95 citations · 197 across the 25 of their papers we have counts for
27 papers
VoT: Vision-of-Thought for Unified Multimodal Representation Alignment
Jingxiang Sun, Chao Liao, Zhengxiong Luo +6
Current text-to-image systems typically employ a "text encoder plus diffusion decoder" paradigm, in which text semantics directly modulate continuous latent noise. Despite their su…
ARM: An AutoRegressive Large Multimodal Model with Unified Discrete Representations
Junke Wang, Xiao Wang, Jiacheng Pan +16
This paper introduces ARM, a discrete representation-based AutoRegressive Model that unifies image understanding, generation, and editing within a next-token prediction framework.…
MMCORE: MultiModal COnnection with Representation Aligned Latent Embeddings
Zijie Li, Yichun Shi, Jingxiang Sun +8
We present MMCORE, a unified framework designed for multimodal image generation and editing. MMCORE leverages a pre-trained Vision-Language Model (VLM) to predict semantic visual e…
GeoDiff4D: Geometry-Aware Diffusion for 4D Head Avatar Reconstruction
Chao Xu, Xiaochen Zhao, Xiang Deng +4
Reconstructing photorealistic and animatable 4D head avatars from a single portrait image remains a fundamental challenge in computer vision. While diffusion models have enabled re…
VTok: A Unified Video Tokenizer with Decoupled Spatial-Temporal Latents
Feng Wang, Yichun Shi, Ceyuan Yang +4
This work presents VTok, a unified video tokenization framework that can be used for both generation and understanding tasks. Unlike the leading vision-language systems that tokeni…
FlexAvatar: Flexible Large Reconstruction Model for Animatable Gaussian Head Avatars with Detailed Deformation
Cheng Peng, Zhuo Su, Liao Wang +7
We present FlexAvatar, a flexible large reconstruction model for high-fidelity 3D head avatars with detailed dynamic deformation from single or sparse images, without requiring cam…
GeoSAM2: Unleashing the Power of SAM2 for 3D Part Segmentation
Ken Deng, Yunhan Yang, Jingxiang Sun +4
We introduce GeoSAM2, a prompt-controllable framework for 3D part segmentation that casts the task as multi-view 2D mask prediction. Given a textureless object, we render normal an…
MoReMouse: Monocular Reconstruction of Laboratory Mouse
Yuan Zhong, Jingxiang Sun, Zhongbin Zhang +2
Laboratory mice, particularly the C57BL/6 strain, are essential animal models in biomedical research. However, accurate 3D surface motion reconstruction of mice remains a significa…
SemanticSplat: Feed-Forward 3D Scene Understanding with Language-Aware Gaussian Fields
Qijing Li, Jingxiang Sun, Liang An +3
Holistic 3D scene understanding, which jointly models geometry, appearance, and semantics, is crucial for applications like augmented reality and robotic interaction. Existing feed…
Parametric Gaussian Human Model: Generalizable Prior for Efficient and Realistic Human Avatar Modeling
Cheng Peng, Jingxiang Sun, Yushuo Chen +3
Photorealistic and animatable human avatars are a key enabler for virtual/augmented reality, telepresence, and digital entertainment. While recent advances in 3D Gaussian Splatting…
DetailGen3D: Generative 3D Geometry Enhancement via Data-Dependent Flow
Ken Deng, Yuan-Chen Guo, Jingxiang Sun +6
Modern 3D generation methods can rapidly create shapes from sparse or single views, but their outputs often lack geometric detail due to computational constraints. We present Detai…
DreamCraft3D++: Efficient Hierarchical 3D Generation with Multi-Plane Reconstruction Model
Jingxiang Sun, Cheng Peng, Ruizhi Shao +6
We introduce DreamCraft3D++, an extension of DreamCraft3D that enables efficient high-quality generation of complex 3D assets. DreamCraft3D++ inherits the multi-stage generation pr…
Human4DiT: 360-degree Human Video Generation with 4D Diffusion Transformer
Ruizhi Shao, Youxin Pang, Zerong Zheng +2
We present a novel approach for generating 360-degree high-quality, spatio-temporally coherent human videos from a single image. Our framework combines the strengths of diffusion t…
DeepSeek-VL: Towards Real-World Vision-Language Understanding
Haoyu Lu, Wen Liu, Bo Zhang +12
We present DeepSeek-VL, an open-source Vision-Language (VL) Model designed for real-world vision and language understanding applications. Our approach is structured around three ke…
DeepSeek LLM: Scaling Open-Source Language Models with Longtermism
DeepSeek-AI, :, Xiao Bi +85
The rapid development of open-source large language models (LLMs) has been truly remarkable. However, the scaling law described in previous literature presents varying conclusions,…
VectorTalker: SVG Talking Face Generation with Progressive Vectorisation
Hao Hu, Xuan Wang, Jingxiang Sun +3
High-fidelity and efficient audio-driven talking head generation has been a key research topic in computer graphics and computer vision. In this work, we study vector image based a…
InvertAvatar: Incremental GAN Inversion for Generalized Head Avatars
Xiaochen Zhao, Jingxiang Sun, Lizhen Wang +2
While high fidelity and efficiency are central to the creation of digital head avatars, recent methods relying on 2D or 3D generative models often experience limitations such as sh…
DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior
Jingxiang Sun, Bo Zhang, Ruizhi Shao +4
We present DreamCraft3D, a hierarchical 3D content generation method that produces high-fidelity and coherent 3D objects. We tackle the problem by leveraging a 2D reference image t…
HAvatar: High-fidelity Head Avatar via Facial Model Conditioned Neural Radiance Field
Xiaochen Zhao, Lizhen Wang, Jingxiang Sun +3
The problem of modeling an animatable 3D human head avatar under light-weight setups is of significant importance but has not been well solved. Existing 3D representations either p…
Control4D: Efficient 4D Portrait Editing with Text
Ruizhi Shao, Jingxiang Sun, Cheng Peng +4
We introduce Control4D, an innovative framework for editing dynamic 4D portraits using text instructions. Our method addresses the prevalent challenges in 4D editing, notably the i…
StyleAvatar: Real-time Photo-realistic Portrait Avatar from a Single Video
Lizhen Wang, Xiaochen Zhao, Jingxiang Sun +4
Face reenactment methods attempt to restore and re-animate portrait videos as realistically as possible. Existing methods face a dilemma in quality versus controllability: 2D GAN-b…
ITportrait: Image-Text Coupled 3D Portrait Domain Adaptation
Xiangwen Deng, Yufeng Wang, Yuanhao Cai +3
Domain adaptation of 3D portraits has gained more and more attention. However, the transfer mechanism of existing methods is mainly based on vision or language, which ignores the p…
High-fidelity Facial Avatar Reconstruction from Monocular Video with Generative Priors
Yunpeng Bai, Yanbo Fan, Xuan Wang +4
High-fidelity facial avatar reconstruction from a monocular video is a significant research problem in computer graphics and computer vision. Recently, Neural Radiance Field (NeRF)…
Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatars
Jingxiang Sun, Xuan Wang, Lizhen Wang +4
3D-aware generative adversarial networks (GANs) synthesize high-fidelity and multi-view-consistent facial images using only collections of single-view 2D imagery. Towards fine-grai…