Hao Zhu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Hao Zhu has a total of 92 co-authors. Here are the top co-authors by number of shared publications:
- Xun Cao
Nanjing University, Nanjing, China
9 shared publications Xun Cao
Nanjing University
4 shared publications- Siyu Zhu
Shanghai Innovation Institute, Shanghai, China and Fudan University, Shanghai, China
3 shared publications - Xinxin Zuo
Concordia University
3 shared publications - Yao Yao
Nanjing University, Suzhou, China
3 shared publications - Yiyu Zhuang
Nanjing University, Nanjing, China
3 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 4406-4415
Hallo-Live: Real-Time Streaming Joint Audio-Video Avatar Generation with Asynchronous Dual-Stream and Human-Centric Preference Distillation
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 4406-4415
Open AccessHallo-Live: Real-Time Streaming Joint Audio-Video Avatar Generation with Asynchronous Dual-Stream and Human-Centric Preference Distillation
- 1 October 2026
- Published by Springer Nature
- p. 521-538
DiGS-Avatar: Single-Image Animatable 3D Human Reconstruction via UV-Space Diffusion
- 1 October 2026
- Published by Springer Nature
- p. 521-538
DiGS-Avatar: Single-Image Animatable 3D Human Reconstruction via UV-Space Diffusion
- Open Access
- 1 February 2026
- Published by KEAI Publishing in Fundamental Research
Towards native generative model for 3D head avatar
- 1 February 2026
- Published by KEAI Publishing in Fundamental Research
Open AccessTowards native generative model for 3D head avatar
- Open Access
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Sketch2PoseNet: Efficient and Generalized Sketch to 3D Human Pose Prediction
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessSketch2PoseNet: Efficient and Generalized Sketch to 3D Human Pose Prediction
- 7 January 2025
- Published by Springer Nature in Machine Intelligence Research
- Vol. 22 (2) , 304-323
Learning Hierarchical Adaptive Code Clouds for Neural 3D Shape Representation
- 7 January 2025
- Published by Springer Nature in Machine Intelligence Research
- Vol. 22 (2) , 304-323
Learning Hierarchical Adaptive Code Clouds for Neural 3D Shape Representation
- Top Cited Papers
- 27 November 2024
- Published by Springer Nature
- p. 145-162
Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance
- 27 November 2024
- Published by Springer Nature
- p. 145-162
Top Cited PapersChamp: Controllable and Consistent Human Image Animation with 3D Parametric Guidance
- 30 October 2024
- Published by Springer Nature
- p. 254-272
Head360: Learning a Parametric 3D Full-Head for Free-View Synthesis in 360$^\circ $- 30 October 2024
- Published by Springer Nature
- p. 254-272
Head360: Learning a Parametric 3D Full-Head for Free-View Synthesis in 360$^\circ $- 30 September 2024
- Published by Springer Nature
- p. 55-72
EmoTalk3D: High-Fidelity Free-View Synthesis of Emotional 3D Talking Head
- 30 September 2024
- Published by Springer Nature
- p. 55-72
EmoTalk3D: High-Fidelity Free-View Synthesis of Emotional 3D Talking Head
- Open Access
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (7) , 7828-7836
A Pre-convolved Representation for Plug-and-Play Neural Illumination Fields
Recent advances in implicit neural representation have demonstrated the ability to recover detailed geometry and material from multi-view images. However, the use of simplified lighting models such as environment maps to represent non-distant illumination, or using a network to fit indirect light modeling without a solid basis, can lead to an undesirable decomposition between lighting and material. To address this, we propose a fully differentiable framework named Neural Illumination Fields (NeIF) that uses radiance fields as a lighting model to handle complex lighting in a physically based way. Together with integral lobe encoding for roughness-adaptive specular lobe and leveraging the pre-convolved background for accurate decomposition, the proposed method represents a significant step towards integrating physically based rendering into the NeRF representation. The experiments demonstrate the superior performance of novel-view rendering compared to previous works, and the capability to re-render objects under arbitrary NeRF-style environments opens up exciting possibilities for bridging the gap between virtual and real-world scenes.
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (7) , 7828-7836
Open AccessA Pre-convolved Representation for Plug-and-Play Neural Illumination Fields
Recent advances in implicit neural representation have demonstrated the ability to recover detailed geometry and material from multi-view images. However, the use of simplified lighting models such as environment maps to represent non-distant illumination, or using a network to fit indirect light modeling without a solid basis, can lead to an undesirable decomposition between lighting and material. To address this, we propose a fully differentiable framework named Neural Illumination Fields (NeIF) that uses radiance fields as a lighting model to handle complex lighting in a physically based way. Together with integral lobe encoding for roughness-adaptive specular lobe and leveraging the pre-convolved background for accurate decomposition, the proposed method represents a significant step towards integrating physically based rendering into the NeRF representation. The experiments demonstrate the superior performance of novel-view rendering compared to previous works, and the capability to re-render objects under arbitrary NeRF-style environments opens up exciting possibilities for bridging the gap between virtual and real-world scenes.
- 4 February 2024
- Published by Springer Nature
- p. 78-90
Explicit Composition of Neural Radiance Fields by Learning an Occlusion Field
- 4 February 2024
- Published by Springer Nature
- p. 78-90
Explicit Composition of Neural Radiance Fields by Learning an Occlusion Field