Renjiao Yi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Renjiao Yi has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
- Chenyang Zhu
National University of Defense Technology (NUDT), Changsha, China
8 shared publications - Kai Xu
Institute of AI for Industries, Chinese Academy of Sciences, Nanjing, China
7 shared publications Kai Xu
Xiangjiang Laboratory, Changsha, China
3 shared publications- Kunlun He
Medical Big Data Research Center, Chinese PLA General Hospital
2 shared publications - Lintao Zheng
College of Computing, National University of Defense Technology, Changsha 410073, China
2 shared publications Xin Wen
College of Computer Science and Technology, National University of Defense Technology, Changsha, China
2 shared publications
Latest Publications
- 8 August 2026
- Published by Springer Nature in Frontiers of Computer Science
- Vol. 20 (9) , 2009713
From dark flash images to relightable 3D scenes with photometric stereo priors
- 8 August 2026
- Published by Springer Nature in Frontiers of Computer Science
- Vol. 20 (9) , 2009713
From dark flash images to relightable 3D scenes with photometric stereo priors
- Open Access
- 11 November 2025
- Published by Springer Nature in Frontiers of Computer Science
- Vol. 20 (4) , 1-24
A survey on 3D editing based on NeRF and 3DGS
In recent years, 3D editing has become a significant research topic, primarily due to its ability to manipulate 3D assets in ways that fulfill the growing demand for personalized customization. The advent of radiance field-based methods, exemplified by pioneering frameworks such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS), represents a pivotal innovation in scene representation and novel view synthesis, greatly enhancing the effectiveness and efficiency of 3D editing. This survey provides a comprehensive overview of the current advancements in 3D editing based on NeRF and 3DGS, systematically categorizing existing methods according to specific editing tasks while analyzing the current challenges and potential research directions. Our goal through this survey is to offer a comprehensive and valuable resource for researchers in the field, encouraging innovative ideas that may drive further progress in 3D editing.
- 11 November 2025
- Published by Springer Nature in Frontiers of Computer Science
- Vol. 20 (4) , 1-24
Open AccessA survey on 3D editing based on NeRF and 3DGS
In recent years, 3D editing has become a significant research topic, primarily due to its ability to manipulate 3D assets in ways that fulfill the growing demand for personalized customization. The advent of radiance field-based methods, exemplified by pioneering frameworks such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS), represents a pivotal innovation in scene representation and novel view synthesis, greatly enhancing the effectiveness and efficiency of 3D editing. This survey provides a comprehensive overview of the current advancements in 3D editing based on NeRF and 3DGS, systematically categorizing existing methods according to specific editing tasks while analyzing the current challenges and potential research directions. Our goal through this survey is to offer a comprehensive and valuable resource for researchers in the field, encouraging innovative ideas that may drive further progress in 3D editing.
- 24 June 2025
- Published by Springer Nature in The Visual Computer
- p. 1-13
Angio-Diff: learning a self-supervised adversarial diffusion model for angiographic geometry generation
- 24 June 2025
- Published by Springer Nature in The Visual Computer
- p. 1-13
Angio-Diff: learning a self-supervised adversarial diffusion model for angiographic geometry generation
- Open Access
Angio-Diff: Learning a Self-Supervised Adversarial Diffusion Model for Angiographic Geometry Generation
Vascular diseases pose a significant threat to human health, with X-ray angiography established as the gold standard for diagnosis, allowing for detailed observation of blood vessels. However, angiographic X-rays expose personnel and patients to higher radiation levels than non-angiographic X-rays, which are unwanted. Thus, modality translation from non-angiographic to angiographic X-rays is desirable. Data-driven deep approaches are hindered by the lack of paired large-scale X-ray angiography datasets. While making high-quality vascular angiography synthesis crucial, it remains challenging. We find that current medical image synthesis primarily operates at pixel level and struggles to adapt to the complex geometric structure of blood vessels, resulting in unsatisfactory quality of blood vessel image synthesis, such as disconnections or unnatural curvatures. To overcome this issue, we propose a self-supervised method via diffusion models to transform non-angiographic X-rays into angiographic X-rays, mitigating data shortages for data-driven approaches. Our model comprises a diffusion model that learns the distribution of vascular data from diffusion latent, a generator for vessel synthesis, and a mask-based adversarial module. To enhance geometric accuracy, we propose a parametric vascular model to fit the shape and distribution of blood vessels. The proposed method contributes a pipeline and a synthetic dataset for X-ray angiography. We conducted extensive comparative and ablation experiments to evaluate the Angio-Diff. The results demonstrate that our method achieves state-of-the-art performance in synthetic angiography image quality and more accurately synthesizes the geometric structure of blood vessels. The code is available at https://github.com/zfw-cv/AngioDiff.
