrich Fraundorfer, Vincent Lepetit
In order to deal with occlusions between components of the layout, which is a problem ignored by previous works, we introduce an analysis-by-synthesis method to iteratively refine the 3D layout estimate.
4 code implementations • CVPR 2020 • Shreyas Hampali, Mahdi Rad, Markus Oberweger, Vincent Lepetit
This dataset is currently made of 77, 558 frames, 68 sequences, 10 persons, and 10 objects.
Ranked #16 on
3D Hand Pose Estimation
on HO-3D v2