Alert button
Picture for Chenjie Cao

Chenjie Cao

Alert button

Repositioning the Subject within Image

Jan 30, 2024
Yikai Wang, Chenjie Cao, Qiaole Dong, Yifan Li, Yanwei Fu

Viaarxiv icon

MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo

Jan 22, 2024
Chenjie Cao, Xinlin Ren, Yanwei Fu

Viaarxiv icon

Towards Stable and Faithful Inpainting

Dec 08, 2023
Yikai Wang, Chenjie Cao, Yanwei Fu

Viaarxiv icon

Local Consensus Enhanced Siamese Network with Reciprocal Loss for Two-view Correspondence Learning

Aug 06, 2023
Linbo Wang, Jing Wu, Xianyong Fang, Zhengyi Liu, Chenjie Cao, Yanwei Fu

Figure 1 for Local Consensus Enhanced Siamese Network with Reciprocal Loss for Two-view Correspondence Learning
Figure 2 for Local Consensus Enhanced Siamese Network with Reciprocal Loss for Two-view Correspondence Learning
Figure 3 for Local Consensus Enhanced Siamese Network with Reciprocal Loss for Two-view Correspondence Learning
Figure 4 for Local Consensus Enhanced Siamese Network with Reciprocal Loss for Two-view Correspondence Learning
Viaarxiv icon

A Unified Prompt-Guided In-Context Inpainting Framework for Reference-based Image Manipulations

May 19, 2023
Chenjie Cao, Qiaole Dong, Yikai Wang, Yunuo Cai, Yanwei Fu

Figure 1 for A Unified Prompt-Guided In-Context Inpainting Framework for Reference-based Image Manipulations
Figure 2 for A Unified Prompt-Guided In-Context Inpainting Framework for Reference-based Image Manipulations
Figure 3 for A Unified Prompt-Guided In-Context Inpainting Framework for Reference-based Image Manipulations
Figure 4 for A Unified Prompt-Guided In-Context Inpainting Framework for Reference-based Image Manipulations
Viaarxiv icon

Rethinking Optical Flow from Geometric Matching Consistent Perspective

Mar 15, 2023
Qiaole Dong, Chenjie Cao, Yanwei Fu

Figure 1 for Rethinking Optical Flow from Geometric Matching Consistent Perspective
Figure 2 for Rethinking Optical Flow from Geometric Matching Consistent Perspective
Figure 3 for Rethinking Optical Flow from Geometric Matching Consistent Perspective
Figure 4 for Rethinking Optical Flow from Geometric Matching Consistent Perspective
Viaarxiv icon

Rethinking the Multi-view Stereo from the Perspective of Rendering-based Augmentation

Mar 11, 2023
Chenjie Cao, Xinlin Ren, Xiangyang Xue, Yanwei Fu

Figure 1 for Rethinking the Multi-view Stereo from the Perspective of Rendering-based Augmentation
Figure 2 for Rethinking the Multi-view Stereo from the Perspective of Rendering-based Augmentation
Figure 3 for Rethinking the Multi-view Stereo from the Perspective of Rendering-based Augmentation
Figure 4 for Rethinking the Multi-view Stereo from the Perspective of Rendering-based Augmentation
Viaarxiv icon

Improving Transformer-based Image Matching by Cascaded Capturing Spatially Informative Keypoints

Mar 06, 2023
Chenjie Cao, Yanwei Fu

Figure 1 for Improving Transformer-based Image Matching by Cascaded Capturing Spatially Informative Keypoints
Figure 2 for Improving Transformer-based Image Matching by Cascaded Capturing Spatially Informative Keypoints
Figure 3 for Improving Transformer-based Image Matching by Cascaded Capturing Spatially Informative Keypoints
Figure 4 for Improving Transformer-based Image Matching by Cascaded Capturing Spatially Informative Keypoints
Viaarxiv icon

ZITS++: Image Inpainting by Improving the Incremental Transformer on Structural Priors

Oct 12, 2022
Chenjie Cao, Qiaole Dong, Yanwei Fu

Figure 1 for ZITS++: Image Inpainting by Improving the Incremental Transformer on Structural Priors
Figure 2 for ZITS++: Image Inpainting by Improving the Incremental Transformer on Structural Priors
Figure 3 for ZITS++: Image Inpainting by Improving the Incremental Transformer on Structural Priors
Figure 4 for ZITS++: Image Inpainting by Improving the Incremental Transformer on Structural Priors
Viaarxiv icon

MVSFormer: Multi-View Stereo with Pre-trained Vision Transformers and Temperature-based Depth

Aug 08, 2022
Chenjie Cao, Xinlin Ren, Yanwei Fu

Figure 1 for MVSFormer: Multi-View Stereo with Pre-trained Vision Transformers and Temperature-based Depth
Figure 2 for MVSFormer: Multi-View Stereo with Pre-trained Vision Transformers and Temperature-based Depth
Figure 3 for MVSFormer: Multi-View Stereo with Pre-trained Vision Transformers and Temperature-based Depth
Figure 4 for MVSFormer: Multi-View Stereo with Pre-trained Vision Transformers and Temperature-based Depth
Viaarxiv icon