38 citations · 71 across the 13 of their papers we have counts for
5 papers · 1 filter
TBench: Benchmarking Current Progress in Text-to-3D Generation
Yuze He, Yushi Bai, Matthieu Lin +6
Recent methods in text-to-3D leverage powerful pretrained diffusion models to optimize NeRF. Notably, these methods are able to produce high-quality 3D scenes without training on 3…
DiffPoseTalk: Speech-Driven Stylistic 3D Facial Animation and Head Pose Generation via Diffusion Models
Zhiyao Sun, Tian Lv, Sheng Ye +5
The generation of stylistic 3D facial animations driven by speech presents a significant challenge as it requires learning a many-to-many mapping between speech, style, and the cor…
Indoor Scene Reconstruction with Fine-Grained Details Using Hybrid Representation and Normal Prior Enhancement
Sheng Ye, Yubin Hu, Matthieu Lin +4
The reconstruction of indoor scenes from multi-view RGB images is challenging due to the coexistence of flat and texture-less regions alongside delicate and fine-grained regions. R…
O-Recon: Completing 3D Reconstruction of Occluded Objects in the Scene with a Pre-trained 2D Diffusion Model
Yubin Hu, Sheng Ye, Wang Zhao +5
Occlusion is a common issue in 3D reconstruction from RGB-D videos, often blocking the complete reconstruction of objects and presenting an ongoing problem. In this paper, we propo…
DETR for Crowd Pedestrian Detection
Matthieu Lin, Chuming Li, Xingyuan Bu +5
Pedestrian detection in crowd scenes poses a challenging problem due to the heuristic defined mapping from anchors to pedestrians and the conflict between NMS and highly overlapped…