Yixin Chen
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
Yixin Chen has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
- Siyuan Huang
Beijing Institute for General Artificial Intelligence (BIGAI)
10 shared publications - Baoxiong Jia
Beijing Institute for General Artificial Intelligence (BIGAI)
5 shared publications - Yu Liu
Tsinghua University, Beijing, China
4 shared publications - Junfeng Ni
Tsinghua University, Beijing, China
2 shared publications - Nan Jiang
Institute for AI, Peking University, Beijing, China and National Key Lab of General AI, BIGAI, Beijing, China
2 shared publications - Qing Li
Beijing Institute for General Artificial Intelligence (BIGAI)
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (6) , 1-12
DecomVoxel: Harnessing 3D-Native Priors with Guided In-situ Denoising Optimization for Decompositional Scene Reconstruction
Decompositional scene reconstruction aims to reconstruct high-quality objects and background, yet existing methods still struggle with the level of quality under heavy occlusions. While generative priors offer a potential solution, 2D image-based priors often suffer from multi-view inconsistency due to a lack of 3D awareness. Conversely, 3D-native priors provide stronger structural inductive biases but frequently lead to spatial drift and misalignment within complex scenes. To address these issues, we propose DecomVoxel, formulating object completion as a guided in-situ denoising optimization that bridges 3D-native priors with neural scene reconstruction. Our framework introduces a reformulated epsilon-based distillation loss to ensure stable latent refinement, alongside adaptive spatial guidance that utilizes occupied and vacant anchors with temporal annealing to suppress generative hallucinations and mitigate spatial drift. Experiments on Replica and ScanNet++ show that DecomVoxel significantly outperforms state-of-the-art methods while faithfully preserving the original spatial layout, structural fidelity, and style-consistent texture. Our method pushes the boundary of decompositional reconstruction by delivering high-quality textured meshes with clean topology, geometry, and appearance, providing a robust solution for the decompositional reconstruction of complex real-world scenes. Code is available at https://github.com/DecomVoxel/DecomVoxel.
- 9 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (6) , 1-12
Open AccessDecomVoxel: Harnessing 3D-Native Priors with Guided In-situ Denoising Optimization for Decompositional Scene Reconstruction
Decompositional scene reconstruction aims to reconstruct high-quality objects and background, yet existing methods still struggle with the level of quality under heavy occlusions. While generative priors offer a potential solution, 2D image-based priors often suffer from multi-view inconsistency due to a lack of 3D awareness. Conversely, 3D-native priors provide stronger structural inductive biases but frequently lead to spatial drift and misalignment within complex scenes. To address these issues, we propose DecomVoxel, formulating object completion as a guided in-situ denoising optimization that bridges 3D-native priors with neural scene reconstruction. Our framework introduces a reformulated epsilon-based distillation loss to ensure stable latent refinement, alongside adaptive spatial guidance that utilizes occupied and vacant anchors with temporal annealing to suppress generative hallucinations and mitigate spatial drift. Experiments on Replica and ScanNet++ show that DecomVoxel significantly outperforms state-of-the-art methods while faithfully preserving the original spatial layout, structural fidelity, and style-consistent texture. Our method pushes the boundary of decompositional reconstruction by delivering high-quality textured meshes with clean topology, geometry, and appearance, providing a robust solution for the decompositional reconstruction of complex real-world scenes. Code is available at https://github.com/DecomVoxel/DecomVoxel.
