7 papers · 1 filter
Efficient RWKV-based Representation Learning for 3D Point Clouds
Yun Liu, Xuefeng Yan, Liangliang Nan +5
The recent receptance weighted key value (RWKV) model combines RNN-style recurrence, offering a linear-complexity alternative to Transformers' quadratic self-attention for modeling…
LUNA: Learning Universal 3D Human Animation Beyond Skinning
Peng Li, Rawal Khirodkar, Junxuan Li +6
Creating photorealistic, animatable 3D human avatars from monocular images still largely depends on Linear Blend Skinning (LBS) and parametric body models, which constrain expressi…
Know3D: Prompting 3D Generation with Knowledge from Vision-Language Models
Wenyue Chen, Wenjue Chen, Peng Li +6
Recent advances in 3D generation have improved the fidelity and geometric details of synthesized 3D assets. However, due to the inherent ambiguity of single-view observations and t…
UniSH: Unifying Scene and Human Reconstruction in a Feed-Forward Pass
Mengfei Li, Peng Li, Zheng Zhang +9
We present UniSH, a unified, feed-forward framework for joint metric-scale 3D scene and human reconstruction. A key challenge in this domain is the scarcity of large-scale, annotat…
SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction
Wenyue Chen, Peng Li, Wangguandong Zheng +6
Photorealistic 3D full-body human reconstruction from a single image is a critical yet challenging task for applications in films and video games due to inherent ambiguities and se…
PanoLAM: Large Avatar Model for Gaussian Full-Head Synthesis from One-shot Unposed Image
Peng Li, Yisheng He, Yingdong Hu +7
We present a feed-forward framework for Gaussian full-head synthesis from a single unposed image. Unlike previous work that relies on time-consuming GAN inversion and test-time opt…