About

Brian Curless is a Professor in the Allen School of Computer Science & Engineering at the University of Washington. His professional homepage lists his affiliation with the UW Reality Lab, the Graphics and Imaging Laboratory (GRAIL), and the Animation Research Labs. He teaches courses in computer graphics at the undergraduate, graduate, and professional masters levels, including CSE 457, CSE 557, CSEP 557, and CSE 558. His research spans a broad range of topics in computer graphics, 3D photography, computational photography, and videography, with a focus on image-based modeling, 3D reconstruction, and novel imaging techniques. Curless has contributed to the development of software tools such as VripPack for volumetric range image processing and Snoop, an image magnifier for Windows. His extensive publication record includes pioneering work on volumetric methods for building complex models from range images, multi-view stereo reconstruction, photometric stereo, and light field matting. His research has been presented at leading conferences such as CVPR, SIGGRAPH, ECCV, and ICCV, reflecting his significant contributions to the fields of computer vision and graphics.

Research topics

• Computer Science
• Artificial Intelligence
• Computer vision
• Remote sensing
• Physics
• Geology
• Computer graphics (images)
• Telecommunications
• Mathematics

Selected publications

• COMIC: Agentic Sketch Comedy Generation

  arXiv (Cornell University) · 2026-03-11

  preprintOpen access

  We propose a fully automated AI system that produces short comedic videos similar to sketch shows such as Saturday Night Live. Starting with character references, the system employs a population of agents loosely based on real production studio roles, structured to optimize the quality and diversity of ideas and outputs through iterative competition, evaluation, and improvement. A key contribution is the introduction of LLM critics aligned with real viewer preferences through the analysis of a corpus of comedy videos on YouTube to automatically evaluate humor. Our experiments show that our framework produces results approaching the quality of professionally produced sketches while demonstrating state-of-the-art performance in video generation.

  PublisherDOI

• COMIC: Agentic Sketch Comedy Generation

  ArXiv.org · 2026-03-11

  articleOpen access

  We propose a fully automated AI system that produces short comedic videos similar to sketch shows such as Saturday Night Live. Starting with character references, the system employs a population of agents loosely based on real production studio roles, structured to optimize the quality and diversity of ideas and outputs through iterative competition, evaluation, and improvement. A key contribution is the introduction of LLM critics aligned with real viewer preferences through the analysis of a corpus of comedy videos on YouTube to automatically evaluate humor. Our experiments show that our framework produces results approaching the quality of professionally produced sketches while demonstrating state-of-the-art performance in video generation.

  PublisherOA PDF

• How Animals Dance (When You're Not Looking)

  ArXiv.org · 2025-05-29

  preprintOpen access

  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 a novel high-level control signal for dance video generation. These patterns can be automatically estimated from human dance videos. Starting from a few keyframes representing distinct animal poses, generated via text-to-image prompting or GPT-4o, we formulate dance synthesis as a graph optimization problem that seeks the optimal keyframe structure to satisfy a specified choreography pattern of beats. We also introduce an approach for mirrored pose image generation, essential for capturing symmetry in dance. In-between frames are synthesized using an video diffusion model. With as few as six input keyframes, our method can produce up to 30 seconds dance videos across a wide range of animals and music tracks.

  PublisherOA PDFDOI

• Generating Fit Check Videos with a Handheld Camera

  ArXiv.org · 2025-05-29

  preprintOpen access

  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 devices. Our approach takes as input two static photos (front and back) of you in a mirror, along with an IMU motion reference that you perform while holding your mobile phone, and synthesizes a realistic video of you performing a similar target motion. We enable rendering into a new scene, with consistent illumination and shadows. We propose a novel video diffusion-based model to achieve this. Specifically, we propose a parameter-free frame generation strategy and a multi-reference attention mechanism to effectively integrate appearance information from both the front and back selfies into the video diffusion model. Further, we introduce an image-based fine-tuning strategy to enhance frame sharpness and improve shadows and reflections generation for more realistic human-scene composition.

  PublisherOA PDFDOI

• View2CAD: Reconstructing View-Centric CAD Models from Single RGB-D Scans

  ArXiv.org · 2025-04-05

  preprintOpen accessSenior author

  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, editing, and fabrication. However, B-Reps are often inaccessible due to conversion to more standardized, less expressive geometry formats. Existing methods to recover B-Reps from measured data require complete, noise-free 3D data, which are laborious to obtain. We alleviate this difficulty by enabling the precise reconstruction of CAD shapes from a single RGB-D image. We propose a method that addresses the challenge of reconstructing only the observed geometry from a single view. To allow for these partial observations, and to avoid hallucinating incorrect geometry, we introduce a novel view-centric B-rep (VB-Rep) representation, which incorporates structures to handle visibility limits and encode geometric uncertainty. We combine panoptic image segmentation with iterative geometric optimization to refine and improve the reconstruction process. Our results demonstrate high-quality reconstruction on synthetic and real RGB-D data, showing that our method can bridge the reality gap.

