Thomas J. Cashman
7 papers · 2017–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Conference Polyglot (3) π Academic Marathon (8) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (18) π§ Keyword Pioneer
π£
Hot Topic Early Bird
π
Cross-Pollinator
(15)
Conferences
ICCV (4)
CVPR (2)
ECCV (1)
Top co-authors
Keywords
synthetic datum
(2)
3d reconstruction
(2)
pose estimation
(1)
face analysis
(1)
depth estimation
(1)
surface normal estimation
(1)
human pose estimation
(1)
object tracking
(1)
motion generation
(1)
variational autoencoder
(1)
3d gaussian splatting
(1)
neural radiance field
(1)
uncertainty estimation
(1)
flow-based model
(1)
camera pose
(1)
model efficiency
(1)
view synthesis
(1)
3d avatar
(1)
mixed reality
(1)
foreground segmentation
(1)
Papers
VoluMe - Authentic 3D Video Calls from Live Gaussian Splat Prediction
ICCV 2025
DAViD: Data-efficient and Accurate Vision Models from Synthetic Data
ICCV 2025
FLAG: Flow-Based 3D Avatar Generation From Sparse Observations
CVPR 2022
Full-Body Motion From a Single Head-Mounted Device: Generating SMPL Poses From Partial Observations
ICCV 2021
Fake It Till You Make It: Face Analysis in the Wild Using Synthetic Data Alone
ICCV 2021
The Phong Surface: Efficient 3D Model Fitting using Lifted Optimization
ECCV 2020
An Efficient Background Term for 3D Reconstruction and Tracking With Smooth Surface Models
CVPR 2017