5 papers
PerformRecast: Expression and Head Pose Disentanglement for Portrait Video Editing
Jiadong Liang, Bojun Xiong, Jie Tian +4
This paper primarily investigates the task of expression-only portrait video performance editing based on a driving video, which plays a crucial role in animation and film industri…
LM-Gaussian: Boost Sparse-view 3D Gaussian Splatting with Large Model Priors
Hanyang Yu, Xiaoxiao Long, Ping Tan
We aim to address sparse-view reconstruction of a 3D scene by leveraging priors from large-scale vision models. While recent advancements such as 3D Gaussian Splatting (3DGS) have…
CraftsMan3D: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refiner
Weiyu Li, Jiarui Liu, Hongyu Yan +5
We present a novel generative 3D modeling system, coined CraftsMan, which can generate high-fidelity 3D geometries with highly varied shapes, regular mesh topologies, and detailed…
Dora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoders
Rui Chen, Jianfeng Zhang, Yixun Liang +7
Recent 3D content generation pipelines commonly employ Variational Autoencoders (VAEs) to encode shapes into compact latent representations for diffusion-based generation. However,…
Multi-View Large Reconstruction Model via Geometry-Aware Positional Encoding and Attention
Mengfei Li, Xiaoxiao Long, Yixun Liang +6
Despite recent advancements in the Large Reconstruction Model (LRM) demonstrating impressive results, when extending its input from single image to multiple images, it exhibits ine…