75 citations · 262 across the 24 of their papers we have counts for
3 papers · 2 filters
Replay: Multi-modal Multi-view Acted Videos for Casual Holography
Roman Shapovalov, Yanir Kleiman, Ignacio Rocco +6
We introduce Replay, a collection of multi-view, multi-modal videos of humans interacting socially. Each scene is filmed in high production quality, from different viewpoints with…
CLIP-Count: Towards Text-Guided Zero-Shot Object Counting
Ruixiang Jiang, Lingbo Liu, Changwen Chen
Recent advances in visual-language models have shown remarkable zero-shot text-image matching ability that is transferable to downstream tasks such as object detection and segmenta…
Novel-View Acoustic Synthesis
Changan Chen, Alexander Richard, Roman Shapovalov +4
We introduce the novel-view acoustic synthesis (NVAS) task: given the sight and sound observed at a source viewpoint, can we synthesize the sound of that scene from an unseen targe…