Junting Dong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Junting Dong has a total of 41 co-authors. Here are the top co-authors by number of shared publications:
- Hujun Bao
State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China
6 shared publications - Xiaowei Zhou
State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China
6 shared publications - Linning Xu
The Chinese University of Hong Kong
3 shared publications - Mulin Yu
Shanghai Artificial Intelligence Laboratory, Shanghai, China
3 shared publications - Qing Shuai
Zhejiang University, Hangzhou, China
3 shared publications - Sida Peng
Zhejiang University, Hangzhou, China
3 shared publications
Latest Publications
- Open Access
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
M 3 : Dense Matching Meets Multi-View Foundation Models for Monocular Gaussian Splatting SLAM
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessM 3 : Dense Matching Meets Multi-View Foundation Models for Monocular Gaussian Splatting SLAM
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-10
SynthVerse: A Large-Scale Diverse Synthetic Dataset for Point Tracking
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Open AccessSynthVerse: A Large-Scale Diverse Synthetic Dataset for Point Tracking
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-10
TrajVG: 3D Trajectory-Coupled Visual Geometry Learning
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Open AccessTrajVG: 3D Trajectory-Coupled Visual Geometry Learning
- Open Access
- 4 December 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 44 (6) , 1-15
Split4D: Decomposed 4D Scene Reconstruction Without Video Segmentation
This paper addresses the problem of decomposed 4D scene reconstruction from multi-view videos. Recent methods achieve this by lifting video segmentation results to a 4D representation through differentiable rendering techniques. Therefore, they heavily rely on the quality of video segmentation maps, which are often unstable, leading to unreliable reconstruction results. To overcome this challenge, our key idea is to represent the decomposed 4D scene with the Freetime FeatureGS and design a streaming feature learning strategy to accurately recover it from per-image segmentation maps, eliminating the need for video segmentation. Freetime FeatureGS models the dynamic scene as a set of Gaussian primitives with learnable features and linear motion ability, allowing them to move to neighboring regions over time. We apply a contrastive loss to Freetime FeatureGS, forcing primitive features to be close or far apart based on whether their projections belong to the same instance in the 2D segmentation map. As our Gaussian primitives can move across time, it naturally extends the feature learning to the temporal dimension, achieving 4D segmentation. Furthermore, we sample observations for training in a temporally ordered manner, enabling the streaming propagation of features over time and effectively avoiding local minima during the optimization process. Experimental results on several datasets show that the reconstruction quality of our method outperforms recent methods by a large margin.
- 4 December 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 44 (6) , 1-15
Open AccessSplit4D: Decomposed 4D Scene Reconstruction Without Video Segmentation
This paper addresses the problem of decomposed 4D scene reconstruction from multi-view videos. Recent methods achieve this by lifting video segmentation results to a 4D representation through differentiable rendering techniques. Therefore, they heavily rely on the quality of video segmentation maps, which are often unstable, leading to unreliable reconstruction results. To overcome this challenge, our key idea is to represent the decomposed 4D scene with the Freetime FeatureGS and design a streaming feature learning strategy to accurately recover it from per-image segmentation maps, eliminating the need for video segmentation. Freetime FeatureGS models the dynamic scene as a set of Gaussian primitives with learnable features and linear motion ability, allowing them to move to neighboring regions over time. We apply a contrastive loss to Freetime FeatureGS, forcing primitive features to be close or far apart based on whether their projections belong to the same instance in the 2D segmentation map. As our Gaussian primitives can move across time, it naturally extends the feature learning to the temporal dimension, achieving 4D segmentation. Furthermore, we sample observations for training in a temporally ordered manner, enabling the streaming propagation of features over time and effectively avoiding local minima during the optimization process. Experimental results on several datasets show that the reconstruction quality of our method outperforms recent methods by a large margin.
