Chunan Yu's homepage

I'm a PhD student in the Knowledge Mining Group (KMG) at Nanjing University of Science and Technology, under the supervision of Professor Yang Yang and Associate Professor Qingyuan Jiang. I received my Master's degree from Huzhou University in 2025 and my Bachelor's degree from Linyi University in 2022. My current research interests include computer vision and multimodal learning, with a particular focus on 3D reconstruction and multimodal imbalance. If you have any questions, you can contact me by yuchun_an@njust.edu.cn.

News

[2026.01.29] One paper is accepted in IEEE TVCG.

[2025.07.26] One paper is accepted in IEEE TVCG.

[2025.06.23] One paper is accepted in IEEE TII.

[2025.05.10] Awarded Zhejiang Province Outstanding Graduate.

[2025.03.05] One paper is accepted in Reasoning and Planning for LLMs @ ICLR2025.

[2024.12.10] Received the National Scholarship for Master's Students.

[2024.02.27] One paper is accepted in CVPR (Highlight).

[2023.12.14] One paper is accepted in ICASSP.

Publications

* Equal contribution † Corresponding author

TVCG
From Sketch to Reality: Enabling High-Quality, Cross-Category 3D Model Generation from Free-Hand Sketches with Minimal Data.

Ying Zang*, Chunan Yu*, Jiahao Zhang, Jing Li, Shengyuan Zhang, Lanyun Zhu, Chaotao Ding, Renjun Xu, Tianrun Chen^†

IEEE Trans. Vis. Comput. Graph (TVCG), 2026.

Paper

This paper presents a novel approach for generating high-quality, cross-category 3D models from free-hand sketches with limited training data. We propose the first semi-supervised learning method to our knowledge for sketch-to-3D model conversion. Innovatively, we design a coarse-to-fine pipeline to perform the semi-supervised learning in the coarse stage and train a diffusion-based refiner to get a high-resolution 3D model. We designed a sketch-augmentation method for semi-supervised learning and integrated priors such as CLIP loss, shape prototypes, and adversarial loss to help generate high-quality results even with abstract and imprecise sketches. We also introduce an innovative procedural 3D generation method based on CAD code, which helps pre-train part of the network before fine-tuning with limited real data. Our approach, coupled with a specifically designed curriculum learning, allows us to generate high-quality 3D models across multiple categories with as few as 300 sketch-3D model pairs, marking a significant advancement over previous single-category approaches. In addition, we introduce the KO2D dataset, the largest collection of hand-drawn sketch-3D pairs to support further research in this area. As sketches are a far more intuitive and detailed way for users to express their unique ideas, we believe that this paper can move us closer to democratizing 3D content creation, enabling anyone to transform their ideas into 3D models effortlessly
```
@article{DBLP:journals/tvcg/ZangYZLZZDXC26,
  author       = {Ying Zang and
                  Chunan Yu and
                  Jiahao Zhang and
                  Jing Li and
                  Shengyuan Zhang and
                  Lanyun Zhu and
                  Chaotao Ding and
                  Renjun Xu and
                  Tianrun Chen},
  title        = {From Sketch to Reality: Enabling High-Quality, Cross-Category 3D Model Generation from 
                  Free-Hand Sketches with Minimal Data},
  journal      = {{IEEE} Trans. Vis. Comput. Graph.},
  year         = {2026},
}
```
TII
Img2CAD: Conditioned 3D CAD Model Generation from Single Image with Structured Visual Geometry

Tianrun Chen*, Chunan Yu*, Yuanqi Hu, Jing Li, Tao Xu, Runlong Cao, Lanyun Zhu, Ying Zang^†, Yong Zhang, Zejian Li, Lingyun Sun

IEEE Trans. Ind. Informatics (TII), 2025.

Paper

In this paper, we propose Img2CAD, the first approach to our knowledge that uses 2D image inputs to generate CAD models with editable parameters. Unlike existing AI methods for 3D model generation using text or image inputs often rely on mesh-based representations, which are incompatible with CAD tools and lack editability and fine control, Img2CAD enables seamless integration between AI-based 3D reconstruction and CAD software. We have identified an innovative intermediate representation called Structured Visual Geometry (SVG), characterized by vectorized wireframes extracted from objects. This representation significantly enhances the performance of generating conditioned CAD models. Additionally, we introduce two new datasets to further support research in this area: ABC-mono, the largest known dataset comprising over 200,000 3D CAD models with rendered images, and KOCAD, the first dataset featuring real-world captured objects alongside their ground truth CAD models, supporting further research in conditioned CAD model generation.
```
@article{DBLP:journals/tii/ChenYHLXCZZZLS25,
  author       = {Tianrun Chen and
                  Chunan Yu and
                  Yuanqi Hu and
                  Jing Li and
                  Tao Xu and
                  Runlong Cao and
                  Lanyun Zhu and
                  Ying Zang and
                  Yong Zhang and
                  Zejian Li and
                  Linyun Sun},
  title       = {Img2CAD: Conditioned 3D {CAD} Model Generation from Single Image with
                  Structured Visual Geometry},
  journal      = {{IEEE} Trans. Ind. Informatics},
  year         = {2025}
  }
```
TVCG
From Air to Wear: Personalized 3D Digital Fashion with AR/VR Immersive 3D Sketching

