Brown Visual Computing
@brownvc.bsky.social
visual.cs.brown.edu - vision, graphics, HCI, design+fabrication
FoundHand: Large-Scale Domain-Specific Learning for Controllable Hand Image Generation
ivl.cs.brown.edu/research/fou...
A dataset and foundational model for hand images. Tired of weird/malformed hands in your diffusion model outputs? FoundHand can fix them. (7/7)
ivl.cs.brown.edu/research/fou...
A dataset and foundational model for hand images. Tired of weird/malformed hands in your diffusion model outputs? FoundHand can fix them. (7/7)
FoundHand: Large-Scale Domain-Specific Learning for Controllable Hand Image Generation
The Interactive 3D Vision & Learning Lab (IVL) led by Srinath Sridhar, part of Brown Visual Computing, works on 3D computer vision and machine learning problems to better understand how humans interac...
ivl.cs.brown.edu
April 19, 2025 at 8:57 PM
FoundHand: Large-Scale Domain-Specific Learning for Controllable Hand Image Generation
ivl.cs.brown.edu/research/fou...
A dataset and foundational model for hand images. Tired of weird/malformed hands in your diffusion model outputs? FoundHand can fix them. (7/7)
ivl.cs.brown.edu/research/fou...
A dataset and foundational model for hand images. Tired of weird/malformed hands in your diffusion model outputs? FoundHand can fix them. (7/7)
UVGS: Reimagining Unstructured 3D Gaussian Splatting using UV Mapping
aashishrai3799.github.io/uvgs/
Shows how to compress a 3DGS representation of an object into a single RGB image which is amenable to analysis and generation with state-of-the-art image models. (6/7)
aashishrai3799.github.io/uvgs/
Shows how to compress a 3DGS representation of an object into a single RGB image which is amenable to analysis and generation with state-of-the-art image models. (6/7)
UVGS
UVGS
aashishrai3799.github.io
April 19, 2025 at 8:57 PM
UVGS: Reimagining Unstructured 3D Gaussian Splatting using UV Mapping
aashishrai3799.github.io/uvgs/
Shows how to compress a 3DGS representation of an object into a single RGB image which is amenable to analysis and generation with state-of-the-art image models. (6/7)
aashishrai3799.github.io/uvgs/
Shows how to compress a 3DGS representation of an object into a single RGB image which is amenable to analysis and generation with state-of-the-art image models. (6/7)
Zero-shot Monocular Scene Flow Estimation in the Wild
research.nvidia.com/labs/lpr/zer...
Take any two unposed views of a video and generate 3D points + 3D motion. Trained only on synthetic data, the model generalizes well to casual real-world videos or even robot pick and place. (5/7)
research.nvidia.com/labs/lpr/zer...
Take any two unposed views of a video and generate 3D points + 3D motion. Trained only on synthetic data, the model generalizes well to casual real-world videos or even robot pick and place. (5/7)
ZeroMSF
Zero-shot Monocular Scene Flow Estimation in the Wild
research.nvidia.com
April 19, 2025 at 8:57 PM
Zero-shot Monocular Scene Flow Estimation in the Wild
research.nvidia.com/labs/lpr/zer...
Take any two unposed views of a video and generate 3D points + 3D motion. Trained only on synthetic data, the model generalizes well to casual real-world videos or even robot pick and place. (5/7)
research.nvidia.com/labs/lpr/zer...
Take any two unposed views of a video and generate 3D points + 3D motion. Trained only on synthetic data, the model generalizes well to casual real-world videos or even robot pick and place. (5/7)
Time of the Flight of the Gaussians: Optimizing Depth Indirectly in Dynamic Radiance Fields
visual.cs.brown.edu/projects/gft...
Models continuous-wave time of flight signals within Gaussian splatting, revealing ways to better optimize GS to converge in underconstrained monocular settings. (4/7)
visual.cs.brown.edu/projects/gft...
Models continuous-wave time of flight signals within Gaussian splatting, revealing ways to better optimize GS to converge in underconstrained monocular settings. (4/7)
GF-TöRF: Time of the Flight of the Gaussians
visual.cs.brown.edu
April 19, 2025 at 8:56 PM
Time of the Flight of the Gaussians: Optimizing Depth Indirectly in Dynamic Radiance Fields
visual.cs.brown.edu/projects/gft...
Models continuous-wave time of flight signals within Gaussian splatting, revealing ways to better optimize GS to converge in underconstrained monocular settings. (4/7)
visual.cs.brown.edu/projects/gft...
Models continuous-wave time of flight signals within Gaussian splatting, revealing ways to better optimize GS to converge in underconstrained monocular settings. (4/7)
GigaHands: A Massive Annotated Dataset of Bimanual Hand Activities
ivl.cs.brown.edu/research/gig...
A massive annotated dataset of bimanual hand activities. Opens up new applications in (conditional) hand motion generation, dynamic reconstruction, motion retargeting, and more. (3/7)
ivl.cs.brown.edu/research/gig...
A massive annotated dataset of bimanual hand activities. Opens up new applications in (conditional) hand motion generation, dynamic reconstruction, motion retargeting, and more. (3/7)
GigaHands: A Massive Annotated Dataset of Bimanual Hand Activities
The Interactive 3D Vision & Learning Lab (IVL) led by Srinath Sridhar, part of Brown Visual Computing, works on 3D computer vision and machine learning problems to better understand how humans interac...
ivl.cs.brown.edu
April 19, 2025 at 8:56 PM
GigaHands: A Massive Annotated Dataset of Bimanual Hand Activities
ivl.cs.brown.edu/research/gig...
A massive annotated dataset of bimanual hand activities. Opens up new applications in (conditional) hand motion generation, dynamic reconstruction, motion retargeting, and more. (3/7)
ivl.cs.brown.edu/research/gig...
A massive annotated dataset of bimanual hand activities. Opens up new applications in (conditional) hand motion generation, dynamic reconstruction, motion retargeting, and more. (3/7)
Pattern Analogies: Learning to Perform Programmatic Image Edits by Analogy
bardofcodes.github.io/patterns/
Analogy-based editing in-the-wild pattern images. Now you can take any image of a regular-grid tiling pattern and turn into, say, a radially-tiled version of the same pattern. (2/7)
bardofcodes.github.io/patterns/
Analogy-based editing in-the-wild pattern images. Now you can take any image of a regular-grid tiling pattern and turn into, say, a radially-tiled version of the same pattern. (2/7)
Pattern Analogies: Learning to Perform Programmatic Image Edits by Analogy
Pattern Analogies: Learning to Perform Programmatic Image Edits by Analogy
bardofcodes.github.io
April 19, 2025 at 8:56 PM
Pattern Analogies: Learning to Perform Programmatic Image Edits by Analogy
bardofcodes.github.io/patterns/
Analogy-based editing in-the-wild pattern images. Now you can take any image of a regular-grid tiling pattern and turn into, say, a radially-tiled version of the same pattern. (2/7)
bardofcodes.github.io/patterns/
Analogy-based editing in-the-wild pattern images. Now you can take any image of a regular-grid tiling pattern and turn into, say, a radially-tiled version of the same pattern. (2/7)