- 17 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (6) , 4147-4159
Animatable Implicit Neural Representations for Creating Realistic Avatars From Videos
This paper addresses the challenge of reconstructing an animatable human model from a multi-view video. Some recent works have proposed to decompose a non-rigidly deforming scene into a canonical neural radiance field and a set of deformation fields that map observation-space points to the canonical space, thereby enabling them to learn the dynamic scene from images. However, they represent the deformation field as translational vector field or SE(3) field, which makes the optimization highly under-constrained. Moreover, these representations cannot be explicitly controlled by input motions. Instead, we introduce blend weight fields to produce the deformation fields. Based on the skeleton-driven deformation, blend weight fields are used with 3D human skeletons to generate observation-to-canonical and canonical-to-observation correspondences. Since 3D human skeletons are more observable, they can regularize the learning of deformation fields. Moreover, the blend weight fields can be combined with input skeletal motions to generate new deformation fields to animate the human model. To improve the quality of human modeling, we further represent the human geometry as a signed distance field in the canonical space. Additionally, a neural point displacement field is introduced to enhance the capability of the blend weight field on modeling detailed human motions. Experiments show that our approach significantly outperforms recent human modeling methods. The code is available at https://zju3dv.github.io/animatable nerf/ .
- 17 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (6) , 4147-4159
Animatable Implicit Neural Representations for Creating Realistic Avatars From Videos
This paper addresses the challenge of reconstructing an animatable human model from a multi-view video. Some recent works have proposed to decompose a non-rigidly deforming scene into a canonical neural radiance field and a set of deformation fields that map observation-space points to the canonical space, thereby enabling them to learn the dynamic scene from images. However, they represent the deformation field as translational vector field or SE(3) field, which makes the optimization highly under-constrained. Moreover, these representations cannot be explicitly controlled by input motions. Instead, we introduce blend weight fields to produce the deformation fields. Based on the skeleton-driven deformation, blend weight fields are used with 3D human skeletons to generate observation-to-canonical and canonical-to-observation correspondences. Since 3D human skeletons are more observable, they can regularize the learning of deformation fields. Moreover, the blend weight fields can be combined with input skeletal motions to generate new deformation fields to animate the human model. To improve the quality of human modeling, we further represent the human geometry as a signed distance field in the canonical space. Additionally, a neural point displacement field is introduced to enhance the capability of the blend weight field on modeling detailed human motions. Experiments show that our approach significantly outperforms recent human modeling methods. The code is available at https://zju3dv.github.io/animatable nerf/ .
- 12 March 2022
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 130 (5) , 1165-1180
iMoCap: Motion Capture from Internet Videos
- 12 March 2022
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 130 (5) , 1165-1180
iMoCap: Motion Capture from Internet Videos
- Open Access
Animatable Neural Radiance Fields for Modeling Dynamic Human Bodies
This paper addresses the challenge of reconstructing an animatable human model from a multi-view video. Some recent works have proposed to decompose a non-rigidly deforming scene into a canonical neural radiance field and a set of deformation fields that map observation-space points to the canonical space, thereby enabling them to learn the dynamic scene from images. However, they represent the deformation field as translational vector field or SE(3) field, which makes the optimization highly under-constrained. Moreover, these representations cannot be explicitly controlled by input motions. Instead, we introduce neural blend weight fields to produce the deformation fields. Based on the skeleton-driven deformation, blend weight fields are used with 3D human skeletons to generate observation-to-canonical and canonical-to-observation correspondences. Since 3D human skeletons are more observable, they can regularize the learning of deformation fields. Moreover, the learned blend weight fields can be combined with input skeletal motions to generate new deformation fields to animate the human model. Experiments show that our approach significantly outperforms recent human synthesis methods. The code and supplementary materials are available at https://zju3dv.github.io/animatable_nerf/.
Open AccessAnimatable Neural Radiance Fields for Modeling Dynamic Human Bodies
This paper addresses the challenge of reconstructing an animatable human model from a multi-view video. Some recent works have proposed to decompose a non-rigidly deforming scene into a canonical neural radiance field and a set of deformation fields that map observation-space points to the canonical space, thereby enabling them to learn the dynamic scene from images. However, they represent the deformation field as translational vector field or SE(3) field, which makes the optimization highly under-constrained. Moreover, these representations cannot be explicitly controlled by input motions. Instead, we introduce neural blend weight fields to produce the deformation fields. Based on the skeleton-driven deformation, blend weight fields are used with 3D human skeletons to generate observation-to-canonical and canonical-to-observation correspondences. Since 3D human skeletons are more observable, they can regularize the learning of deformation fields. Moreover, the learned blend weight fields can be combined with input skeletal motions to generate new deformation fields to animate the human model. Experiments show that our approach significantly outperforms recent human synthesis methods. The code and supplementary materials are available at https://zju3dv.github.io/animatable_nerf/.
