activity
20182023
most citedUnsupervised 3D Pose Estimation with Geometric Self-Supervision

19 citations · 27 across the 4 of their papers we have counts for

collaborators
Showing cs.CVShow all

9 papers · 1 filter

cs.CV2023

FlexNeRF: Photorealistic Free-viewpoint Rendering of Moving Humans from Sparse Views

Vinoj Jayasundara, Amit Agrawal, Nicolas Heron +2

We present FlexNeRF, a method for photorealistic freeviewpoint rendering of humans in motion from monocular videos. Our approach works well with sparse views, which is a challengin…

cs.CV20222 cited

Sequential Ensembling for Semantic Segmentation

Rawal Khirodkar, Brandon Smith, Siddhartha Chandra +2

Ensemble approaches for deep-learning-based semantic segmentation remain insufficiently explored despite the proliferation of competitive benchmarks and downstream applications. In…

cs.CV2021

Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation

Rawal Khirodkar, Visesh Chari, Amit Agrawal +1

A key assumption of top-down human pose estimation approaches is their expectation of having a single person/instance present in the input bounding box. This often leads to failure…

cs.CV2020

PoseNet3D: Learning Temporally Consistent 3D Human Pose via Knowledge Distillation

Shashank Tripathi, Siddhant Ranade, Ambrish Tyagi +1

Recovering 3D human pose from 2D joints is a highly unconstrained problem. We propose a novel neural network framework, PoseNet3D, that takes 2D joints as input and outputs 3D skel…

cs.CV201919 cited

Unsupervised 3D Pose Estimation with Geometric Self-Supervision

Ching-Hang Chen, Ambrish Tyagi, Amit Agrawal +4

We present an unsupervised learning approach to recover 3D human pose from 2D skeletal joints extracted from a single image. Our method does not require any multi-view image data,…

cs.CV20196 cited

Learning to Generate Synthetic Data via Compositing

Shashank Tripathi, Siddhartha Chandra, Amit Agrawal +3

We present a task-aware approach to synthetic data generation. Our framework employs a trainable synthesizer network that is optimized to produce meaningful training samples by ass…