Search Results for author: HaoYu Wu

Found 8 papers, 2 papers with code

VideoDPO: Omni-Preference Alignment for Video Diffusion Generation

no code implementations18 Dec 2024 Runtao Liu, HaoYu Wu, Zheng Ziqiang, Chen Wei, Yingqing He, Renjie Pi, Qifeng Chen

Unlike previous image alignment methods that focus solely on either (i) visual quality or (ii) semantic alignment between text and videos, we comprehensively consider both dimensions and construct a preference score accordingly, which we term the OmniScore.

Image Generation Text-to-Video Generation +1

MLI-NeRF: Multi-Light Intrinsic-Aware Neural Radiance Fields

1 code implementation26 Nov 2024 Yixiong Yang, Shilin Hu, HaoYu Wu, Ramon Baldrich, Dimitris Samaras, Maria Vanrell

By leveraging scene information provided by different light source positions complementing the multi-view information, we generate pseudo-label images for reflectance and shading to guide intrinsic image decomposition without the need for ground truth data.

Intrinsic Image Decomposition NeRF +1

Direct and Explicit 3D Generation from a Single Image

no code implementations17 Nov 2024 HaoYu Wu, Meher Gitika Karumuri, Chuhang Zou, Seungbae Bang, Yuelong Li, Dimitris Samaras, Sunil Hadap

Current image-to-3D approaches suffer from high computational costs and lack scalability for high-resolution outputs.

3D Generation Decoder +2

VGG-Tex: A Vivid Geometry-Guided Facial Texture Estimation Model for High Fidelity Monocular 3D Face Reconstruction

no code implementations15 Sep 2024 HaoYu Wu, Ziqiao Peng, Xukun Zhou, Yunfei Cheng, Jun He, Hongyan Liu, Zhaoxin Fan

Specifically, VGG-Tex includes a Facial Attributes Encoding Module, a Geometry-Guided Texture Generator, and a Visibility-Enhanced Texture Completion Module.

3D Face Reconstruction

Learning Relighting and Intrinsic Decomposition in Neural Radiance Fields

no code implementations16 Jun 2024 Yixiong Yang, Shilin Hu, HaoYu Wu, Ramon Baldrich, Dimitris Samaras, Maria Vanrell

The task of extracting intrinsic components, such as reflectance and shading, from neural radiance fields is of growing interest.

EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation

2 code implementations ICCV 2023 Ziqiao Peng, HaoYu Wu, Zhenbo Song, Hao Xu, Xiangyu Zhu, Jun He, Hongyan Liu, Zhaoxin Fan

Specifically, we introduce the emotion disentangling encoder (EDE) to disentangle the emotion and content in the speech by cross-reconstructed speech signals with different emotion labels.

3D Face Animation Decoder +1

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