Search Results for author:
Found 26 papers, 4 papers with code
EgoPoseFormer: A Simple Baseline for Egocentric 3D Human Pose Estimation
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.
FoundPose: Unseen Object Pose Estimation with Foundation Features
Pose hypotheses are then generated from 2D-3D correspondences established by matching DINOv2 patch features between the query image and a retrieved template, and finally optimized by featuremetric refinement.
AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation
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.
MotionDeltaCNN: Sparse CNN Inference of Frame Differences in Moving Camera Videos with Spherical Buffers and Padded Convolutions
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.
Social Diffusion: Long-term Multiple Human Motion Anticipation
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.
In-Hand 3D Object Scanning from an RGB Sequence
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
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
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
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.
DeltaCNN: End-to-End CNN Inference of Sparse Frame Differences in Videos
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
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.
Multiresolution Deep Implicit Functions for 3D Shape Representation
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.
HumanGPS: Geodesic PreServing Feature for Dense Human Correspondences
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
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.
Deep Implicit Volume Compression
We describe a novel approach for compressing truncated signed distance fields (TSDF) stored in 3D voxel grids, and their corresponding textures.
RePose: Learning Deep Kinematic Priors for Fast Human Pose Estimation
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.
Volumetric Capture of Humans with a Single RGBD Camera via Semi-Parametric Learning
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
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.
SplineNets: Continuous Neural Decision Graphs
We present SplineNets, a practical and novel approach for using conditioning in convolutional neural networks (CNNs).
Conditional Information Gain Networks
These decision mechanisms are trained using cost functions based on differentiable Information Gain, inspired by the training procedures of decision trees.
Learning to Navigate the Energy Landscape
We demonstrate the efficacy of our approach on the challenging problem of RGB Camera Relocalization.
Opening the Black Box: Hierarchical Sampling Optimization for Estimating Human Hand Pose
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.
Computationally Bounded Retrieval
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.
Learning an Efficient Model of Hand Shape Variation From Depth Images
We represent the observed surface using Loop subdivision of a control mesh that is deformed by our learned parametric shape and pose model.
User-Specific Hand Modeling from Monocular Depth Sequences
We focus on modeling the human hand, and assume that a single rough template model is available.
Filter Forests for Learning Data-Dependent Convolutional Kernels
We propose 'filter forests' (FF), an efficient new discriminative approach for predicting continuous variables given a signal and its context.
