6 papers
Dissecting Embodied Abilities in Multimodal Language Models through Skill-level Evaluation and Diagnosis
Yu Qi, Haibo Zhao, Ziyu Guo +17
Understanding the capability bottlenecks of embodied multimodal large language models (MLLMs) is crucial for improving embodied agents. However, existing embodied benchmarks mainly…
-Mesh: Reinforcement Learning Powered Mesh Reconstruction via Geometry and Appearance Refinement
Haoyang Wang, Liming Liu, Xinggong Zhang
Mesh reconstruction from Neural Radiance Fields (NeRF) is widely used in 3D reconstruction and has been applied across numerous domains. However, existing methods typically rely so…
HybridPrompt: Bridging Generative Priors and Traditional Codecs for Mobile Streaming
Liming Liu, Jiangkai Wu, Haoyang Wang +3
In Video on Demand (VoD) scenarios, traditional codecs are the industry standard due to their high decoding efficiency. However, they suffer from severe quality degradation under l…
R-Meshfusion: Reinforcement Learning Powered Sparse-View Mesh Reconstruction with Diffusion Priors
Haoyang Wang, Liming Liu, Peiheng Wang +3
Mesh reconstruction from multi-view images is a fundamental problem in computer vision, but its performance degrades significantly under sparse-view conditions, especially in unsee…
PromptMobile: Efficient Promptus for Low Bandwidth Mobile Video Streaming
Liming Liu, Jiangkai Wu, Haoyang Wang +3
Traditional video compression algorithms exhibit significant quality degradation at extremely low bitrates. Promptus emerges as a new paradigm for video streaming, substantially cu…
GaussVideoDreamer: 3D Scene Generation with Video Diffusion and Inconsistency-Aware Gaussian Splatting
Junlin Hao, Peiheng Wang, Haoyang Wang +2
Single-image 3D scene reconstruction presents significant challenges due to its inherently ill-posed nature and limited input constraints. Recent advances have explored two promisi…