Brian Curless
YOU?
Author Swipe
View article: Don't look at the camera: Achieving perceived eye contact in remote video communication
Don't look at the camera: Achieving perceived eye contact in remote video communication Open
Eye contact is a crucial aspect of social interaction, conveying social cues based on the direction of one's gaze. Perceiving eye contact affects behavior and social processing. The widespread use of remote video conferencing technologies …
View article: Fast and Scalable Mixed Precision Euclidean Distance Calculations Using GPU Tensor Cores
Fast and Scalable Mixed Precision Euclidean Distance Calculations Using GPU Tensor Cores Open
Modern GPUs are equipped with tensor cores (TCs) that are commonly used for matrix multiplication in artificial intelligence workloads. However, because they have high computational throughput, they can lead to significant performance gain…
View article: GenEscape: Hierarchical Multi-Agent Generation of Escape Room Puzzles
GenEscape: Hierarchical Multi-Agent Generation of Escape Room Puzzles Open
We challenge text-to-image models with generating escape room puzzle images that are visually appealing, logically solid, and intellectually stimulating. While base image models struggle with spatial relationships and affordance reasoning,…
View article: How Animals Dance (When You're Not Looking)
How Animals Dance (When You're Not Looking) Open
We present a framework for generating music-synchronized, choreography aware animal dance videos. Our framework introduces choreography patterns -- structured sequences of motion beats that define the long-range structure of a dance -- as …
View article: Generating Fit Check Videos with a Handheld Camera
Generating Fit Check Videos with a Handheld Camera Open
Self-captured full-body videos are popular, but most deployments require mounted cameras, carefully-framed shots, and repeated practice. We propose a more convenient solution that enables full-body video capture using handheld mobile devic…
View article: View2CAD: Reconstructing View-Centric CAD Models from Single RGB-D Scans
View2CAD: Reconstructing View-Centric CAD Models from Single RGB-D Scans Open
Parametric CAD models, represented as Boundary Representations (B-reps), are foundational to modern design and manufacturing workflows, offering the precision and topological breakdown required for downstream tasks such as analysis, editin…
View article: VidPanos: Generative Panoramic Videos from Casual Panning Videos
VidPanos: Generative Panoramic Videos from Casual Panning Videos Open
Panoramic image stitching provides a unified, wide-angle view of a scene that extends beyond the camera's field of view. Stitching frames of a panning video into a panoramic photograph is a well-understood problem for stationary scenes, bu…
View article: Inverse Painting: Reconstructing The Painting Process
Inverse Painting: Reconstructing The Painting Process Open
Given an input painting, we reconstruct a time-lapse video of how it may have been painted. We formulate this as an autoregressive image generation problem, in which an initially blank "canvas" is iteratively updated. The model learns from…
View article: Generative Inbetweening: Adapting Image-to-Video Models for Keyframe Interpolation
Generative Inbetweening: Adapting Image-to-Video Models for Keyframe Interpolation Open
We present a method for generating video sequences with coherent motion between a pair of input key frames. We adapt a pretrained large-scale image-to-video diffusion model (originally trained to generate videos moving forward in time from…
View article: ExtraNeRF: Visibility-Aware View Extrapolation of Neural Radiance Fields with Diffusion Models
ExtraNeRF: Visibility-Aware View Extrapolation of Neural Radiance Fields with Diffusion Models Open
We propose ExtraNeRF, a novel method for extrapolating the range of views handled by a Neural Radiance Field (NeRF). Our main idea is to leverage NeRFs to model scene-specific, fine-grained details, while capitalizing on diffusion models t…
View article: Infinite Texture: Text-guided High Resolution Diffusion Texture Synthesis
Infinite Texture: Text-guided High Resolution Diffusion Texture Synthesis Open
We present Infinite Texture, a method for generating arbitrarily large texture images from a text prompt. Our approach fine-tunes a diffusion model on a single texture, and learns to embed that statistical distribution in the output domain…
View article: Don't Look at the Camera: Achieving Perceived Eye Contact
Don't Look at the Camera: Achieving Perceived Eye Contact Open
We consider the question of how to best achieve the perception of eye contact when a person is captured by camera and then rendered on a 2D display. For single subjects photographed by a camera, conventional wisdom tells us that looking di…
View article: Animating Street View
Animating Street View Open
We present a system that automatically brings street view imagery to life by\npopulating it with naturally behaving, animated pedestrians and vehicles. Our\napproach is to remove existing people and vehicles from the input image, insert\nm…
View article: Generative Powers of Ten
Generative Powers of Ten Open
We present a method that uses a text-to-image model to generate consistent content across multiple image scales, enabling extreme semantic zooms into a scene, e.g., ranging from a wide-angle landscape view of a forest to a macro shot of an…
View article: Total Selfie: Generating Full-Body Selfies
Total Selfie: Generating Full-Body Selfies Open
We present a method to generate full-body selfies from photographs originally taken at arms length. Because self-captured photos are typically taken close up, they have limited field of view and exaggerated perspective that distorts facial…
View article: Controllable Light Diffusion for Portraits
Controllable Light Diffusion for Portraits Open
We introduce light diffusion, a novel method to improve lighting in portraits, softening harsh shadows and specular highlights while preserving overall scene illumination. Inspired by professional photographers' diffusers and scrims, our m…
View article: PersonNeRF: Personalized Reconstruction from Photo Collections
PersonNeRF: Personalized Reconstruction from Photo Collections Open
We present PersonNeRF, a method that takes a collection of photos of a subject (e.g. Roger Federer) captured across multiple years with arbitrary body poses and appearances, and enables rendering the subject with arbitrary novel combinatio…
View article: Mates2Motion: Learning How Mechanical CAD Assemblies Work
Mates2Motion: Learning How Mechanical CAD Assemblies Work Open
We describe our work on inferring the degrees of freedom between mated parts in mechanical assemblies using deep learning on CAD representations. We train our model using a large dataset of real-world mechanical assemblies consisting of CA…
View article: A device‐agnostic shape model for automated body composition estimates from 3D optical scans
A device‐agnostic shape model for automated body composition estimates from 3D optical scans Open
Background Many predictors of morbidity caused by metabolic disease are associated with body shape. 3D optical (3DO) scanning captures body shape and has been shown to accurately and precisely predict body composition variables associated …
View article: 3D Moments from Near-Duplicate Photos
3D Moments from Near-Duplicate Photos Open
We introduce 3D Moments, a new computational photography effect. As input we take a pair of near-duplicate photos, i.e., photos of moving subjects from similar viewpoints, common in people's photo collections. As output, we produce a video…
View article: FILM: Frame Interpolation for Large Motion
FILM: Frame Interpolation for Large Motion Open
We present a frame interpolation algorithm that synthesizes multiple intermediate frames from two input images with large in-between motion. Recent methods use multiple networks to estimate optical flow or depth and a separate network dedi…
View article: HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video
HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video Open
We introduce a free-viewpoint rendering method -- HumanNeRF -- that works on a given monocular video of a human performing complex body motions, e.g. a video from YouTube. Our method enables pausing the video at any frame and rendering the…
View article: A Light Stage on Every Desk
A Light Stage on Every Desk Open
Every time you sit in front of a TV or monitor, your face is actively illuminated by time-varying patterns of light. This paper proposes to use this time-varying illumination for synthetic relighting of your face with any new illumination …