paper-with-me

홈 › Papers

Recovering Dynamic 3D Sketches from Videos

2025-03-26 · CVPR 2025 1 · Jaeah Lee, Changwoon Choi, Young Min Kim, Jaesik Park

Understanding 3D motion from videos presents inherent challenges due to the diverse types of movement, ranging from rigid and deformable objects to articulated structures. To overcome this, we propose Liv3Stroke, a novel approach for abstracting objects in motion with deformable 3D strokes. The detailed movements of an object may be represented by unstructured motion vectors or a set of motion primitives using a pre-defined articulation from a template model. Just as a free-hand sketch can intuitively visualize scenes or intentions with a sparse set of lines, we utilize a set of parametric 3D curves to capture a set of spatially smooth motion elements for general objects with unknown structures. We first extract noisy, 3D point cloud motion guidance from video frames using semantic features, and our approach deforms a set of curves to abstract essential motion features as a set of explicit 3D representations. Such abstraction enables an understanding of prominent components of motions while maintaining robustness to environmental factors. Our approach allows direct analysis of 3D object movements from video, tackling the uncertainty that typically occurs when translating real-world motion into recorded footage. The project page is accessible via: https://jaeah.me/liv3stroke_web

📄 PDF Abstract BibTeX arXiv:2503.20321

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Dynamic Similarity Search on Integer Sketches

2020-09-24 · Shunsuke Kanda, Yasuo Tabei

Similarity-preserving hashing is a core technique for fast similarity searches, and it randomly maps data points in a metric space to strings of discrete symbols (i.e., sketches) in the Hamming space. While traditional h…

Two-Stage Co-Segmentation Network Based on Discriminative Representation for Recovering Human Mesh From Videos

2023-01-01 · CVPR 2023 1 · Boyang Zhang, Kehua Ma, Suping Wu, Zhixiang Yuan

Recovering 3D human mesh from videos has recently made significant progress. However, most of the existing methods focus on the temporal consistency of videos, while ignoring the spatial representation in complex sce…

Cartoonish sketch-based face editing in videos using identity deformation transfer

2017-03-25 · Long Zhao, Fangda Han, Xi Peng, Xun Zhang 외

We address the problem of using hand-drawn sketches to create exaggerated deformations to faces in videos, such as enlarging the shape or modifying the position of eyes or mouth. This task is formulated as a 3D face mode…

Face Model

Genie: Generative Interactive Environments

2024-02-23 · Jake Bruce, Michael Dennis, Ashley Edwards, Jack Parker-Holder 외

We introduce Genie, the first generative interactive environment trained in an unsupervised manner from unlabelled Internet videos. The model can be prompted to generate an endless variety of action-controllable virtual …

4-Doodle: Text to 3D Sketches that Move!

2025-10-29 · Hao Chen, Jiaqi Wang, Yonggang Qi, Ke Li 외 arxiv

We present a novel task: text-to-3D sketch animation, which aims to bring freeform sketches to life in dynamic 3D space. Unlike prior works focused on photorealistic content generation, we target sparse, stylized, and vi…

Point CloudsText to 3D