2 papers
cs.CV2026
HumanMoveVQA: Can Video MLLMs reason about human movement in videos?
Pulkit Gera, Faegheh Sardari, Asmar Nadeem +4
Despite the rapid advance of Multimodal Large Language Models (MLLMs) in high-level video understanding, a fundamental bottleneck remains: these models collapse complex human motio…
cs.CV2025
HumanOLAT: A Large-Scale Dataset for Full-Body Human Relighting and Novel-View Synthesis
Timo Teufel, Pulkit Gera, Xilong Zhou +5
Simultaneous relighting and novel-view rendering of digital human representations is an important yet challenging task with numerous applications. Progress in this area has been si…