Search Results for author: Srinath Sridhar

Found 34 papers, 14 papers with code

AnyHome: Open-Vocabulary Generation of Structured and Textured 3D Homes

no code implementations11 Dec 2023 Zehao Wen, Zichen Liu, Srinath Sridhar, Rao Fu

We introduce AnyHome, a framework that translates open-vocabulary descriptions, ranging from simple labels to elaborate paragraphs, into well-structured and textured 3D indoor scenes at a house-scale.

MANUS: Markerless Hand-Object Grasp Capture using Articulated 3D Gaussians

no code implementations4 Dec 2023 Chandradeep Pokhariya, Ishaan N Shah, Angela Xing, Zekun Li, Kefan Chen, Avinash Sharma, Srinath Sridhar

Since our representation uses Gaussian primitives, it enables us to efficiently and accurately estimate contacts between the hand and the object.

Mixed Reality Object

HyP-NeRF: Learning Improved NeRF Priors using a HyperNetwork

no code implementations NeurIPS 2023 Bipasha Sen, Gaurav Singh, Aditya Agarwal, Rohith Agaram, K Madhava Krishna, Srinath Sridhar

Neural Radiance Fields (NeRF) have become an increasingly popular representation to capture high-quality appearance and shape of scenes and objects.


Semantic Attention Flow Fields for Monocular Dynamic Scene Decomposition

no code implementations ICCV 2023 Yiqing Liang, Eliot Laidlaw, Alexander Meyerowitz, Srinath Sridhar, James Tompkin

From video, we reconstruct a neural volume that captures time-varying color, density, scene flow, semantics, and attention information.


SCARP: 3D Shape Completion in ARbitrary Poses for Improved Grasping

no code implementations17 Jan 2023 Bipasha Sen, Aditya Agarwal, Gaurav Singh, Brojeshwar B., Srinath Sridhar, Madhava Krishna

Unlike existing methods that depend on an external canonicalization, SCARP performs canonicalization, pose estimation, and shape completion in a single network, improving the performance by 45% over the existing baselines.

3D Shape Generation Pose Estimation +1

Canonical Fields: Self-Supervised Learning of Pose-Canonicalized Neural Fields

1 code implementation CVPR 2023 Rohith Agaram, Shaurya Dewan, Rahul Sajnani, Adrien Poulenard, Madhava Krishna, Srinath Sridhar

We present Canonical Field Network (CaFi-Net), a self-supervised method to canonicalize the 3D pose of instances from an object category represented as neural fields, specifically neural radiance fields (NeRFs).

Object Self-Supervised Learning

ShapeCrafter: A Recursive Text-Conditioned 3D Shape Generation Model

1 code implementation19 Jul 2022 Rao Fu, Xiao Zhan, YiWen Chen, Daniel Ritchie, Srinath Sridhar

Results show that our method can generate shapes consistent with text descriptions, and shapes evolve gradually as more phrases are added.

3D Shape Generation

Unsupervised Kinematic Motion Detection for Part-segmented 3D Shape Collections

1 code implementation17 Jun 2022 Xianghao Xu, Yifan Ruan, Srinath Sridhar, Daniel Ritchie

We operationalize this concept with an algorithm that optimizes a shape's part motion parameters such that it can transform into other shapes in the collection.

Motion Detection motion prediction +2

NeuralODF: Learning Omnidirectional Distance Fields for 3D Shape Representation

no code implementations12 Jun 2022 Trevor Houchens, Cheng-You Lu, Shivam Duggal, Rao Fu, Srinath Sridhar

We propose Omnidirectional Distance Fields (ODFs), a new 3D shape representation that encodes geometry by storing the depth to the object's surface from any 3D position in any viewing direction.

3D Shape Representation

Learning Body-Aware 3D Shape Generative Models

no code implementations13 Dec 2021 Bryce Blinn, Alexander Ding, R. Kenny Jones, Manolis Savva, Srinath Sridhar, Daniel Ritchie

The body-shape-conditioned models produce chairs which will be comfortable for a person with the given body shape; the pose-conditioned models produce chairs which accommodate the given sitting pose.

Neural Fields in Visual Computing and Beyond

1 code implementation22 Nov 2021 Yiheng Xie, Towaki Takikawa, Shunsuke Saito, Or Litany, Shiqin Yan, Numair Khan, Federico Tombari, James Tompkin, Vincent Sitzmann, Srinath Sridhar

Recent advances in machine learning have created increasing interest in solving visual computing problems using a class of coordinate-based neural networks that parametrize physical properties of scenes or objects across space and time.

