Search Results for author: Cem Keskin

Found 26 papers, 4 papers with code

EgoPoseFormer: A Simple Baseline for Egocentric 3D Human Pose Estimation

no code implementations26 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.

Egocentric Pose Estimation

FoundPose: Unseen Object Pose Estimation with Foundation Features

no code implementations30 Nov 2023 Evin Pınar Örnek, Yann Labbé, Bugra Tekin, Lingni Ma, Cem Keskin, Christian Forster, Tomas Hodan

We find that reliable correspondences can be established by kNN matching of patch descriptors from an intermediate DINOv2 layer.

6D Pose Estimation Object +1

AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation

no code implementations CVPR 2023 Takehiko Ohkawa, Kun He, Fadime Sener, Tomas Hodan, Luan Tran, Cem Keskin

To obtain high-quality 3D hand pose annotations for the egocentric images, we develop an efficient pipeline, where we use an initial set of manual annotations to train a model to automatically annotate a much larger dataset.

3D Hand Pose Estimation Action Classification

Social Diffusion: Long-term Multiple Human Motion Anticipation

1 code implementation ICCV 2023 Julian Tanke, Linguang Zhang, Amy Zhao, Chengcheng Tang, Yujun Cai, Lezi Wang, Po-Chen Wu, Juergen Gall, Cem Keskin

We propose Social Diffusion, a novel method for short-term and long-term forecasting of the motion of multiple persons as well as their social interactions.

MotionDeltaCNN: Sparse CNN Inference of Frame Differences in Moving Camera Videos with Spherical Buffers and Padded Convolutions

no code implementations ICCV 2023 Mathias Parger, Chengcheng Tang, Thomas Neff, Christopher D. Twigg, Cem Keskin, Robert Wang, Markus Steinberger

Moving cameras add new challenges in how to fuse newly unveiled image regions with already processed regions efficiently to minimize the update rate - without increasing memory overhead and without knowing the camera extrinsics of future frames.

In-Hand 3D Object Scanning from an RGB Sequence

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.


UmeTrack: Unified multi-view end-to-end hand tracking for VR

no code implementations31 Oct 2022 Shangchen Han, Po-Chen Wu, Yubo Zhang, Beibei Liu, Linguang Zhang, Zheng Wang, Weiguang Si, Peizhao Zhang, Yujun Cai, Tomas Hodan, Randi Cabezas, Luan Tran, Muzaffer Akbay, Tsz-Ho Yu, Cem Keskin, Robert Wang

In this paper, we present a unified end-to-end differentiable framework for multi-view, multi-frame hand tracking that directly predicts 3D hand pose in world space.

MotionDeltaCNN: Sparse CNN Inference of Frame Differences in Moving Camera Videos

no code implementations18 Oct 2022 Mathias Parger, Chengcheng Tang, Thomas Neff, Christopher D. Twigg, Cem Keskin, Robert Wang, Markus Steinberger

Moving cameras add new challenges in how to fuse newly unveiled image regions with already processed regions efficiently to minimize the update rate - without increasing memory overhead and without knowing the camera extrinsics of future frames.

Neural Correspondence Field for Object Pose Estimation

no code implementations30 Jul 2022 Lin Huang, Tomas Hodan, Lingni Ma, Linguang Zhang, Luan Tran, Christopher Twigg, Po-Chen Wu, Junsong Yuan, Cem Keskin, Robert Wang

Unlike classical correspondence-based methods which predict 3D object coordinates at pixels of the input image, the proposed method predicts 3D object coordinates at 3D query points sampled in the camera frustum.

3D Reconstruction Object +1

DeltaCNN: End-to-End CNN Inference of Sparse Frame Differences in Videos

no code implementations CVPR 2022 Mathias Parger, Chengcheng Tang, Christopher D. Twigg, Cem Keskin, Robert Wang, Markus Steinberger

With DeltaCNN, we present a sparse convolutional neural network framework that enables sparse frame-by-frame updates to accelerate video inference in practice.

Rethinking the Data Annotation Process for Multi-view 3D Pose Estimation with Active Learning and Self-Training

1 code implementation27 Dec 2021 Qi Feng, Kun He, He Wen, Cem Keskin, Yuting Ye

Notably, on CMU Panoptic Studio, we are able to reduce the turn-around time by 60% and annotation cost by 80% when compared to the conventional annotation process.

3D Pose Estimation Active Learning +1

Multiresolution Deep Implicit Functions for 3D Shape Representation

no code implementations ICCV 2021 Zhang Chen, yinda zhang, Kyle Genova, Sean Fanello, Sofien Bouaziz, Christian Haene, Ruofei Du, Cem Keskin, Thomas Funkhouser, Danhang Tang

To the best of our knowledge, MDIF is the first deep implicit function model that can at the same time (1) represent different levels of detail and allow progressive decoding; (2) support both encoder-decoder inference and decoder-only latent optimization, and fulfill multiple applications; (3) perform detailed decoder-only shape completion.

