William T. Freeman

William T. Freeman

Auto-generated profile, based on publicly available information

William T. Freeman

Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology Cambridge 02139 USA

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 February 2007 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
CLCe Liu
Ce Liu
HSHeung-Yeung Shum
Heung-Yeung Shum
WFWilliam T. Freeman
William T. Freeman

19 September 2024 in International Journal of Computer Vision
Verified
Journal Article
Open access
PDF file
GXGuangxuan Xiao
Guangxuan Xiao
TYTianwei Yin
Tianwei Yin
WFWilliam T. Freeman
William T. Freeman
FDFrédo Durand
Frédo Durand
SHSong Han
Song Han
Diffusion models excel at text-to-image generation, especially in subject-driven generation for personalized images. However, existing methods are inefficient due to the subject-specific fine-tuning, which is computationally intensive and hampers efficient deployment. Moreover, existing methods struggle with multi-subject generation as they often blend identity among subjects. We present FastComposer which enables efficient, personalized, multi-subject text-to-image generation without fine-tuning. FastComposer uses subject embeddings extracted by an image encoder to augment the generic text conditioning in diffusion models, enabling personalized image generation based on subject images and textual instructions with only forward passes. To address the identity blending problem in the multi-subject generation, FastComposer proposes cross-attention localization supervision during training, enforcing the attention of reference subjects localized to the correct regions in the target images. Naively conditioning on subject embeddings results in subject overfitting. FastComposer proposes delayed subject conditioning in the denoising step to maintain both identity and editability in subject-driven image generation. FastComposer generates images of multiple unseen individuals with different styles, actions, and contexts. It achieves 300 $$\times $$ × –2500 $$\times $$ × speedup compared to fine-tuning-based methods and requires zero extra storage for new subjects. FastComposer paves the way for efficient, personalized, and high-quality multi-subject image creation. Code, model, and dataset are available here (https://github.com/mit-han-lab/fastcomposer).

1 June 2007
Verified
Conference Paper
Closed access
YWYair Weiss
Yair Weiss
WFWilliam T. Freeman
William T. Freeman
Many low-level vision algorithms assume a prior probability over images, and there has been great interest in trying to learn this prior from examples. Since images are very non Gaussian, high dimensional, continuous signals, learning their distribution presents a tremendous computational challenge. Perhaps the most successful recent algorithm is the Fields of Experts (FOE) [20] model which has shown impressive performance by modeling image statistics with a product of potentials defined on filter outputs. However, as in previous models of images based on filter outputs [30], calculating the probability of an image given the model requires evaluating an intractable partition function. This makes learning very slow (requires Monte-Carlo sampling at every step) and makes it virtually impossible to compare the likelihood of two different models. Given this computational difficulty, it is hard to say whether nonintu-itive features learned by such models represent a true property of natural images or an artifact of the approximations used during learning. In this paper we present (1) tractable lower and upper bounds on the partition function of models based on filter outputs and (2) efficient learning algorithms that do not require any sampling. Our results are based on recent results in machine learning that deal with Gaussian potentials. We extend these results to non-Gaussian potentials and derive a novel, basis rotation algorithm for approximating the maximum likelihood filters. Our results allow us to (1) rigorously compare the likelihood of different models and (2) calculate high likelihood models of natural image statistics in a matter of minutes. Applying our results to previous models shows that the nonintuitive features are not an artifact of the learning process but rather are capturing robust properties of natural images.

1 September 2017 in Journal of Infrastructure Systems
Verified
Journal Article
Closed access
JCJustin G. Chen
Justin G. Chen
ADAbe Davis
Abe Davis
NWNeal Wadhwa
Neal Wadhwa
FDFrédo Durand
Frédo Durand
WFWilliam T. Freeman
William T. Freeman
OBOral Büyüköztürk
Oral Büyüköztürk
Visual testing, as one of the oldest methods for nondestructive testing (NDT), plays a large role in the inspection of civil infrastructure. As NDT has evolved, more quantitative techniques have emerged such as vibration analysis. New computer vision techniques for analyzing the small motions in videos, collectively called motion magnification, have been recently developed, allowing quantitative measurement of the vibration behavior of structures from videos. Video cameras offer the benefit of long range measurement and can collect a large amount of data at once because each pixel is effectively a sensor. This paper presents a video camera-based vibration measurement methodology for civil infrastructure. As a proof of concept, measurements are made of an antenna tower on top of the Green Building on the campus of the Massachusetts Institute of Technology (MIT) from a distance of over 175 m, and the resonant frequency of the antenna tower on the roof is identified with an amplitude of 0.21 mm, whic...

9 August 2007 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
ESErik B. Sudderth
Erik B. Sudderth
ATAntonio Torralba
Antonio Torralba
WFWilliam T. Freeman
William T. Freeman
AWAlan S. Willsky
Alan S. Willsky

27 October 2016 in Galaxies
Verified
Journal Article
Open access
PDF file
VFVincent Fish
Vincent Fish
KAKazunori Akiyama
Kazunori Akiyama
KBKatherine L. Bouman
Katherine L. Bouman
ACAndrew Chael
Andrew Chael
MJMichael Johnson
Michael Johnson
TCThe Event Horizon Telescope Collaboration
The Event Horizon Telescope Collaboration
Originally developed to image the shadow region of the central black hole in Sagittarius A* and in the nearby galaxy M87, the Event Horizon Telescope (EHT) provides deep, very high angular resolution data on other active galactic nucleus (AGN) sources too. The challenges of working with EHT data have spurred the development of new image reconstruction algorithms. This work briefly reviews the status of the EHT and its utility for observing AGN sources, with emphasis on novel imaging techniques that offer the promise of better reconstructions at 1.3 mm and other wavelengths.