Jingxiang Sun (孙景翔)

Email: sunjingxiang_stark[at]126.com      Google Scholar     Github     Twitter     Youtube

I am a second-year PhD student of Department of Automation, Tsinghua University in fall, 2022 and under the supervision of Prof. Yebin Liu. Prior to Tsinghua University I obtained M.S. from Department of ECE, University of Illinois at Urbana-Champaign. My research focuses on neural rendering, digital avatar and 3D generation.

I am very fortunate to have spent summer 2021 at Tencent AI Lab with Xuan Wang and Jue Wang; fall 2020 at State Key Laboratory of CAD&CG at Zhejiang University with Xiaowei Zhou.

2024-10: We introduce DreamCraft3D++, a new technique for high-quality 3D content generation!
2024-08: One paper is accepted by SIGGRAPH ASIA 2024!
2024-03: One paper is accepted by SIGGRAPH 2024!
2024-02: Two papers are accepted by CVPR 2024!
2024-02: Start my internship at NVIDIA Research with Koki Nagano and Shalini De Mello.
2024-01: DreamCraft3D is accepted at ICLR 2024. See you in Vienna!
2023-09: HAvatar is accepted by ACM TOG 2023.
2023-03: StyleAvatar is accepted by ACM SIGGRAPH 2023.
2023-03: Next3D is selected as CVPR Highlight papers (10% of accepted papers, 2.5% of submissions).

We present DreamCraft3D++, an extension of DreamCraft3D that enables efficient high-quality generation of complex 3D assets in 10 minutes.

Given a reference image, SMPL sequences and camera parameters, our method is capable of generating free-view dynamic human videos.

We present DreamCraft3D, a hierarchical 3D content generation method that produces high-fidelity and coherent 3D object.

We present the Incremental 3D GAN Inversion, which efficiently reconstructs photorealistic 3D facial avatars in under 1s, using single or multiple source images.

We propose Control4D, an approach to high-fidelity and spatiotemporal-consistent 4D portrait editing with only text instructions.

We present RAM-Avatar, a real-time photo-realistic human avatar learning method based on monocular videos, which not only achieves high-fidelity rendering with full-body control including the face and hands but also supports real-time animation.

We present VectorTalker, a novel method for creating high-fidelity, audio-driven talking heads using scalable vector graphics, effective for various image styles.

We introduce the Facial Model Conditioned Neural Radiance Field, a hybrid 3D representation method that merges NeRF's expressiveness with parametric template data, enabling topological flexibility through synthetic-renderings-based conditioning.

We propose StyleAvatar, a real-time photo-realistic portrait avatar reconstruction method using StyleGAN-based networks, which can generate high-fidelity portrait avatars with faithful expression control.

We propose a novel 3D GAN framework for unsupervised learning of generative, high-quality and 3D-consistent facial avatars from unstructured 2D images. To achieve both deformation accuracy and topological flexibility, we present a 3D representation called Generative Texture-Rasterized Tri-planes.

We propose an efficient method to construct the personalized generative prior based on a small set of facial images of a given individual. After learning, it allows for photo-realistic rendering with novel views and the face reenactment can be realized by performing navigation in the latent space. Our proposed method is applicable for different driven signals, including RGB images, 3DMM coefficients, and audios.

We propose DiffuStereo, a novel system using only sparse cameras (8 in this work) for high-quality 3D human reconstruction. At its core is a novel diffusion-based stereo module, which introduces diffusion models, a type of powerful generative models, into the iterative stereo matching network.

We propose a high-resolution 3D-aware generative model that not only enables local control of the facial shape and texture, but also supports real-time, interactive editing.

We propose FENeRF, a 3D-aware generator that can produce view-consistent and locally-editable portrait images. Our method uses two decoupled latent codes to generate corresponding facial semantics and texture in a spatial aligned 3D volume with shared geometry. We also reveal that joint learning semantics and texture helps to generate finer geometry.

We propose a novel optimization-based framework and experimentally demonstrate its ability to recover much more precise and detailed motion from multiple videos, compared against monocular pose estimation methods.

We propose a general and practical evaluation framework for analysing various widely used prediction models (i.e. delay, k- nearest-neighbor, kernel regression, additive model, and recur- rent neural network using long short term memory) for bus arrival time.

Introducing DeepSeek-VL, an open-source Vision-Language (VL) Model designed for real-world vision and language understanding applications.

The website template was adapted from Yu Deng.