  PublisherOA PDFDOI

• Don't look at the camera: Achieving perceived eye contact in remote video communication

  Journal of Vision · 2025-09-11

  articleOpen access

  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 impacts these social cues, because most technologies do not support natural eye contact. We consider the question of how to best achieve the perception of eye contact when a person is captured by a camera and then rendered on a two-dimensional display. To test this, 17 participants were asked to rate whether 3 actors, photographed while looking at different vertical locations, were making eye contract (yes-no analysis), or were looking up or down (up-down analysis). We quantitatively assessed the gaze direction required to optimize the perception of eye contact with the camera lens. Contrary to conventional wisdom, which suggests looking directly into the camera leads to the perception of eye contact, results from both the yes-no and the up-down analyses showed that it is preferable to look approximately 2° below the camera lens. These results provide a surprising answer to the question of where to look to convey an impression of eye contact in screen-mediated interactions.

  PublisherOA PDFDOI

• GenEscape: Hierarchical Multi-Agent Generation of Escape Room Puzzles

  ArXiv.org · 2025-06-27

  preprintOpen access

  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, we propose a hierarchical multi-agent framework that decomposes this task into structured stages: functional design, symbolic scene graph reasoning, layout synthesis, and local image editing. Specialized agents collaborate through iterative feedback to ensure the scene is visually coherent and functionally solvable. Experiments show that agent collaboration improves output quality in terms of solvability, shortcut avoidance, and affordance clarity, while maintaining visual quality.

  PublisherOA PDFDOI

• GenEscape: Hierarchical Multi-Agent Generation of Escape Room Puzzles

  2025-10-19

  article

  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, we propose a hierarchical multi-agent framework that decomposes this task into structured stages: functional design, symbolic scene graph reasoning, layout synthesis, and local image editing. Specialized agents collaborate through iterative feedback to ensure the scene is visually coherent and functionally solvable. Experiments show that agent collaboration improves output quality in terms of solvability, shortcut avoidance, and affordance clarity, while maintaining visual quality.

  PublisherDOI

• 3D convolutional deep learning for nonlinear estimation of body composition from whole body morphology

  npj Digital Medicine · 2025-02-02 · 3 citations

  articleOpen access

  Abstract Body composition prediction from 3D optical imagery has previously been studied with linear algorithms. In this study, we present a novel application of deep 3D convolutional graph networks and nonlinear Gaussian process regression for human body shape parameterization and body composition estimation. We trained and tested linear and nonlinear models with ablation studies on a novel ensemble body shape dataset containing 4286 scans. Nonlinear GPR produced up to a 20% reduction in prediction error and up to a 30% increase in precision over linear regression for both sexes in 10 tested body composition variables. Deep shape features produced 6–8% reduction in prediction error over linear PCA features for males only, and a 4–14% reduction in precision error for both sexes. All coefficients of determination ( R 2 ) for all predicted variables were above 0.86 and achieved lower estimation RMSEs than all previous work on 10 metrics of body composition.

  PublisherOA PDFDOI

• Infinite Texture: Text-guided High Resolution Diffusion Texture Synthesis

  arXiv (Cornell University) · 2024-05-13

  preprintOpen access

  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 of the model. We seed this fine-tuning process with a sample texture patch, which can be optionally generated from a text-to-image model like DALL-E 2. At generation time, our fine-tuned diffusion model is used through a score aggregation strategy to generate output texture images of arbitrary resolution on a single GPU. We compare synthesized textures from our method to existing work in patch-based and deep learning texture synthesis methods. We also showcase two applications of our generated textures in 3D rendering and texture transfer.

  PublisherOA PDFDOI

Recent grants

• VEC: Medium: The 3D Memex for Virtual Teleportation

  NSF · $739k · 2015–2019

• MRI: The Digital Eye--A Visual Measurement and Processing Facility

  NSF · $500k · 2003–2007

Frequent coauthors

• Michael Wong

  University of Hawaii Cancer Center

  81 shared

• Nisa N. Kelly

  University of Washington

  81 shared

• Steven B. Heymsfield

  Louisiana State University

  78 shared

• Steven M. Seitz

  University of Washington

  75 shared

• Isaac Y. Tian

  72 shared

• Andrea K. Garber

  University of California, San Francisco

  70 shared

• Jason Liu

  Wayne State University

  64 shared

• Yong Liu

  Guangzhou First People's Hospital

  64 shared

Labs

• Graphics and Imaging Laboratory (GRAIL)PI

Education

• B.S.

  University of Texas at Austin

• M.S.

  Stanford

  1991

• Ph.D.

  Stanford

  1997