Virtual Elastic Objects

Chen, Hsiao-Yu; Tretschk, Edith; Stuyck, Tuur; Kadleček, Petr; Kavan, Ladislav; Vouga, Etienne; Lassner, Christoph

doi:10.1109/cvpr52688.2022.01537

Cited by 4 publications

(2 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…to magnify the observed motions and increase oscillation amplitudes). The VEOs approach [CTS*22] estimates a point cloud of an object non‐rigidly deforming under the influence of external forces observed in a multi‐view video. The material parameters of the object—estimated with a differentiable particle‐based simulator—ensure that the reconstructions match the observations.…”

Section: State‐of‐the‐art Methodsmentioning

confidence: 99%

“…Some particle‐based methods target long‐term novel view synthesis scenarios (with the input monocular videos following dynamic objects) [PK24] or reconstruction and editing of dynamically vibrating scenes [PPGT*23], while other ones estimate physical parameters of non‐rigid objects (such as stiffness and volume preservation coefficients) from multi‐view videos [CTS*22, LQC*22] or infer fluid dynamics from sequential image observations [GDWY22]. Point‐DynRF [PK24] analyses the entire long sequence and distinguishes the background from the moving objects; its joint optimization scheme alleviates degenerate solutions.…”

Section: State‐of‐the‐art Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Recent Trends in 3D Reconstruction of General Non‐Rigid Scenes

Yunus,

Lenssen,

Niemeyer

et al. 2024

Computer Graphics Forum

View full text Add to dashboard Cite

Reconstructing models of the real world, including 3D geometry, appearance, and motion of real scenes, is essential for computer graphics and computer vision. It enables the synthesizing of photorealistic novel views, useful for the movie industry and AR/VR applications. It also facilitates the content creation necessary in computer games and AR/VR by avoiding laborious manual design processes. Further, such models are fundamental for intelligent computing systems that need to interpret real‐world scenes and actions to act and interact safely with the human world. Notably, the world surrounding us is dynamic, and reconstructing models of dynamic, non‐rigidly moving scenes is a severely underconstrained and challenging problem. This state‐of‐the‐art report (STAR) offers the reader a comprehensive summary of state‐of‐the‐art techniques with monocular and multi‐view inputs such as data from RGB and RGB‐D sensors, among others, conveying an understanding of different approaches, their potential applications, and promising further research directions. The report covers 3D reconstruction of general non‐rigid scenes and further addresses the techniques for scene decomposition, editing and controlling, and generalizable and generative modeling. More specifically, we first review the common and fundamental concepts necessary to understand and navigate the field and then discuss the state‐of‐the‐art techniques by reviewing recent approaches that use traditional and machine‐learning‐based neural representations, including a discussion on the newly enabled applications. The STAR is concluded with a discussion of the remaining limitations and open challenges.

show abstract

Section: State‐of‐the‐art Methodsmentioning

confidence: 99%

Section: State‐of‐the‐art Methodsmentioning

confidence: 99%