2s-DAS: Two-Stream Diffusion with Multi-Modal Fusion for Temporal Action Segmentation. [PDF]
J ImagingLi C +5 more
europepmc +1 more source
A Real‐Time Multi‐Scale Neural Representation for Complex Surface Reflectance
Computer Graphics Forum, EarlyView.Abstract Recent machine learning methods have significantly advanced the state of the art in the classic problem of representing surface appearance over angle, space, and scale. The models tend, however, to be relatively heavy compared to traditional fixed‐function representations, making real‐time application challenging.
Heikki Timonen +2 more
wiley +1 more source
Use of Computer Vision with Conventional Video Recordings of Gait in Older Adults: A Scoping Review. [PDF]
Healthcare (Basel)Banarjee C +7 more
europepmc +1 more source
Neural Local Inter‐reflection Modeling for Garment Fold Rendering
Computer Graphics Forum, EarlyView.Abstract Realistic garment rendering requires simulating complex multi‐bounce light paths within intricate fold geometries. In these regions, conventional path tracing is computationally expensive as light becomes trapped, necessitating high bounce counts for convergence.
Jooeun Son +4 more
wiley +1 more source
A Multimodal Dual-Stream Framework for Sheep Behavior Recognition Using Skeletal and Local Visual Fusion. [PDF]
Animals (Basel)Xuan C, Jia J, Liu S, Tang Z.
europepmc +1 more source
High‐Gloss SVBRDF Capture Using Bounce Light
Computer Graphics Forum, EarlyView.Abstract Reflectance capture aims at the visual reproduction of an object under varying illumination. Past works differ substantially in their experimental overhead, from single‐ or few‐image approaches, that employ significant (often learned) priors at the expense of biased reconstructions, to more accurate approaches that tend to be time‐consuming ...
Tomáš Iser +2 more
wiley +1 more source
Hybrid Compression Method for Trained 3D Gaussian Splatting Models Based on VQ and HEVC. [PDF]
Sensors (Basel)Kim DH, Choi BY, Oh KJ, Lee G, Kim JG.
europepmc +1 more source
MultiCOIN: Multi‐Modal COntrollable INbetweening
Computer Graphics Forum, EarlyView.Abstract Video inbetweening creates smooth transitions between two frames making it an indispensable tool for video editing and longform video synthesis. Existing methods struggle with large or complex motion and offer limited control over intermediate frames, often misaligning with user intent.
M. Tanveer +6 more
wiley +1 more source
MiDAS: A Multimodal Data Acquisition System and Dataset for Robot-Assisted Minimally Invasive Surgery. [PDF]
Int J Med RobotWeerasinghe K +5 more
europepmc +1 more source
Step2Motion: Locomotion Reconstruction from Pressure Sensing Insoles
Computer Graphics Forum, EarlyView.Abstract Human motion is fundamentally driven by continuous physical interaction with the environment. Whether walking, running, or simply standing, the forces exchanged between our feet and the ground provide crucial insights for understanding and reconstructing human movement. Recent advances in wearable insole devices offer a compelling solution for
J. L. Ponton +5 more
wiley +1 more source