6 papers
4DP-QA: Scalable QA for 4D Perception in Vision Language Models
Seokju Cho, Abhishek Badki, Hang Su +5
Despite recent advances, Vision Language Models (VLMs) still struggle to grasp the dynamics of the world. We note that the ability to reason about a 4D scene, challenging in itself…
Unmasking Puppeteers: Leveraging Biometric Leakage to Expose Impersonation in AI-Based Videoconferencing
Danial Samadi Vahdati, Tai Duc Nguyen, Ekta Prashnani +4
AI-based talking-head videoconferencing systems reduce bandwidth by sending a compact pose-expression latent and re-synthesizing RGB at the receiver, but this latent can be puppete…
L4P: Towards Unified Low-Level 4D Vision Perception
Abhishek Badki, Hang Su, Bowen Wen +1
The spatio-temporal relationship between the pixels of a video carries critical information for low-level 4D perception tasks. A single model that reasons about it should be able t…
FoundationStereo: Zero-Shot Stereo Matching
Bowen Wen, Matthew Trepte, Joseph Aribido +3
Tremendous progress has been made in deep stereo matching to excel on benchmark datasets through per-domain fine-tuning. However, achieving strong zero-shot generalization - a hall…
Zero-Shot Monocular Scene Flow Estimation in the Wild
Yiqing Liang, Abhishek Badki, Hang Su +2
Large models have shown generalization across datasets for many low-level vision tasks, like depth estimation, but no such general models exist for scene flow. Even though scene fl…
nvTorchCam: An Open-source Library for Camera-Agnostic Differentiable Geometric Vision
Daniel Lichy, Hang Su, Abhishek Badki +2
We introduce nvTorchCam, an open-source library under the Apache 2.0 license, designed to make deep learning algorithms camera model-independent. nvTorchCam abstracts critical came…