6 papers
Focused Forcing: Content-Aware Per-Frame KV Selection for Efficient Autoregressive Video Diffusion
Peiliang Cai, Evelyn Zhang, Jiacheng Liu +8
Recent advances in autoregressive video diffusion have enabled sequential and streaming video generation. However, long-horizon generation requires increasingly large KV caches, ma…
DiT-IC: Aligned Diffusion Transformer for Efficient Image Compression
Junqi Shi, Ming Lu, Xingchen Li +3
Diffusion-based image compression has recently shown outstanding perceptual fidelity, yet its practicality is hindered by prohibitive sampling overhead and high memory usage. Most…
Mesh Splatting for End-to-end Multiview Surface Reconstruction
Ruiqi Zhang, Jiacheng Wu, Jie Chen
Surfaces are typically represented as meshes, which can be extracted from volumetric fields via meshing or optimized directly as surface parameterizations. Volumetric representatio…
Deep Inverse Shading: Consistent Albedo and Surface Detail Recovery via Generative Refinement
Jiacheng Wu, Ruiqi Zhang, Jie Chen
Reconstructing human avatars using generative priors is essential for achieving versatile and realistic avatar models. Traditional approaches often rely on volumetric representatio…
Fast and Physically-based Neural Explicit Surface for Relightable Human Avatars
Jiacheng Wu, Ruiqi Zhang, Jie Chen +1
Efficiently modeling relightable human avatars from sparse-view videos is crucial for AR/VR applications. Current methods use neural implicit representations to capture dynamic geo…
Extraction of energy from a black hole in Einstein-Maxwell-scalar theory
Cheng-Yong Zhang, Zehong Zhang, Ruifeng Zheng
Recently, it has been discovered that the nonlinear self-interaction of matter can induce energy extraction from black holes beyond superradiant instability. This process is closel…