Open AccessAngio-Diff: Learning a Self-Supervised Adversarial Diffusion Model for Angiographic Geometry Generation
Vascular diseases pose a significant threat to human health, with X-ray angiography established as the gold standard for diagnosis, allowing for detailed observation of blood vessels. However, angiographic X-rays expose personnel and patients to higher radiation levels than non-angiographic X-rays, which are unwanted. Thus, modality translation from non-angiographic to angiographic X-rays is desirable. Data-driven deep approaches are hindered by the lack of paired large-scale X-ray angiography datasets. While making high-quality vascular angiography synthesis crucial, it remains challenging. We find that current medical image synthesis primarily operates at pixel level and struggles to adapt to the complex geometric structure of blood vessels, resulting in unsatisfactory quality of blood vessel image synthesis, such as disconnections or unnatural curvatures. To overcome this issue, we propose a self-supervised method via diffusion models to transform non-angiographic X-rays into angiographic X-rays, mitigating data shortages for data-driven approaches. Our model comprises a diffusion model that learns the distribution of vascular data from diffusion latent, a generator for vessel synthesis, and a mask-based adversarial module. To enhance geometric accuracy, we propose a parametric vascular model to fit the shape and distribution of blood vessels. The proposed method contributes a pipeline and a synthetic dataset for X-ray angiography. We conducted extensive comparative and ablation experiments to evaluate the Angio-Diff. The results demonstrate that our method achieves state-of-the-art performance in synthetic angiography image quality and more accurately synthesizes the geometric structure of blood vessels. The code is available at https://github.com/zfw-cv/AngioDiff.
- 28 January 2025
- Published by Springer Nature in Frontiers of Computer Science
- Vol. 19 (10) , 1-23
CAD-NeRF: learning NeRFs from uncalibrated few-view images by CAD model retrieval
- 28 January 2025
- Published by Springer Nature in Frontiers of Computer Science
- Vol. 19 (10) , 1-23
CAD-NeRF: learning NeRFs from uncalibrated few-view images by CAD model retrieval
- Open Access
- 1 December 2024
- Published by Tsinghua University Press in Computational Visual Media
- Vol. 10 (6) , 1121-1135
THP: Tensor-field-driven hierarchical path planning for autonomous scene exploration with depth sensors
It is challenging to automatically explore an unknown 3D environment with a robot only equipped with depth sensors due to the limited field of view. We introduce THP, a tensor field-based framework for efficient environment exploration which can better utilize the encoded depth information through the geometric characteristics of tensor fields. Specifically, a corresponding tensor field is constructed incrementally and guides the robot to formulate optimal global exploration paths and a collision-free local movement strategy. Degenerate points generated during the exploration are adopted as anchors to formulate a hierarchical TSP for global path optimization. This novel strategy can help the robot avoid long-distance round trips more effectively while maintaining scanning completeness. Furthermore, the tensor field also enables a local movement strategy to avoid collision based on particle advection. As a result, the framework can eliminate massive, time-consuming recalculations of local movement paths. We have experimentally evaluate our method with a ground robot in 8 complex indoor scenes. Our method can on average achieve 14% better exploration efficiency and 21% better exploration completeness than state-of-the-art alternatives using LiDAR scans. Moreover, compared to similar methods, our method makes path decisions 39% faster due to our hierarchical exploration strategy.
