A method for relighting a video of an actor’s performance with a novel 3D lighting environment by combining AI-based image manipulation with traditional 3D visual effects techniques is described, demonstrating that performances originally captured in diffuse lighting environments can be later relit in artistic ways, offering filmmakers a new option for low-cost virtual production.
Precise control over camera and object motion is essential for professional video production. Existing methods control objects only coarsely, through image-plane cues that are ambiguous in depth and rotation or through 3D tracks and blobs that lack complete geometry and lose consistency across viewpoint changes. We int...
Wei Cao, Hao Zhang, Vikram Voleti et al.· 1 citation
This work shows that camera motion, object trajectories, and depth can be unified into a single 3D point-track representation, from which one model performs joint camera and object control, depth editing, and motion transfer in a single forward pass, enabling interactive 4D-controllable streaming generation for the fir...
Shiqian Li, Chenguo Lin, Zhi-Guang Liu et al.· 0 citations
Explicit 3D scene representations such as 3D Gaussian Splatting (3DGS) have recently enabled high-quality, real-time novel view synthesis. However, these methods assume static scenes, limiting realism in the presence of dynamic phenomena ubiquitous in real-world environments. While coherent motion (e.g., humans or vehi...
Kjell Keune, Florian Hahlbohm, Jannis Möller et al.· 0 citations
This work introduces RenderBench, a benchmark of 12 reconstructed real-world scenes spanning large-scale indoor environments and egocentric viewpoints, with both static and dynamic settings, and provides paired real observations and editable scene state for assessing both appearance fidelity and preservation of geometr...
Di-Cong Qiu, Zhi-Yuan Xu, Yao Liu et al.· 0 citations
Relightable interactive scene reconstruction aims to build an editable 3D model from scans of different object arrangements and render new layouts under novel illumination. Existing methods either bake lighting into appearance or recover material and illumination only for fixed scenes, leaving edited layouts with incon...
Haonan Zhou, Gaoxiang Linghu, You-Lin Jia et al.· 0 citations
Generative models have rapidly pushed content creation be-yond 2D imagery toward dynamic 3D and 4D scene synthesis. Yet pro-ducing realistic and temporally stable 4D content from a single image is still difficult because one view provides limited structural cues and weak motion evidence. We introduce MATE4D, a framewor...
Xiao-Tian Chen, Dong-Fu Yin· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
