Video Pop-up: Monocular 3D Reconstruction of Dynamic Scenes

By Chris Russell, Rui Yu, Lourdes de Agapito. 2014

123 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Lifting Object Detection Datasets into 3D (2015, neutral): “Index Terms—Object reconstruction, structure-from-motion, viewpoint estimation, visual hulls F”
Part-based modelling of compound scenes from images (2015, methodology): “Our method also has similarities with work in non-rigid reconstruction including the piecewise methods such as [16, 17] that fit generic models to parts of a video using a segmentation approach.”
Learning the Depths of Moving People by Watching Frozen People (2019, background): “We also compare with Video-Popup [31], which deals with dynamic scenes.”
Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes (2020, background): “A few prior monocular methods proposed using strong hand-crafted priors to decompose dynamic scenes into piece-wise rigid parts [34, 59, 61].”
Tensor4D: Efficient Neural 4D Decomposition for High-Fidelity Dynamic Reconstruction and Rendering (2022, methodology): “There are various ways to capture and reconstruct the 3D dynamic scenes, involving methods based on silhouette [23, 54], stereo [29, 45], flow [16, 43, 70], segmentation [40, 41], and photometric [2, 19].”
Co-fusion: Real-time segmentation, tracking and fusion of multiple objects (2017, background): “Achieving higher level semantic scene descriptions by using a dense planar representation [21] or real-time 3D object recognition [22] further improved tracking performance while opening the door to virtual or even real interaction with the scene.”