Our group focuses on synthetic image generation, computational photography, digital manufacturing, and geometry.
Our research spans most aspects of computer graphics, picture generation and creation to geometry processing, with emphasis on mathematical analysis, signal processing, inspiration from perceptual sciences, and a broad range of applications including digital manufacturing, imaging, scientific computing, and animation.
First-ever imaging privacy threats from non-imaging components (ambient light sensors) of smart devices. An idea inspired by George Orwell's dystopian novel 1984 -- "Big Brother is watching you" through a two-way TV-like telescreen.
First-ever imaging privacy threats from non-imaging components (ambient light sensors) of smart devices. An idea inspired by George Orwell's dystopian novel 1984 -- "Big Brother is watching you" through a two-way TV-like telescreen.
This work presents a differentiable cloth simulator that extends a state-of-the-art cloth simulator based on Projective Dynamics (PD) and with dry frictional contact. A novel back-propagation technique is proposed to accelerate gradient computation. We demonstrate the effectiveness of the simulator through inverse tasks including system identification, trajectory optimization for assisted dressing, closed-loop control, inverse design.
To achieve high-quality photo lighting in challenging environments, our prototype camera dynamically reconstructs a 3D scene model and directs a motor-controlled flash head at nearby walls and ceilings for soft indirect illumination.
A new algorithm solves complicated partial differential equations by breaking them down into simpler problems, potentially guiding computer graphics and geometry processing.
DenseAV, developed at MIT, learns to parse and understand the meaning of language just by watching videos of people talking, with potential applications in multimedia search, language learning, and robotics.
“Alchemist” system adjusts the material attributes of specific objects within images to potentially modify video game models to fit different environments, fine-tune VFX, and diversify robotic training.
Novel method makes tools like Stable Diffusion and DALL-E-3 faster by simplifying the image-generating process to a single step while maintaining or enhancing image quality.
Given an image, MIT CSAIL's machine-learning system can smoothly separate the objects in it, enabling easier editing of photos - and, eventually, videos
