13 papers
One-Shot Feed-Forward 360 Animatable Avatar via Inpainted UV-Space Gaussian Modeling
Shuling Zhao, Dan Xu
Building one-shot 3D animatable head avatars is an important yet challenging problem. Existing methods generally collapse under large camera pose variations, compromising the reali…
Dynamic Parsing and Updating Natural Language Specification using VLMs for Robust Vision-Language Tracking
Xiao Wang, Liye Jin, Dan Xu +5
Vision-language tracking guided by natural language specifications leverages high-level semantic cues of target objects to substantially boost tracking accuracy and robustness. Exi…
FlashVGGT: Efficient and Scalable Visual Geometry Transformers with Compressed Descriptor Attention
Zipeng Wang, Dan Xu
3D reconstruction from multi-view images is a core challenge in computer vision. Recently, feed-forward methods have emerged as efficient and robust alternatives to traditional per…
Mono4DGS-HDR: High Dynamic Range 4D Gaussian Splatting from Alternating-exposure Monocular Videos
Jinfeng Liu, Lingtong Kong, Mi Zhou +2
We introduce Mono4DGS-HDR, the first system for reconstructing renderable 4D high dynamic range (HDR) scenes from unposed monocular low dynamic range (LDR) videos captured with alt…
Do MLLMs Exhibit Human-like Perceptual Behaviors? HVSBench: A Benchmark for MLLM Alignment with Human Perceptual Behavior
Jiaying Lin, Shuquan Ye, Dan Xu +2
While Multimodal Large Language Models (MLLMs) excel at many vision tasks, it is unknown if they exhibit human-like perceptual behaviors. To evaluate this, we introduce HVSBench, t…
Are We Ready for RL in Text-to-3D Generation? A Progressive Investigation
Yiwen Tang, Zoey Guo, Kaixin Zhu +11
Reinforcement learning (RL), earlier proven to be effective in large language and multi-modal models, has been successfully extended to enhance 2D image generation recently. Howeve…