Picture for Sicheng Mo

Sicheng Mo

SimGen: Simulator-conditioned Driving Scene Generation

Add code
Jun 13, 2024
Viaarxiv icon

Ctrl-X: Controlling Structure and Appearance for Text-To-Image Generation Without Guidance

Add code
Jun 11, 2024
Viaarxiv icon

SnAG: Scalable and Accurate Video Grounding

Add code
Apr 05, 2024
Viaarxiv icon

FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Condition

Add code
Dec 12, 2023
Figure 1 for FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Condition
Figure 2 for FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Condition
Figure 3 for FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Condition
Figure 4 for FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Condition
Viaarxiv icon

Where a Strong Backbone Meets Strong Features -- ActionFormer for Ego4D Moment Queries Challenge

Add code
Nov 16, 2022
Viaarxiv icon

A Simple Transformer-Based Model for Ego4D Natural Language Queries Challenge

Add code
Nov 16, 2022
Viaarxiv icon

Physics to the Rescue: Deep Non-line-of-sight Reconstruction for High-speed Imaging

Add code
May 03, 2022
Figure 1 for Physics to the Rescue: Deep Non-line-of-sight Reconstruction for High-speed Imaging
Figure 2 for Physics to the Rescue: Deep Non-line-of-sight Reconstruction for High-speed Imaging
Figure 3 for Physics to the Rescue: Deep Non-line-of-sight Reconstruction for High-speed Imaging
Figure 4 for Physics to the Rescue: Deep Non-line-of-sight Reconstruction for High-speed Imaging
Viaarxiv icon