Ying Zang, Yuanqi Hu, Xinyu Chen, Suhui Wang, Yuxia Xu, Chunan Yu, Lanyun Zhu, Deyi Ji, Xin Xu, Tianrun Chen^†

IEEE Trans. Vis. Comput. Graph (TVCG), 2025.

Paper

In the era of immersive consumer electronics, such as AR/VR headsets and smart devices, people increasingly seek ways to express their identity through virtual fashion. However, existing 3D garment design tools remain inaccessible to everyday users due to steep technical barriers and limited data. In this work, we introduce a 3D sketch-driven 3D garment generation framework that empowers ordinary users — even those without design experience — to create high-quality digital clothing through simple 3D sketches in AR/VR environments. By combining a conditional diffusion model, a sketch encoder trained in a shared latent space, and an adaptive curriculum learning strategy, our system interprets imprecise, free-hand input and produces realistic, personalized garments. To address the scarcity of training data, we also introduce KO3DClothes, a new dataset of paired 3D garments and user-created sketches. Extensive experiments and user studies confirm that our method significantly outperforms existing baselines in both fidelity and usability, demonstrating its promise for democratized fashion design on next-generation consumer platforms.
```
@article{DBLP:journals/tvcg/ZangHCWXYZJXC25,
  author       = {Ying Zang and
                  Yuanqi Hu and
                  Xinyu Chen and
                  Suhui Wang and
                  Yuxia Xu and
                  Chunan Yu and
                  Lanyun Zhu and
                  Deyi Ji and
                  Xin Xu and
                  Tianrun Chen},
  title        = {From Air to Wear: Personalized 3D Digital Fashion With {AR/VR} Immersive
                  3D Sketching},
  journal      = {{IEEE} Trans. Vis. Comput. Graph.},
  volume       = {31},
  number       = {12},
  pages        = {10227--10236},
  year         = {2025},
}
```
ICLR Workshop
Reasoning3D - Grounding and Reasoning in 3D: Fine-Grained Zero-Shot Open-Vocabulary 3D Reasoning Part Segmentation via Large Vision-Language Models

Tianrun Chen*, Chunan Yu*, Jing Li, Jianqi Zhang, Lanyun Zhu, Deyi Ji, Yong Zhang, Ying Zang^†, Zejian Li, Lingyun Sun

ICLR Workshop LLM Reason and Plan. 2025

Paper

In this paper, we introduce a new task: Zero-Shot 3D Reasoning Segmentation for parts searching and localization for objects, which is a new paradigm to 3D segmentation that transcends limitations for previous category-specific 3D semantic segmentation, 3D instance segmentation, and open-vocabulary 3D segmentation. We design a simple baseline method, Reasoning3D, with the capability to understand and execute complex commands for (fine-grained) segmenting specific parts for 3D meshes with contextual awareness and reasoned answers for interactive segmentation. Specifically, Reasoning3D leverages an off-the-shelf pre-trained 2D segmentation network, powered by Large Language Models (LLMs), to interpret user input queries in a zero-shot manner. Previous research has shown that extensive pre-training endows foundation models with prior world knowledge, enabling them to comprehend complex commands, a capability we can harness to "segment anything" in 3D with limited 3D datasets (source efficient). Experimentation reveals that our approach is generalizable and can effectively localize and highlight parts of 3D objects (in 3D mesh) based on implicit textual queries, including these articulated 3D objects and real-world scanned data. Our method can also generate natural language explanations corresponding to these 3D models and the decomposition. Moreover, our training-free approach allows rapid deployment and serves as a viable universal baseline for future research of part-level 3D (semantic) object understanding in various fields including robotics, object manipulation, part assembly, autonomous driving applications, augmented reality and virtual reality (AR/VR), and medical applications. The code and the user interface have been released publicly.
```
@article{DBLP:journals/iclr/ChenYLZZJZZLS25,
  author       = {Tianrun Chen and
                  Chunan Yu and
                  Jing Li and
                  Jianqi Zhang and
                  Lanyun Zhu and
                  Deyi Ji and
                  Yong Zhang and
                  Ying Zang and
                  Zejian Li and
                  Lingyun Sun},
  title        = {Reasoning3D - Grounding and Reasoning in 3D: Fine-Grained Zero-Shot
                  Open-Vocabulary 3D Reasoning Part Segmentation via Large Vision-Language
                  Models},
  booktitle      = {ICLR 2025 Workshop LLM Reason and Plan},
  year         = {2024},
}
```
CVPR
Rapid 3d model generation with intuitive 3d input