- 1 December 2024
- Published by Tsinghua University Press in Computational Visual Media
- Vol. 10 (6) , 1121-1135
Open AccessTHP: Tensor-field-driven hierarchical path planning for autonomous scene exploration with depth sensors
It is challenging to automatically explore an unknown 3D environment with a robot only equipped with depth sensors due to the limited field of view. We introduce THP, a tensor field-based framework for efficient environment exploration which can better utilize the encoded depth information through the geometric characteristics of tensor fields. Specifically, a corresponding tensor field is constructed incrementally and guides the robot to formulate optimal global exploration paths and a collision-free local movement strategy. Degenerate points generated during the exploration are adopted as anchors to formulate a hierarchical TSP for global path optimization. This novel strategy can help the robot avoid long-distance round trips more effectively while maintaining scanning completeness. Furthermore, the tensor field also enables a local movement strategy to avoid collision based on particle advection. As a result, the framework can eliminate massive, time-consuming recalculations of local movement paths. We have experimentally evaluate our method with a ground robot in 8 complex indoor scenes. Our method can on average achieve 14% better exploration efficiency and 21% better exploration completeness than state-of-the-art alternatives using LiDAR scans. Moreover, compared to similar methods, our method makes path decisions 39% faster due to our hierarchical exploration strategy.
- 3 November 2024
- Published by Springer Nature
- p. 285-298
MaskEditor: Instruct 3D Object Editing with Learned Masks
- 3 November 2024
- Published by Springer Nature
- p. 285-298
MaskEditor: Instruct 3D Object Editing with Learned Masks
- Open Access
- 1 April 2024
- Published by Tsinghua University Press in Computational Visual Media
- Vol. 10 (2) , 309-330
Learning accurate template matching with differentiable coarse-to-fine correspondence refinement
Template matching is a fundamental task in computer vision and has been studied for decades. It plays an essential role in manufacturing industry for estimating the poses of different parts, facilitating downstream tasks such as robotic grasping. Existing methods fail when the template and source images have different modalities, cluttered backgrounds, or weak textures. They also rarely consider geometric transformations via homographies, which commonly exist even for planar industrial parts. To tackle the challenges, we propose an accurate template matching method based on differentiable coarse-to-fine correspondence refinement. We use an edge-aware module to overcome the domain gap between the mask template and the grayscale image, allowing robust matching. An initial warp is estimated using coarse correspondences based on novel structure-aware information provided by transformers. This initial alignment is passed to a refinement network using references and aligned images to obtain sub-pixel level correspondences which are used to give the final geometric transformation. Extensive evaluation shows that our method to be significantly better than state-of-the-art methods and baselines, providing good generalization ability and visually plausible results even on unseen real data.
- 1 April 2024
- Published by Tsinghua University Press in Computational Visual Media
- Vol. 10 (2) , 309-330
Open AccessLearning accurate template matching with differentiable coarse-to-fine correspondence refinement
Template matching is a fundamental task in computer vision and has been studied for decades. It plays an essential role in manufacturing industry for estimating the poses of different parts, facilitating downstream tasks such as robotic grasping. Existing methods fail when the template and source images have different modalities, cluttered backgrounds, or weak textures. They also rarely consider geometric transformations via homographies, which commonly exist even for planar industrial parts. To tackle the challenges, we propose an accurate template matching method based on differentiable coarse-to-fine correspondence refinement. We use an edge-aware module to overcome the domain gap between the mask template and the grayscale image, allowing robust matching. An initial warp is estimated using coarse correspondences based on novel structure-aware information provided by transformers. This initial alignment is passed to a refinement network using references and aligned images to obtain sub-pixel level correspondences which are used to give the final geometric transformation. Extensive evaluation shows that our method to be significantly better than state-of-the-art methods and baselines, providing good generalization ability and visually plausible results even on unseen real data.
