Chao Liu

Introducing DINOv2 for Medical Image Boundary Tracking

Jing Chen, Gangming Zhao, Jun Wu, Chong Tian et autres

cn, bd (code pays fourni par la source)

Coherent 3D Portrait Video Reconstruction via Triplane Fusion

Shengze Wang, Xueting Li, Chao Liu, Matthew Chan et autres

Recent breakthroughs in single-image 3D portrait reconstruction have enabled telepresence systems to stream 3D portrait videos from a single camera in real-time, democratizing telepresence. However, per-frame 3D reconstruction exhibits temporal inconsistency and forgets the user’s appearance. On the other hand, self-reenactment methods …

us (code pays fourni par la source)

Compositional Text-to-Image Generation with Feedforward Layout Generation

Sifei Liu, Weili Nie, An‐Chieh Cheng, Morteza Mardani et autres

us (code pays fourni par la source)

Coherent3D: Coherent 3D Portrait Video Reconstruction via Triplane Fusion

Shengze Wang, Xueting Li, Chao Liu, Matthew Chan et autres

Recent breakthroughs in single-image 3D portrait reconstruction have enabled telepresence systems to stream 3D portrait videos from a single camera in real-time, democratizing telepresence. However, per-frame 3D reconstruction exhibits temporal inconsistency and forgets the user's appearance. On the other hand, self-reenactment methods …

BlobGEN-3D: Compositional 3D-Consistent Freeview Image Generation with 3D Blobs

Chao Liu, Weili Nie, Sifei Liu, Abhishek Badki et autres

us (code pays fourni par la source)

Coherent 3D Portrait Video Reconstruction via Triplane Fusion

Shengze Wang, Xueting Li, Chao Liu, Matthew Chan et autres

Recent breakthroughs in single-image 3D portrait reconstruction have enabled telepresence systems to stream 3D portrait videos from a single camera in real-time, potentially democratizing telepresence. However, per-frame 3D reconstruction exhibits temporal inconsistency and forgets the user's appearance. On the other hand, self-reenactment …

HARFMR: Human Activity Recognition with Feature Masking and Reconstruction

Wenxuan Cui, Yingjie Chen, Yong Qing Huang, Chao Liu et autres

cn (code pays fourni par la source)

AI-Mediated 3D Video Conferencing

Michael Stengel, Koki Nagano, Chao Liu, Matthew Chan et autres

We present an AI-mediated 3D video conferencing system that can reconstruct and autostereoscopically display a life-sized talking head using consumer-grade compute resources and minimal capture equipment. Our 3D capture uses a novel 3D lifting method that encodes a given 2D input into …

us (code pays fourni par la source)

Real-Time Radiance Fields for Single-Image Portrait View Synthesis

Alex Trevithick, Matthew Chan, Michael Stengel, Eric R. Chan et autres

We present a one-shot method to infer and render a photorealistic 3D representation from a single unposed image (e.g., face portrait) in real-time. Given a single RGB input, our image encoder directly predicts a canonical triplane representation of a neural radiance field …

us (code pays fourni par la source)

Real-Time Radiance Fields for Single-Image Portrait View Synthesis

Alex Trevithick, Matthew Chan, Michael Stengel, Eric R. Chan et autres

We present a one-shot method to infer and render a photorealistic 3D representation from a single unposed image (e.g., face portrait) in real-time. Given a single RGB input, our image encoder directly predicts a canonical triplane representation of a neural radiance field …

Alpha-SGANet: A multi-attention-scale feature pyramid network combined with lightweight network based on Alpha-IoU loss

Hong Li, Qian Zhou, Yao Mao, Bing Zhang et autres

The design of deep convolutional neural networks has resulted in significant advances and successes in the field of object detection. However, despite these achievements, the high computational and memory costs of such object detection networks on the edge or in mobile scenarios …

cn (code pays fourni par la source)

How do Plastic Surgeons use the Metaverse: A Systematic Review

Pengfei Sun, Shanbaga Zhao, Yang Yang, Chao Liu et autres

OBJECTIVE: In 2021, metaverse became a buzzword. The metaverse is a digital virtual world in which people can live as a digital virtual identity. In the metaverse, people can participate in making rules and create their own worlds. As plastic surgeons in …

cn (code pays fourni par la source)