3D Reconstruction 3D Shape Representation +1

HumanGPS: Geodesic PreServing Feature for Dense Human Correspondences

1 code implementation CVPR 2021 Feitong Tan, Danhang Tang, Mingsong Dou, Kaiwen Guo, Rohit Pandey, Cem Keskin, Ruofei Du, Deqing Sun, Sofien Bouaziz, Sean Fanello, Ping Tan, yinda zhang

In this paper, we address the problem of building dense correspondences between human images under arbitrary camera viewpoints and body poses.

Gradient Flow in Sparse Neural Networks and How Lottery Tickets Win

1 code implementation7 Oct 2020 Utku Evci, Yani A. Ioannou, Cem Keskin, Yann Dauphin

Sparse Neural Networks (NNs) can match the generalization of dense NNs using a fraction of the compute/storage for inference, and also have the potential to enable efficient training.

RePose: Learning Deep Kinematic Priors for Fast Human Pose Estimation

no code implementations10 Feb 2020 Hossam Isack, Christian Haene, Cem Keskin, Sofien Bouaziz, Yuri Boykov, Shahram Izadi, Sameh Khamis

At the coarsest resolution, and in a manner similar to classical part-based approaches, we leverage the kinematic structure of the human body to propagate convolutional feature updates between the keypoints or body parts.

Pose Estimation

Volumetric Capture of Humans with a Single RGBD Camera via Semi-Parametric Learning

no code implementations CVPR 2019 Rohit Pandey, Anastasia Tkach, Shuoran Yang, Pavel Pidlypenskyi, Jonathan Taylor, Ricardo Martin-Brualla, Andrea Tagliasacchi, George Papandreou, Philip Davidson, Cem Keskin, Shahram Izadi, Sean Fanello

The key insight is to leverage previously seen "calibration" images of a given user to extrapolate what should be rendered in a novel viewpoint from the data available in the sensor.

LookinGood: Enhancing Performance Capture with Real-time Neural Re-Rendering

no code implementations12 Nov 2018 Ricardo Martin-Brualla, Rohit Pandey, Shuoran Yang, Pavel Pidlypenskyi, Jonathan Taylor, Julien Valentin, Sameh Khamis, Philip Davidson, Anastasia Tkach, Peter Lincoln, Adarsh Kowdle, Christoph Rhemann, Dan B. Goldman, Cem Keskin, Steve Seitz, Shahram Izadi, Sean Fanello

We take the novel approach to augment such real-time performance capture systems with a deep architecture that takes a rendering from an arbitrary viewpoint, and jointly performs completion, super resolution, and denoising of the imagery in real-time.

Denoising Super-Resolution

SplineNets: Continuous Neural Decision Graphs

no code implementations NeurIPS 2018 Cem Keskin, Shahram Izadi

We present SplineNets, a practical and novel approach for using conditioning in convolutional neural networks (CNNs).


Conditional Information Gain Networks

no code implementations25 Jul 2018 Ufuk Can Biçici, Cem Keskin, Lale Akarun

These decision mechanisms are trained using cost functions based on differentiable Information Gain, inspired by the training procedures of decision trees.

General Classification

Opening the Black Box: Hierarchical Sampling Optimization for Estimating Human Hand Pose

no code implementations ICCV 2015 Danhang Tang, Jonathan Taylor, Pushmeet Kohli, Cem Keskin, Tae-Kyun Kim, Jamie Shotton

In this paper, we show that we can significantly improving upon black box optimization by exploiting high-level knowledge of the structure of the parameters and using a local surrogate energy function.

Hand Pose Estimation Image Generation

Computationally Bounded Retrieval

no code implementations CVPR 2015 Mohammad Rastegari, Cem Keskin, Pushmeet Kohli, Shahram Izadi

We demonstrate this technique on large retrieval databases, specifically ImageNET, GIST1M and SUN-attribute for the task of nearest neighbor retrieval, and show that our method achieves a speed-up of up to a factor of 100 over state-of-the-art methods, while having on-par and in some cases even better accuracy.

Attribute Image Retrieval +1

Learning an Efficient Model of Hand Shape Variation From Depth Images

no code implementations CVPR 2015 Sameh Khamis, Jonathan Taylor, Jamie Shotton, Cem Keskin, Shahram Izadi, Andrew Fitzgibbon

We represent the observed surface using Loop subdivision of a control mesh that is deformed by our learned parametric shape and pose model.

Filter Forests for Learning Data-Dependent Convolutional Kernels

no code implementations CVPR 2014 Sean Ryan Fanello, Cem Keskin, Pushmeet Kohli, Shahram Izadi, Jamie Shotton, Antonio Criminisi, Ugo Pattacini, Tim Paek

We propose 'filter forests' (FF), an efficient new discriminative approach for predicting continuous variables given a signal and its context.


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