skip to main content


Search for: All records

Creators/Authors contains: "Freeman, William T."

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. Free, publicly-accessible full text available October 1, 2025
  2. Free, publicly-accessible full text available June 1, 2025
  3. Denoising diffusion models have emerged as a powerful class of generative models capable of capturing the distributions of complex, real-world signals. However, current approaches can only model distributions for which training samples are directly accessible, which is not the case in many real-world tasks. In inverse graphics, for instance, we seek to sample from a distribution over 3D scenes consistent with an image but do not have access to ground-truth 3D scenes, only 2D images. We present a new class of denoising diffusion probabilistic models that learn to sample from distributions of signals that are never observed directly, but instead are only measured through a known differentiable forward model that generates partial observations of the unknown signal. To accomplish this, we directly integrate the forward model into the denoising process. At test time, our approach enables us to sample from the distribution over underlying signals consistent with some partial observation. We demonstrate the efficacy of our approach on three challenging computer vision tasks. For instance, in inverse graphics, we demonstrate that our model enables us to directly sample from the distribution 3D scenes consistent with a single 2D input image. 
    more » « less
  4. Denoising diffusion models have emerged as a powerful class of generative models capable of capturing the distributions of complex, real-world signals. However, current approaches can only model distributions for which training samples are directly accessible, which is not the case in many real-world tasks. In inverse graphics, for instance, we seek to sample from a distribution over 3D scenes consistent with an image but do not have access to ground-truth 3D scenes, only 2D images. We present a new class of denoising diffusion probabilistic models that learn to sample from distributions of signals that are never observed directly, but instead are only measured through a known differentiable forward model that generates partial observations of the unknown signal. To accomplish this, we directly integrate the forward model into the denoising process. At test time, our approach enables us to sample from the distribution over underlying signals consistent with some partial observation. We demonstrate the efficacy of our approach on three challenging computer vision tasks. For instance, in inverse graphics, we demonstrate that our model enables us to directly sample from the distribution 3D scenes consistent with a single 2D input image. 
    more » « less
  5. We study the problem of extracting biometric informa- tion of individuals by looking at shadows of objects cast on diffuse surfaces. We show that the biometric information leakage from shadows can be sufficient for reliable identity inference under representative scenarios via a maximum like- lihood analysis. We then develop a learning-based method that demonstrates this phenomenon in real settings, exploit- ing the subtle cues in the shadows that are the source of the leakage without requiring any labeled real data. In par- ticular, our approach relies on building synthetic scenes composed of 3D face models obtained from a single photo- graph of each identity. We transfer what we learn from the synthetic data to the real data using domain adaptation in a completely unsupervised way. Our model is able to general- ize well to the real domain and is robust to several variations in the scenes. We report high classification accuracies in an identity classification task that takes place in a scene with unknown geometry and occluding objects. 
    more » « less
  6. We present a method to map 2D image observations of a scene to a persistent 3D scene representation, enabling novel view synthesis and disentangled representation of the movable and immovable components of the scene. Motivated by the bird’s-eye-view (BEV) representation commonly used in vision and robotics, we propose conditional neural groundplans, ground-aligned 2D feature grids, as persistent and memory-efficient scene representations. Our method is trained self-supervised from unlabeled multi-view observations using differentiable rendering, and learns to complete geometry and appearance of occluded regions. In addition, we show that we can leverage multi-view videos at training time to learn to separately reconstruct static and movable components of the scene from a single image at test time. The ability to separately reconstruct movable objects enables a variety of downstream tasks using simple heuristics, such as extraction of object-centric 3D representations, novel view synthesis, instance-level segmentation, 3D bounding box prediction, and scene editing. This highlights the value of neural groundplans as a backbone for efficient 3D scene understanding models. 
    more » « less
  7. High-resolution simulations can deliver great visual quality, but they are often limited by available memory, especially on GPUs. We present a compiler for physical simulation that can achieve both high performance and significantly reduced memory costs, by enabling flexible and aggressive quantization. Low-precision ("quantized") numerical data types are used and packed to represent simulation states, leading to reduced memory space and bandwidth consumption. Quantized simulation allows higher resolution simulation with less memory, which is especially attractive on GPUs. Implementing a quantized simulator that has high performance and packs the data tightly for aggressive storage reduction would be extremely labor-intensive and error-prone using a traditional programming language. To make the creation of quantized simulation practical, we have developed a new set of language abstractions and a compilation system. A suite of tailored domain-specific optimizations ensure quantized simulators often run as fast as the full-precision simulators, despite the overhead of encoding-decoding the packed quantized data types. Our programming language and compiler, based on Taichi , allow developers to effortlessly switch between different full-precision and quantized simulators, to explore the full design space of quantization schemes, and ultimately to achieve a good balance between space and precision. The creation of quantized simulation with our system has large benefits in terms of memory consumption and performance, on a variety of hardware, from mobile devices to workstations with high-end GPUs. We can simulate with levels of resolution that were previously only achievable on systems with much more memory, such as multiple GPUs. For example, on a single GPU, we can simulate a Game of Life with 20 billion cells (8× compression per pixel), an Eulerian fluid system with 421 million active voxels (1.6× compression per voxel), and a hybrid Eulerian-Lagrangian elastic object simulation with 235 million particles (1.7× compression per particle). At the same time, quantized simulations create physically plausible results. Our quantization techniques are complementary to existing acceleration approaches of physical simulation: they can be used in combination with these existing approaches, such as sparse data structures, for even higher scalability and performance. 
    more » « less
  8. null (Ed.)
  9. The Event Horizon Telescope (EHT) observation of M87in 2018 has revealed a ring with a diameter that is consistent with the 2017 observation. The brightest part of the ring is shifted to the southwest from the southeast. In this paper, we provide theoretical interpretations for the multi-epoch EHT observations for M87by comparing a new general relativistic magnetohydrodynamics model image library with the EHT observations for M87in both 2017 and 2018. The model images include aligned and tilted accretion with parameterized thermal and nonthermal synchrotron emission properties. The 2018 observation again shows that the spin vector of the M87supermassive black hole is pointed away from Earth. A shift of the brightest part of the ring during the multi-epoch observations can naturally be explained by the turbulent nature of black hole accretion, which is supported by the fact that the more turbulent retrograde models can explain the multi-epoch observations better than the prograde models. The EHT data are inconsistent with the tilted models in our model image library. Assuming that the black hole spin axis and its large-scale jet direction are roughly aligned, we expect the brightest part of the ring to be most commonly observed 90 deg clockwise from the forward jet. This prediction can be statistically tested through future observations.

     
    more » « less
    Free, publicly-accessible full text available January 1, 2026