Showing cs.CVShow all
3 papers · 1 filter
cs.CV2025
Pseudo-Labeling Based Practical Semi-Supervised Meta-Training for Few-Shot Learning
Xingping Dong, Tianran Ouyang, Shengcai Liao +2
Most existing few-shot learning (FSL) methods require a large amount of labeled data in meta-training, which is a major limit. To reduce the requirement of labels, a semi-supervise…
cs.CV2025
Rethinking Temporal Fusion with a Unified Gradient Descent View for 3D Semantic Occupancy Prediction
Dubing Chen, Huan Zheng, Jin Fang +6
We present GDFusion, a temporal fusion method for vision-based 3D semantic occupancy prediction (VisionOcc). GDFusion opens up the underexplored aspects of temporal fusion within t…
cs.CV2024
Towards High-Fidelity 3D Portrait Generation with Rich Details by Cross-View Prior-Aware Diffusion
Haoran Wei, Wencheng Han, Xingping Dong +1
Recent diffusion-based Single-image 3D portrait generation methods typically employ 2D diffusion models to provide multi-view knowledge, which is then distilled into 3D representat…