11 papers
Report of the 8th LSVOS Challenge: Complex and Multimodal Video Object Segmentation
Chang Liu, Henghui Ding, Lingyi Hong +36
This report summarizes the 8th Large-scale Video Object Segmentation (LSVOS) Challenge, held in conjunction with ECCV 2026. The challenge evaluates video segmentation in three comp…
DeSeG: Decoupling Semantic Intent and Geometric Constraints for Physically Plausible Human-Scene Interaction
Jiakun Li, Zhe Li, Wenqiang Wu +4
Synthesizing physically plausible human-scene interactions (HSI) remains a critical challenge in computer vision and the development of human avatars. Although recent generative mo…
Learning Trajectory-Aware Multimodal Large Language Models for Video Reasoning Segmentation
Jingnan Luo, Mingqi Gao, Jun Liu +2
The prosperity of Multimodal Large Language Models (MLLMs) has stimulated the demand for video reasoning segmentation, which aims to segment video objects based on human instructio…
ArtiWorld: LLM-Driven Articulation of 3D Objects in Scenes
Yixuan Yang, Luyang Xie, Zhen Luo +4
Building interactive simulators and scalable robot-learning environments requires a large number of articulated assets. However, most existing 3D assets in simulation are rigid, an…
Leveraging Geometric Priors for Unaligned Scene Change Detection
Ziling Liu, Ziwei Chen, Mingqi Gao +2
Unaligned Scene Change Detection aims to detect scene changes between image pairs captured at different times without assuming viewpoint alignment. To handle viewpoint variations,…
SCORP: Scene-Consistent Object Refinement via Proxy Generation and Tuning
Ziwei Chen, Ziling Liu, Zitong Huang +2
Viewpoint missing of objects is common in scene reconstruction, as camera paths typically prioritize capturing the overall scene structure rather than individual objects. This make…
OptiScene: LLM-driven Indoor Scene Layout Generation via Scaled Human-aligned Data Synthesis and Multi-Stage Preference Optimization
Yixuan Yang, Zhen Luo, Tongsheng Ding +5
Automatic indoor layout generation has attracted increasing attention due to its potential in interior design, virtual environment construction, and embodied AI. Existing methods f…
Few-Shot Referring Video Single- and Multi-Object Segmentation via Cross-Modal Affinity with Instance Sequence Matching
Heng Liu, Guanghui Li, Mingqi Gao +3
Referring video object segmentation (RVOS) aims to segment objects in videos guided by natural language descriptions. We propose FS-RVOS, a Transformer-based model with two key com…
1st Place Solution for MeViS Track in CVPR 2024 PVUW Workshop: Motion Expression guided Video Segmentation
Mingqi Gao, Jingnan Luo, Jinyu Yang +2
Motion Expression guided Video Segmentation (MeViS), as an emerging task, poses many new challenges to the field of referring video object segmentation (RVOS). In this technical re…
Place Anything into Any Video
Ziling Liu, Jinyu Yang, Mingqi Gao +1
Controllable video editing has demonstrated remarkable potential across diverse applications, particularly in scenarios where capturing or re-capturing real-world videos is either…
Learning Cross-Modal Affinity for Referring Video Object Segmentation Targeting Limited Samples
Guanghui Li, Mingqi Gao, Heng Liu +2
Referring video object segmentation (RVOS), as a supervised learning task, relies on sufficient annotated data for a given scene. However, in more realistic scenarios, only minimal…