Picture for Sunghwan Hong

Sunghwan Hong

D^2USt3R: Enhancing 3D Reconstruction with 4D Pointmaps for Dynamic Scenes

Add code
Apr 08, 2025
Viaarxiv icon

Cross-View Completion Models are Zero-shot Correspondence Estimators

Add code
Dec 12, 2024
Viaarxiv icon

PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting

Add code
Oct 29, 2024
Viaarxiv icon

Towards Open-Vocabulary Semantic Segmentation Without Semantic Labels

Add code
Sep 30, 2024
Figure 1 for Towards Open-Vocabulary Semantic Segmentation Without Semantic Labels
Figure 2 for Towards Open-Vocabulary Semantic Segmentation Without Semantic Labels
Figure 3 for Towards Open-Vocabulary Semantic Segmentation Without Semantic Labels
Figure 4 for Towards Open-Vocabulary Semantic Segmentation Without Semantic Labels
Viaarxiv icon

Unifying Feature and Cost Aggregation with Transformers for Semantic and Visual Correspondence

Add code
Mar 17, 2024
Figure 1 for Unifying Feature and Cost Aggregation with Transformers for Semantic and Visual Correspondence
Figure 2 for Unifying Feature and Cost Aggregation with Transformers for Semantic and Visual Correspondence
Figure 3 for Unifying Feature and Cost Aggregation with Transformers for Semantic and Visual Correspondence
Figure 4 for Unifying Feature and Cost Aggregation with Transformers for Semantic and Visual Correspondence
Viaarxiv icon

Unifying Correspondence, Pose and NeRF for Pose-Free Novel View Synthesis from Stereo Pairs

Add code
Dec 12, 2023
Viaarxiv icon

Large Language Models are Frame-level Directors for Zero-shot Text-to-Video Generation

Add code
May 23, 2023
Viaarxiv icon

CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation

Add code
Mar 21, 2023
Viaarxiv icon

Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondence

Add code
Oct 06, 2022
Figure 1 for Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondence
Figure 2 for Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondence
Figure 3 for Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondence
Figure 4 for Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondence
Viaarxiv icon

Integrative Feature and Cost Aggregation with Transformers for Dense Correspondence

Add code
Sep 20, 2022
Figure 1 for Integrative Feature and Cost Aggregation with Transformers for Dense Correspondence
Figure 2 for Integrative Feature and Cost Aggregation with Transformers for Dense Correspondence
Figure 3 for Integrative Feature and Cost Aggregation with Transformers for Dense Correspondence
Figure 4 for Integrative Feature and Cost Aggregation with Transformers for Dense Correspondence
Viaarxiv icon