Tianrun Chen, Chaotao Ding, Shangzhan Zhang, Chunan Yu, Ying Zang^†, Zejian Li^†, Sida Peng, Lingyun Sun^†

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.

Paper

With the emergence of AR/VR, 3D models are in tremendous demand. However, conventional 3D modeling with Computer-Aided Design software requires much expertise and is difficult for novice users. We find that AR/VR devices, in addition to serving as effective display mediums, can offer a promising potential as an intuitive 3D model creation tool, especially with the assistance of AI generative models. Here, we propose Deep3DVRSketch, the first 3D model generation network that inputs 3D VR sketches from novice users and generates highly consistent 3D models in multiple categories within seconds, irrespective of the users’ drawing abilities. We also contribute KO3D+, the largest 3D sketch-shape dataset. Our method pre-trains a conditional diffusion model on quality 3D data, then finetunes an encoder to map 3D sketches onto the generator’s manifold using an adaptive curriculum strategy for limited ground truths. In our experiment, our approach achieves state-of-the-art performance in both model quality and fidelity with real-world input from novice users, and users can even draw and obtain very detailed geometric structures. In our user study, users were able to complete the 3D modeling tasks over 10 times faster using our approach compared to conventional CAD software tools. We believe that our Deep3DVRSketch and KO3D+ dataset can offer a promising solution for future 3D modeling in metaverse era.
```
@inproceedings{DBLP:conf/cvpr/ChenDZYZLPS24,
  author       = {Tianrun Chen and
                  Chaotao Ding and
                  Shangzhan Zhang and
                  Chunan Yu and
                  Ying Zang and
                  Zejian Li and
                  Sida Peng and
                  Lingyun Sun},
  title        = {Rapid 3D Model Generation with Intuitive 3D Input},
  booktitle    = {{IEEE/CVF} Conference on Computer Vision and Pattern Recognition,
                  {CVPR} 2024, Seattle, WA, USA, June 16-22, 2024},
  pages        = {12554--12564},
  publisher    = {{IEEE}},
  year         = {2024},
}
```
ICASSP
Spatio-Temporal Action Detection with a Motion Sense and Semantic Correction Framework

Yong Zhang, Chunan Yu, Chenglong Fu, Yuanqi Hu, Ying Zang^†

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024.

Paper

Accurately distinguishing between action-related features and nonaction-related features is crucial in spatio-temporal action detection tasks. Additionally, the calibration and fusion of information across different modalities remain challenging. This paper proposes a novel Motion Sense and Semantic Correction framework (MS-SC) to address these issues. The MS-SC framework achieves accurate detection by fusing features from images (spatial dimension) and videos (spatio-temporal dimension). A Motion Sense Module (MSM) is proposed to significantly increase the feature distance between action and non-action features in the semantic space, enhancing feature discriminability. Considering the complementary nature of information across different modalities, an efficient Semantic Correction Fusion Module (SFM) is introduced to facilitate interaction between features of distinct modalities and maximize their complementary information integration. To evaluate the performance of the MSSC framework, extensive experiments were conducted on two challenging datasets, UCF101-24 and AVA. The results demonstrate the effectiveness of the MS-SC framework in handling spatio-temporal action detection tasks.
```
@inproceedings{DBLP:conf/icassp/ZhangY0HZ24,
  author       = {Yong Zhang and
                  Chunan Yu and
                  Chenglong Fu and
                  Yuanqi Hu and
                  Ying Zang},
  title        = {Spatio-Temporal Action Detection with a Motion Sense and Semantic
                  Correction Framework},
  booktitle    = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
                  {ICASSP} 2024, Seoul, Republic of Korea, April 14-19, 2024},
  pages        = {3645--3649},
  publisher    = {{IEEE}},
  year         = {2024},
}
```

Service

Reviewer of CVPR, ECCV, IJCAI, AAAI, ICME etc.