- 20 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 44 (10) , 6981-6992
Fast and Robust Multi-Person 3D Pose Estimation and Tracking From Multiple Views
This paper addresses the problem of reconstructing 3D poses of multiple people from a few calibrated camera views. The main challenge of this problem is to find the cross-view correspondences among noisy and incomplete 2D pose predictions. Most previous methods address this challenge by directly reasoning in 3D using a pictorial structure model, which is inefficient due to the huge state space. We propose a fast and robust approach to solve this problem. Our key idea is to use a multi-way matching algorithm to cluster the detected 2D poses in all views. Each resulting cluster encodes 2D poses of the same person across different views and consistent correspondences across the keypoints, from which the 3D pose of each person can be effectively inferred. The proposed convex optimization based multi-way matching algorithm is efficient and robust against missing and false detections, without knowing the number of people in the scene. Moreover, we propose to combine geometric and appearance cues for cross-view matching. Finally, an efficient tracking method is proposed to track the detected 3D poses across the multi-view video. The proposed approach achieves the state-of-the-art performance on the Campus and Shelf datasets, while being efficient for real-time applications.
- 20 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 44 (10) , 6981-6992
Fast and Robust Multi-Person 3D Pose Estimation and Tracking From Multiple Views
This paper addresses the problem of reconstructing 3D poses of multiple people from a few calibrated camera views. The main challenge of this problem is to find the cross-view correspondences among noisy and incomplete 2D pose predictions. Most previous methods address this challenge by directly reasoning in 3D using a pictorial structure model, which is inefficient due to the huge state space. We propose a fast and robust approach to solve this problem. Our key idea is to use a multi-way matching algorithm to cluster the detected 2D poses in all views. Each resulting cluster encodes 2D poses of the same person across different views and consistent correspondences across the keypoints, from which the 3D pose of each person can be effectively inferred. The proposed convex optimization based multi-way matching algorithm is efficient and robust against missing and false detections, without knowing the number of people in the scene. Moreover, we propose to combine geometric and appearance cues for cross-view matching. Finally, an efficient tracking method is proposed to track the detected 3D poses across the multi-view video. The proposed approach achieves the state-of-the-art performance on the Campus and Shelf datasets, while being efficient for real-time applications.
- Open Access
Fast and Robust Multi-Person 3D Pose Estimation from Multiple Views
This paper addresses the problem of 3D pose estimation for multiple people in a few calibrated camera views. The main challenge of this problem is to find the cross-view correspondences among noisy and incomplete 2D pose predictions. Most previous methods address this challenge by directly reasoning in 3D using a pictorial structure model, which is inefficient due to the huge state space. We propose a fast and robust approach to solve this problem. Our key idea is to use a multi-way matching algorithm to cluster the detected 2D poses in all views. Each resulting cluster encodes 2D poses of the same person across different views and consistent correspondences across the keypoints, from which the 3D pose of each person can be effectively inferred. The proposed convex optimization based multi-way matching algorithm is efficient and robust against missing and false detections, without knowing the number of people in the scene. Moreover, we propose to combine geometric and appearance cues for cross-view matching. The proposed approach achieves significant performance gains from the state-of-the-art (96.3% vs. 90.6% and 96.9% vs. 88% on the Campus and Shelf datasets, respectively), while being efficient for real-time applications.
Open AccessFast and Robust Multi-Person 3D Pose Estimation from Multiple Views
This paper addresses the problem of 3D pose estimation for multiple people in a few calibrated camera views. The main challenge of this problem is to find the cross-view correspondences among noisy and incomplete 2D pose predictions. Most previous methods address this challenge by directly reasoning in 3D using a pictorial structure model, which is inefficient due to the huge state space. We propose a fast and robust approach to solve this problem. Our key idea is to use a multi-way matching algorithm to cluster the detected 2D poses in all views. Each resulting cluster encodes 2D poses of the same person across different views and consistent correspondences across the keypoints, from which the 3D pose of each person can be effectively inferred. The proposed convex optimization based multi-way matching algorithm is efficient and robust against missing and false detections, without knowing the number of people in the scene. Moreover, we propose to combine geometric and appearance cues for cross-view matching. The proposed approach achieves significant performance gains from the state-of-the-art (96.3% vs. 90.6% and 96.9% vs. 88% on the Campus and Shelf datasets, respectively), while being efficient for real-time applications.