2 code implementations • 7 Feb 2024 • Vinayak Gupta, Rahul Goel, Sirikonda Dhawal, P. J. Narayanan
Our GSN representation generates new views of unseen scenes on the fly along with consistent, per-pixel semantic features.
no code implementations • 19 Dec 2022 • Rahul Goel, Sirikonda Dhawal, Saurabh Saini, P. J. Narayanan
In this work, we present StyleTRF, a compact, quick-to-optimize strategy for stylized view generation using TensoRF.
no code implementations • 16 Aug 2022 • Pulkit Gera, Mohammad Reza Karimi Dastjerdi, Charles Renaud, P. J. Narayanan, Jean-François Lalonde
We present PanoHDR-NeRF, a neural representation of the full HDR radiance field of an indoor scene, and a pipeline to capture it casually, without elaborate setups or complex capture protocols.
no code implementations • 24 May 2022 • Sai Sagar Jinka, Astitva Srivastava, Chandradeep Pokhariya, Avinash Sharma, P. J. Narayanan
The parametric body prior enforces geometrical consistency on the body shape and pose, while the non-parametric representation models loose clothing and handle self-occlusions as well.
1 code implementation • 14 Oct 2021 • Pulkit Gera, Aakash KT, Dhawal Sirikonda, Parikshit Sakurikar, P. J. Narayanan
We present a neural rendering framework for simultaneous view synthesis and appearance editing of a scene from multi-view images captured under known environment illumination.
no code implementations • 9 Jun 2021 • Sai Sagar Jinka, Rohan Chacko, Astitva Srivastava, Avinash Sharma, P. J. Narayanan
3D human body reconstruction from monocular images is an interesting and ill-posed problem in computer vision with wider applications in multiple domains.
no code implementations • 20 Dec 2020 • Parikshit Sakurikar, P. J. Narayanan
We present a comprehensive algorithm for post-capture refocusing in a geometrically correct manner.
1 code implementation • 16 Feb 2020 • Sai Sagar Jinka, Rohan Chacko, Avinash Sharma, P. J. Narayanan
We introduce PeeledHuman - a novel shape representation of the human body that is robust to self-occlusions.
1 code implementation • 26 Aug 2019 • Aakash KT, Parikshit Sakurikar, Saurabh Saini, P. J. Narayanan
Photo realism in computer generated imagery is crucially dependent on how well an artist is able to recreate real-world materials in the scene.
Graphics
no code implementations • 11 Feb 2019 • Saurabh Saini, P. J. Narayanan
Global context priors establish correspondences at the scene level.
1 code implementation • 3 Dec 2018 • Aryaman Gupta, Kalpit Thakkar, Vineet Gandhi, P. J. Narayanan
Monocular head pose estimation requires learning a model that computes the intrinsic Euler angles for pose (yaw, pitch, roll) from an input image of human face.
Ranked #2 on Head Pose Estimation on AFLW
1 code implementation • 13 Sep 2018 • Kalpit Thakkar, P. J. Narayanan
We divide the skeleton graph into four subgraphs with joints shared across them and learn a recognition model using a part-based graph convolutional network.
Ranked #22 on Action Recognition on NTU RGB+D
no code implementations • ECCV 2018 • Parikshit Sakurikar, Ishit Mehta, Vineeth N. Balasubramanian, P. J. Narayanan
Post-capture control of the focus position of an image is a useful photographic tool.
no code implementations • ECCV 2018 • Rajvi Shah, Visesh Chari, P. J. Narayanan
Accuracy and efficiency of large-scale SfM is crucially dependent on the input view-graph.
no code implementations • ICCV 2017 • Parikshit Sakurikar, P. J. Narayanan
Depth from focus is a highly accessible method to estimate the 3D structure of everyday scenes.
no code implementations • 3 Aug 2017 • Rajvi Shah, Visesh Chari, P. J. Narayanan
Accuracy and efficiency of large-scale SfM is crucially dependent on the input view-graph.
no code implementations • 18 Oct 2016 • Aditya Singh, Saurabh Saini, Rajvi Shah, P. J. Narayanan
In this paper, we focus on the problem of unsupervised action classification in wild vines using traditional labeled datasets.
no code implementations • 19 Dec 2015 • Rajvi Shah, Aditya Deshpande, P. J. Narayanan
We present a multistage approach for SFM reconstruction of a single component that breaks the sequential nature of the incremental SFM methods.