4 papers
GAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generation
Jiahao Lu, Minghao Yin, Wenbo Hu +5
We present a compact geometry-native latent space as a shared foundation for perception and generation. Visual generators can produce photorealistic frames without preserving a con…
Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels
Jiahao Lu, Jiayi Xu, Wenbo Hu +5
Estimating the 3D trajectory of every pixel from a monocular video is crucial and promising for a comprehensive understanding of the 3D dynamics of videos. Recent monocular 3D trac…
PDT: Point Distribution Transformation with Diffusion Models
Jionghao Wang, Cheng Lin, Yuan Liu +7
Point-based representations have consistently played a vital role in geometric data structures. Most point cloud learning and processing methods typically leverage the unordered an…
Epona: Autoregressive Diffusion World Model for Autonomous Driving
Kaiwen Zhang, Zhenyu Tang, Xiaotao Hu +9
Diffusion models have demonstrated exceptional visual quality in video generation, making them promising for autonomous driving world modeling. However, existing video diffusion-ba…