11 papers
ReliCAD: From Uncertain LLM Generation to Reliable Parametric CAD Modeling
Peng Zheng, Xintong Dong, Chuanyang Li +5
Large language models have shown considerable potential for natural-language-driven parametric CAD modeling. However, a fundamental contradiction exists between their probabilistic…
CopyCat: Improving Fine-Grained Subject Consistency in Subject-to-Image Models within Seconds
Peng Zheng, Ruiqi Liu, Rui Ma +1
Recent subject-to-image models have achieved impressive progress in personalized image generation, yet they still struggle to preserve fine-grained subject-specific details. A majo…
HistCAD: Constraint-Aware Parametric CAD Histories for Evaluating Editability
Xintong Dong, Chuanyang Li, Peng Zheng +5
Sketch constraints specify geometric conditions for constructing and modifying parametric CAD models. We study whether predicted constraints allow a given history to reproduce the…
OmniStyle2: Learning to Stylize by Learning to Destylize
Ye Wang, Zili Yi, Yibo Zhang +6
This paper introduces a scalable paradigm for supervised style transfer by inverting the problem: instead of learning to stylize directly, we learn to destylize, reducing stylistic…
Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis
Peng Zheng, Junke Wang, Yi Chang +3
Recent advances in large language models (LLMs) have spurred interests in encoding images as discrete tokens and leveraging autoregressive (AR) frameworks for visual generation. Ho…
FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization
Peng Zheng, Ye Wang, Rui Ma +1
Subject-driven image generation plays a crucial role in applications such as virtual try-on and poster design. Existing approaches typically fine-tune pretrained generative models…
SuperNeRF-GAN: A Universal 3D-Consistent Super-Resolution Framework for Efficient and Enhanced 3D-Aware Image Synthesis
Peng Zheng, Linzhi Huang, Yizhou Yu +3
Neural volume rendering techniques, such as NeRF, have revolutionized 3D-aware image synthesis by enabling the generation of images of a single scene or object from various camera…
D-Aug: Enhancing Data Augmentation for Dynamic LiDAR Scenes
Jiaxing Zhao, Peng Zheng, Rui Ma
Creating large LiDAR datasets with pixel-level labeling poses significant challenges. While numerous data augmentation methods have been developed to reduce the reliance on manual…
SemanticHuman-HD: High-Resolution Semantic Disentangled 3D Human Generation
Peng Zheng, Tao Liu, Zili Yi +1
With the development of neural radiance fields and generative models, numerous methods have been proposed for learning 3D human generation from 2D images. These methods allow contr…
TaylorGrid: Towards Fast and High-Quality Implicit Field Learning via Direct Taylor-based Grid Optimization
Renyi Mao, Qingshan Xu, Peng Zheng +3
Coordinate-based neural implicit representation or implicit fields have been widely studied for 3D geometry representation or novel view synthesis. Recently, a series of efforts ha…
3D-SSGAN: Lifting 2D Semantics for 3D-Aware Compositional Portrait Synthesis
Ruiqi Liu, Peng Zheng, Ye Wang +1
Existing 3D-aware portrait synthesis methods can generate impressive high-quality images while preserving strong 3D consistency. However, most of them cannot support the fine-grain…