5 papers · 1 filter
MacTok: Robust Continuous Tokenization for Image Generation
Hengyu Zeng, Xin Gao, Guanghao Li +5
Continuous image tokenizers enable efficient visual generation, and those based on variational frameworks can learn smooth, structured latent representations through KL regularizat…
GIFT: Global Irreplaceability Frame Targeting for Efficient Video Understanding
Junpeng Ma, Sashuai Zhou, Guanghao Li +9
Video Large Language Models (VLMs) have achieved remarkable success in video understanding, but the significant computational cost from processing dense frames severely limits thei…
CasPoinTr: Point Cloud Completion with Cascaded Networks and Knowledge Distillation
Yifan Yang, Yuxiang Yan, Boda Liu +1
Point clouds collected from real-world environments are often incomplete due to factors such as limited sensor resolution, single viewpoints, occlusions, and noise. These challenge…
Dark-ISP: Enhancing RAW Image Processing for Low-Light Object Detection
Jiasheng Guo, Xin Gao, Yuxiang Yan +2
Low-light Object detection is crucial for many real-world applications but remains challenging due to degraded image quality. While recent studies have shown that RAW images offer…
PointSSC: A Cooperative Vehicle-Infrastructure Point Cloud Benchmark for Semantic Scene Completion
Yuxiang Yan, Boda Liu, Jianfei Ai +3
Semantic Scene Completion (SSC) aims to jointly generate space occupancies and semantic labels for complex 3D scenes. Most existing SSC models focus on volumetric representations,…