Picture for Wenhan Luo

Wenhan Luo

M-LRM: Multi-view Large Reconstruction Model

Add code
Jun 11, 2024
Viaarxiv icon

MIPI 2024 Challenge on Few-shot RAW Image Denoising: Methods and Results

Jun 11, 2024
Viaarxiv icon

Follow-Your-Pose v2: Multiple-Condition Guided Character Image Animation for Stable Pose Control

Jun 05, 2024
Viaarxiv icon

CoCoGesture: Toward Coherent Co-speech 3D Gesture Generation in the Wild

Add code
May 27, 2024
Viaarxiv icon

Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attention

Add code
May 19, 2024
Viaarxiv icon

Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts

Add code
May 18, 2024
Viaarxiv icon

Aux-NAS: Exploiting Auxiliary Labels with Negligibly Extra Inference Cost

Add code
May 09, 2024
Viaarxiv icon

Homography Guided Temporal Fusion for Road Line and Marking Segmentation

Add code
Apr 11, 2024
Figure 1 for Homography Guided Temporal Fusion for Road Line and Marking Segmentation
Figure 2 for Homography Guided Temporal Fusion for Road Line and Marking Segmentation
Figure 3 for Homography Guided Temporal Fusion for Road Line and Marking Segmentation
Figure 4 for Homography Guided Temporal Fusion for Road Line and Marking Segmentation
Viaarxiv icon

Context-Aware Integration of Language and Visual References for Natural Language Tracking

Add code
Mar 29, 2024
Figure 1 for Context-Aware Integration of Language and Visual References for Natural Language Tracking
Figure 2 for Context-Aware Integration of Language and Visual References for Natural Language Tracking
Figure 3 for Context-Aware Integration of Language and Visual References for Natural Language Tracking
Figure 4 for Context-Aware Integration of Language and Visual References for Natural Language Tracking
Viaarxiv icon

OMG: Occlusion-friendly Personalized Multi-concept Generation in Diffusion Models

Add code
Mar 16, 2024
Figure 1 for OMG: Occlusion-friendly Personalized Multi-concept Generation in Diffusion Models
Figure 2 for OMG: Occlusion-friendly Personalized Multi-concept Generation in Diffusion Models
Viaarxiv icon