Picture for Dilin Wang

Dilin Wang

3D Mesh Editing using Masked LRMs

Add code
Dec 11, 2024
Viaarxiv icon

MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds

Add code
Dec 09, 2024
Viaarxiv icon

MVDiffusion++: A Dense High-resolution Multi-view Diffusion Model for Single or Sparse-view 3D Object Reconstruction

Add code
Feb 20, 2024
Viaarxiv icon

SteinDreamer: Variance Reduction for Text-to-3D Score Distillation via Stein Identity

Add code
Dec 31, 2023
Viaarxiv icon

Taming Mode Collapse in Score Distillation for Text-to-3D Generation

Add code
Dec 31, 2023
Figure 1 for Taming Mode Collapse in Score Distillation for Text-to-3D Generation
Figure 2 for Taming Mode Collapse in Score Distillation for Text-to-3D Generation
Figure 3 for Taming Mode Collapse in Score Distillation for Text-to-3D Generation
Figure 4 for Taming Mode Collapse in Score Distillation for Text-to-3D Generation
Viaarxiv icon

EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything

Add code
Dec 01, 2023
Viaarxiv icon

Drag View: Generalizable Novel View Synthesis with Unposed Imagery

Add code
Oct 05, 2023
Viaarxiv icon

TODM: Train Once Deploy Many Efficient Supernet-Based RNN-T Compression For On-device ASR Models

Add code
Sep 05, 2023
Figure 1 for TODM: Train Once Deploy Many Efficient Supernet-Based RNN-T Compression For On-device ASR Models
Figure 2 for TODM: Train Once Deploy Many Efficient Supernet-Based RNN-T Compression For On-device ASR Models
Figure 3 for TODM: Train Once Deploy Many Efficient Supernet-Based RNN-T Compression For On-device ASR Models
Figure 4 for TODM: Train Once Deploy Many Efficient Supernet-Based RNN-T Compression For On-device ASR Models
Viaarxiv icon

Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts

Add code
Jun 08, 2023
Viaarxiv icon

PathFusion: Path-consistent Lidar-Camera Deep Feature Fusion

Add code
Dec 12, 2022
Viaarxiv icon