18 papers
Chat-Scene++: Exploiting Context-Rich Object Identification for 3D LLM
Haifeng Huang, Yilun Chen, Zehan Wang +2
Recent advancements in multi-modal large language models (MLLMs) have shown strong potential for 3D scene understanding. However, existing methods struggle with fine-grained object…
ImVideoEdit: Image-learning Video Editing via 2D Spatial Difference Attention Blocks
Jiayang Xu, Fan Zhuo, Majun Zhang +6
Current video editing models often rely on expensive paired video data, which limits their practical scalability. In essence, most video editing tasks can be formulated as a decoup…
Orient Anything V2: Unifying Orientation and Rotation Understanding
Zehan Wang, Ziang Zhang, Jiayang Xu +5
This work presents Orient Anything V2, an enhanced foundation model for unified understanding of object 3D orientation and rotation from single or paired images. Building upon Orie…
DSI-Bench: A Benchmark for Dynamic Spatial Intelligence
Ziang Zhang, Zehan Wang, Guanghao Zhang +5
Reasoning about dynamic spatial relationships is essential, as both observers and objects often move simultaneously. Although vision-language models (VLMs) and visual expertise mod…
APO: Enhancing Reasoning Ability of MLLMs via Asymmetric Policy Optimization
Minjie Hong, Zirun Guo, Yan Xia +4
Multimodal Large Language Models (MLLMs) are powerful at integrating diverse data, but they often struggle with complex reasoning. While Reinforcement learning (RL) can boost reaso…
GenSpace: Benchmarking Spatially-Aware Image Generation
Zehan Wang, Jiayang Xu, Ziang Zhang +4
Humans can intuitively compose and arrange scenes in the 3D space for photography. However, can advanced AI image generators plan scenes with similar 3D spatial awareness when crea…