3D Reconstruction Image Animation +1

StrobeNet: Category-Level Multiview Reconstruction of Articulated Objects

no code implementations17 May 2021 Ge Zhang, Or Litany, Srinath Sridhar, Leonidas Guibas

We present StrobeNet, a method for category-level 3D reconstruction of articulating objects from one or more unposed RGB images.

3D Reconstruction Object

Pix2Surf: Learning Parametric 3D Surface Models of Objects from Images

1 code implementation ECCV 2020 Jiahui Lei, Srinath Sridhar, Paul Guerrero, Minhyuk Sung, Niloy Mitra, Leonidas J. Guibas

We investigate the problem of learning to generate 3D parametric surface representations for novel object instances, as seen from one or more views.

CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations

1 code implementation NeurIPS 2020 Davis Rempe, Tolga Birdal, Yongheng Zhao, Zan Gojcic, Srinath Sridhar, Leonidas J. Guibas

We propose CaSPR, a method to learn object-centric Canonical Spatiotemporal Point Cloud Representations of dynamically moving or evolving objects.

Object Pose Estimation

Representation Learning Through Latent Canonicalizations

no code implementations26 Feb 2020 Or Litany, Ari Morcos, Srinath Sridhar, Leonidas Guibas, Judy Hoffman

We seek to learn a representation on a large annotated data source that generalizes to a target domain using limited new supervision.


Continuous Geodesic Convolutions for Learning on 3D Shapes

no code implementations6 Feb 2020 Zhangsihao Yang, Or Litany, Tolga Birdal, Srinath Sridhar, Leonidas Guibas

In this work, we wish to challenge this practice and use a neural network to learn descriptors directly from the raw mesh.

Predicting the Physical Dynamics of Unseen 3D Objects

1 code implementation16 Jan 2020 Davis Rempe, Srinath Sridhar, He Wang, Leonidas J. Guibas

Experiments show that we can accurately predict the changes in state for unseen object geometries and initial conditions.


Multiview Aggregation for Learning Category-Specific Shape Reconstruction

1 code implementation NeurIPS 2019 Srinath Sridhar, Davis Rempe, Julien Valentin, Sofien Bouaziz, Leonidas J. Guibas

We investigate the problem of learning category-specific 3D shape reconstruction from a variable number of RGB views of previously unobserved object instances.

3D Shape Reconstruction Object

Learning Generalizable Physical Dynamics of 3D Rigid Objects

no code implementations2 Jan 2019 Davis Rempe, Srinath Sridhar, He Wang, Leonidas J. Guibas

In this work, we focus on predicting the dynamics of 3D rigid objects, in particular an object's final resting position and total rotation when subjected to an impulsive force.

Autonomous Vehicles Object +1

Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB

6 code implementations9 Dec 2017 Dushyant Mehta, Oleksandr Sotnychenko, Franziska Mueller, Weipeng Xu, Srinath Sridhar, Gerard Pons-Moll, Christian Theobalt

Our approach uses novel occlusion-robust pose-maps (ORPM) which enable full body pose inference even under strong partial occlusions by other people and objects in the scene.

3D Human Pose Estimation 3D Multi-Person Pose Estimation (absolute) +3

VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera

1 code implementation3 May 2017 Dushyant Mehta, Srinath Sridhar, Oleksandr Sotnychenko, Helge Rhodin, Mohammad Shafiei, Hans-Peter Seidel, Weipeng Xu, Dan Casas, Christian Theobalt

A real-time kinematic skeleton fitting method uses the CNN output to yield temporally stable 3D global pose reconstructions on the basis of a coherent kinematic skeleton.

3D Human Pose Estimation

Real-time Joint Tracking of a Hand Manipulating an Object from RGB-D Input

no code implementations16 Oct 2016 Srinath Sridhar, Franziska Mueller, Michael Zollhöfer, Dan Casas, Antti Oulasvirta, Christian Theobalt

However, due to difficult occlusions, fast motions, and uniform hand appearance, jointly tracking hand and object pose is more challenging than tracking either of the two separately.

Object Object Tracking

Fast and Robust Hand Tracking Using Detection-Guided Optimization

no code implementations CVPR 2015 Srinath Sridhar, Franziska Mueller, Antti Oulasvirta, Christian Theobalt

In the optimization step, a novel objective function combines the detected part labels and a Gaussian mixture representation of the depth to estimate a pose that best fits the depth.

Pose Estimation

Real-Time Hand Tracking Using a Sum of Anisotropic Gaussians Model

no code implementations11 Feb 2016 Srinath Sridhar, Helge Rhodin, Hans-Peter Seidel, Antti Oulasvirta, Christian Theobalt

In this paper, we propose a new approach that tracks the full skeleton motion of the hand from multiple RGB cameras in real-time.

Cannot find the paper you are looking for? You can Submit a new open access paper.