- Open Access
- 1 February 2024
- Published by Tsinghua University Press in Computational Visual Media
- Vol. 10 (1) , 61-77
6DOF pose estimation of a 3D rigid object based on edge-enhanced point pair features
The point pair feature (PPF) is widely used for 6D pose estimation. In this paper, we propose an efficient 6D pose estimation method based on the PPF framework. We introduce a well-targeted down-sampling strategy that focuses on edge areas for efficient feature extraction for complex geometry. A pose hypothesis validation approach is proposed to resolve ambiguity due to symmetry by calculating the edge matching degree. We perform evaluations on two challenging datasets and one real-world collected dataset, demonstrating the superiority of our method for pose estimation for geometrically complex, occluded, symmetrical objects. We further validate our method by applying it to simulated punctures.
- 1 February 2024
- Published by Tsinghua University Press in Computational Visual Media
- Vol. 10 (1) , 61-77
Open Access6DOF pose estimation of a 3D rigid object based on edge-enhanced point pair features
The point pair feature (PPF) is widely used for 6D pose estimation. In this paper, we propose an efficient 6D pose estimation method based on the PPF framework. We introduce a well-targeted down-sampling strategy that focuses on edge areas for efficient feature extraction for complex geometry. A pose hypothesis validation approach is proposed to resolve ambiguity due to symmetry by calculating the edge matching degree. We perform evaluations on two challenging datasets and one real-world collected dataset, demonstrating the superiority of our method for pose estimation for geometrically complex, occluded, symmetrical objects. We further validate our method by applying it to simulated punctures.
- Open Access
- 1 December 2023
- Published by Tsinghua University Press in Computational Visual Media
- Vol. 9 (4) , 875-892
EFECL: Feature encoding enhancement with contrastive learning for indoor 3D object detection
Good proposal initials are critical for 3D object detection applications. However, due to the significant geometry variation of indoor scenes, incomplete and noisy proposals are inevitable in most cases. Mining feature information among these “bad” proposals may mislead the detection. Contrastive learning provides a feasible way for representing proposals, which can align complete and incomplete/noisy proposals in feature space. The aligned feature space can help us build robust 3D representation even if bad proposals are given. Therefore, we devise a new contrast learning framework for indoor 3D object detection, called EFECL, that learns robust 3D representations by contrastive learning of proposals on two different levels. Specifically, we optimize both instance-level and category-level contrasts to align features by capturing instance-specific characteristics and semantic-aware common patterns. Furthermore, we propose an enhanced feature aggregation module to extract more general and informative features for contrastive learning. Evaluations on ScanNet V2 and SUN RGB-D benchmarks demonstrate the generalizability and effectiveness of our method, and our method can achieve 12.3% and 7.3% improvements on both datasets over the benchmark alternatives. The code and models are publicly available at https://github.com/YaraDuan/EFECL.
- 1 December 2023
- Published by Tsinghua University Press in Computational Visual Media
- Vol. 9 (4) , 875-892
Open AccessEFECL: Feature encoding enhancement with contrastive learning for indoor 3D object detection
Good proposal initials are critical for 3D object detection applications. However, due to the significant geometry variation of indoor scenes, incomplete and noisy proposals are inevitable in most cases. Mining feature information among these “bad” proposals may mislead the detection. Contrastive learning provides a feasible way for representing proposals, which can align complete and incomplete/noisy proposals in feature space. The aligned feature space can help us build robust 3D representation even if bad proposals are given. Therefore, we devise a new contrast learning framework for indoor 3D object detection, called EFECL, that learns robust 3D representations by contrastive learning of proposals on two different levels. Specifically, we optimize both instance-level and category-level contrasts to align features by capturing instance-specific characteristics and semantic-aware common patterns. Furthermore, we propose an enhanced feature aggregation module to extract more general and informative features for contrastive learning. Evaluations on ScanNet V2 and SUN RGB-D benchmarks demonstrate the generalizability and effectiveness of our method, and our method can achieve 12.3% and 7.3% improvements on both datasets over the benchmark alternatives. The code and models are publicly available at https://github.com/YaraDuan/EFECL.