24 papers
World from Motion: Generative Dynamic Gaussian Reconstruction from Monocular Video
Liyuan Zhu, Shengyu Huang, Amrita Mazumdar +6
We present World from Motion, a method for generating freely renderable dynamic 3D Gaussian representations from monocular videos. Our approach conditions a video model on dense, p…
ReGenHuman: Re-Generating Human Appearances for Realistic Full-Body Video Anonymization
Adam Sun, Eshaan Barkataki, Arnold Milstein +2
Anonymizing human-centric video data is an understudied problem. Prior anonymization techniques either blur or redact pixels at the cost of realism and downstream utility, or gener…
Policy-based Foveated Imaging and Perception
Howard Xiao, Jan Ackermann, Boyang Deng +1
Ultra-high-resolution image sensors offer the potential to capture fine spatial details critical for many visual perception tasks, but acquiring and processing all pixels at full r…
Effective Multi-sensor Conditioning for Street-view Novel-view Synthesis
Zhengfei Kuang, Adam Sun, Liyuan Zhu +7
Modern vehicle platforms are equipped with a rich sensor suite, including LiDAR, calibrated multi-camera rigs, and accurate ego-motion, that in principle offers strong signal for r…
GaussFusion: Improving 3D Reconstruction in the Wild with A Geometry-Informed Video Generator
Liyuan Zhu, Manjunath Narayana, Michal Stary +3
We present GaussFusion, a novel approach for improving 3D Gaussian splatting (3DGS) reconstructions in the wild through geometry-informed video generation. GaussFusion mitigates co…
Infinite Gaze Generation for Videos with Autoregressive Diffusion
Jenna Kang, Colin Groth, Tong Wu +4
Predicting human gaze in video is fundamental to advancing scene understanding and multimodal interaction. While traditional saliency maps provide spatial probability distributions…