相关论文: PoseVocab: Learning Joint-structured Pose Embeddin…

We propose a novel neural rendering pipeline, Hybrid Volumetric-Textural Rendering (HVTR), which synthesizes virtual human avatars from arbitrary poses efficiently and at high quality. First, we learn to encode articulated human motions on…

Most current action recognition methods heavily rely on appearance information by taking an RGB sequence of entire image regions as input. While being effective in exploiting contextual information around humans, e.g., human appearance and…

It is now possible to reconstruct dynamic human motion and shape from a sparse set of cameras using Neural Radiance Fields (NeRF) driven by an underlying skeleton. However, a challenge remains to model the deformation of cloth and skin in…

We seek to extract a temporally consistent 6D pose trajectory of a manipulated object from an Internet instructional video. This is a challenging set-up for current 6D pose estimation methods due to uncontrolled capturing conditions, subtle…

In this work, we propose a novel and efficient method for articulated human pose estimation in videos using a convolutional network architecture, which incorporates both color and motion features. We propose a new human body pose dataset,…

Video-driven 3D facial animation transfer aims to drive avatars to reproduce the expressions of actors. Existing methods have achieved remarkable results by constraining both geometric and perceptual consistency. However, geometric…

By leveraging temporal dependency in video sequences, multi-frame human pose estimation algorithms have demonstrated remarkable results in complicated situations, such as occlusion, motion blur, and video defocus. These algorithms are…

There has been significant progress in machine learning algorithms for human pose estimation that may provide immense value in rehabilitation and movement sciences. However, there remain several challenges to routine use of these tools for…

The attention mechanism provides a sequential prediction framework for learning spatial models with enhanced implicit temporal consistency. In this work, we show a systematic design (from 2D to 3D) for how conventional networks and other…

We present Better Together, a method that simultaneously solves the human pose estimation problem while reconstructing a photorealistic 3D human avatar from multi-view videos. While prior art usually solves these problems separately, we…

3D human pose estimation captures the human joint points in three-dimensional space while keeping the depth information and physical structure. That is essential for applications that require precise pose information, such as human-computer…

Reconstructing photo-realistic drivable human avatars from multi-view image sequences has been a popular and challenging topic in the field of computer vision and graphics. While existing NeRF-based methods can achieve high-quality novel…

Real-world scenes are inherently crowded. Hence, estimating 3D poses of all nearby humans, tracking their movements over time, and understanding their activities within social and environmental contexts are essential for many applications,…

A key technical challenge in performing 6D object pose estimation from RGB-D image is to fully leverage the two complementary data sources. Prior works either extract information from the RGB image and depth separately or use costly…

Deep ConvNets have been shown to be effective for the task of human pose estimation from single images. However, several challenging issues arise in the video-based case such as self-occlusion, motion blur, and uncommon poses with few or no…

Pedestrian misalignment, which mainly arises from detector errors and pose variations, is a critical problem for a robust person re-identification (re-ID) system. With bad alignment, the background noise will significantly compromise the…

We propose a de-identification pipeline that protects the privacy of humans in video sequences by replacing them with rendered 3D human models, hence concealing their identity while retaining the naturalness of the scene. The original…

Object pose estimation plays a vital role in mixed-reality interactions when users manipulate tangible objects as controllers. Traditional vision-based object pose estimation methods leverage 3D reconstruction to synthesize training data.…

Recent work on human animation usually involves audio, pose, or movement maps conditions, thereby achieves vivid animation quality. However, these methods often face practical challenges due to extra control conditions, cumbersome condition…

We present a multimodal learning-based method to simultaneously synthesize co-speech facial expressions and upper-body gestures for digital characters using RGB video data captured using commodity cameras. Our approach learns from sparse…