- 25 September 2026
- Published by Springer Nature
- p. 658-676
AutoPhyX: Automatic Text-Condition Physics Property Generation
- 25 September 2026
- Published by Springer Nature
- p. 658-676
AutoPhyX: Automatic Text-Condition Physics Property Generation
- 11 September 2026
- Published by Springer Nature
- p. 516-534
UniFusion: Sparse-View 4D Reconstruction via Unified Spatio-Temporal Depth Alignment
- 11 September 2026
- Published by Springer Nature
- p. 516-534
UniFusion: Sparse-View 4D Reconstruction via Unified Spatio-Temporal Depth Alignment
- Open Access
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-13
Generating Objects with Part-Articulation from a Single Image
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-13
Open AccessGenerating Objects with Part-Articulation from a Single Image
- Open Access
- 3 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Autonomous Character-Scene Interaction Synthesis from Text Instruction
- 3 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessAutonomous Character-Scene Interaction Synthesis from Text Instruction
- 22 October 2024
- Published by Springer Nature
- p. 270-288
SlotLifter: Slot-Guided Feature Lifting for Learning Object-Centric Radiance Fields
- 22 October 2024
- Published by Springer Nature
- p. 270-288
SlotLifter: Slot-Guided Feature Lifting for Learning Object-Centric Radiance Fields
- Top Cited Papers
- 22 October 2024
- Published by Springer Nature
- p. 289-310
SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding
- 22 October 2024
- Published by Springer Nature
- p. 289-310
Top Cited PapersSceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding
- 30 September 2024
- Published by Springer Nature
- p. 188-206
Unifying 3D Vision-Language Understanding via Promptable Queries
- 30 September 2024
- Published by Springer Nature
- p. 188-206
Unifying 3D Vision-Language Understanding via Promptable Queries
- Open Access
SlotLifter: Slot-guided Feature Lifting for Learning Object-centric Radiance Fields
The ability to distill object-centric abstractions from intricate visual scenes underpins human-level generalization. Despite the significant progress in object-centric learning methods, learning object-centric representations in the 3D physical world remains a crucial challenge. In this work, we propose SlotLifter, a novel object-centric radiance model addressing scene reconstruction and decomposition jointly via slot-guided feature lifting. Such a design unites object-centric learning representations and image-based rendering methods, offering state-of-the-art performance in scene decomposition and novel-view synthesis on four challenging synthetic and four complex real-world datasets, outperforming existing 3D object-centric learning methods by a large margin. Through extensive ablative studies, we showcase the efficacy of designs in SlotLifter, revealing key insights for potential future directions.
Open AccessSlotLifter: Slot-guided Feature Lifting for Learning Object-centric Radiance Fields
The ability to distill object-centric abstractions from intricate visual scenes underpins human-level generalization. Despite the significant progress in object-centric learning methods, learning object-centric representations in the 3D physical world remains a crucial challenge. In this work, we propose SlotLifter, a novel object-centric radiance model addressing scene reconstruction and decomposition jointly via slot-guided feature lifting. Such a design unites object-centric learning representations and image-based rendering methods, offering state-of-the-art performance in scene decomposition and novel-view synthesis on four challenging synthetic and four complex real-world datasets, outperforming existing 3D object-centric learning methods by a large margin. Through extensive ablative studies, we showcase the efficacy of designs in SlotLifter, revealing key insights for potential future directions.
- 28 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Evaluating The Effect of Refraction on Underwater Stereo Vision
Underwater binocular stereo vision is a method for the three-dimensional measurement of underwater objects, but its measurement accuracy is affected by the refraction of underwater cameras. The calibration-based refraction compensation method is widely used due to its easy operation and calculation, while the physical model-based method seems to be a higher precision but is not popular enough. In this paper, we propose to compare the calibration-based and the physical model-based refraction correction methods for their best working conditions. We constructed the underwater binocular distance measurement environment and evaluated the calibration-based and the physical model-based method by adjusting the setting of the underwater camera parameters and the calibration mode of the underwater camera. We analyzed the effect of several key factors emphatically, such as the distance between the optical center of the camera and the glass interface (camera-glass distance), the calibration distance of the underwater camera, and the measurement distance of the underwater camera. Results demonstrate that the calibration-based method has smaller errors when the camera-glass distance is smaller, or when the underwater binocular distance measurement is carried out nearby the calibration distance of the underwater camera. In other cases, the physical model method is more suitable.
- 28 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Evaluating The Effect of Refraction on Underwater Stereo Vision
Underwater binocular stereo vision is a method for the three-dimensional measurement of underwater objects, but its measurement accuracy is affected by the refraction of underwater cameras. The calibration-based refraction compensation method is widely used due to its easy operation and calculation, while the physical model-based method seems to be a higher precision but is not popular enough. In this paper, we propose to compare the calibration-based and the physical model-based refraction correction methods for their best working conditions. We constructed the underwater binocular distance measurement environment and evaluated the calibration-based and the physical model-based method by adjusting the setting of the underwater camera parameters and the calibration mode of the underwater camera. We analyzed the effect of several key factors emphatically, such as the distance between the optical center of the camera and the glass interface (camera-glass distance), the calibration distance of the underwater camera, and the measurement distance of the underwater camera. Results demonstrate that the calibration-based method has smaller errors when the camera-glass distance is smaller, or when the underwater binocular distance measurement is carried out nearby the calibration distance of the underwater camera. In other cases, the physical model method is more suitable.