2026 顶会论文
11作者位次 #7/7ECCV 2026Poster
InstanceControl: Controllable Complex Image Generation without Instance Labeling
XIAOYU LIU · Huan Wang · FAN LI · Zhixing Wang · Jiaqi Xu · Ming LIU · Wangmeng Zuo
多模态Recognition, Tracking, Re-ID & Anomaly DetectionOpenReview 作者位次 #3/3ECCV 2026Poster
Consistent Monocular Depth Estimation with Contact Region Boundary-Aware Refinement
Yinuo Wang · QingMiao QingMiao · Wangmeng Zuo
Computational Imaging, Shape Recovery and Camera GeometryOpenReview 作者位次 #6/6ECCV 2026Poster
GradingBench: Evaluating End-to-End Compositional Reasoning of MLLMs for Automated Exam Grading
Yuting Wang · Zixian Guo · Weihao You · Zhilong Ji · Jinfeng Bai · Wangmeng Zuo
多模态推理评测与基准Multimodal, Video & Document UnderstandingOpenReview 作者位次 #9/9ECCV 2026Poster
DreamLite: A Lightweight On-Device Unified Model for Image Generation and Editing
Kailai Feng · Yuxiang WEI · Bo Chen · yang pan · Hu Ye · Songwei Liu · Chenqian Yan · Yuan Gao · Wangmeng Zuo
多模态Image Generation, Editing & DiffusionOpenReview 作者位次 #5/5ECCV 2026Poster
Generalize LMMs to Versatile Visual Modalities via Fabricated Modality Synthesis
Shihao Yuan · Yuanze Li · Ruyi Zhang · Ming LIU · Wangmeng Zuo
多模态理论与学习动力学Multimodal, Video & Document UnderstandingOpenReview 作者位次 #8/8ECCV 2026Poster
AnE: Pushing the Reasoning Frontier of Multimodal LLMs via Anchor Evolution
Zehao Wang · Yihan Zeng · Zidong Gong · Yuanfan Guo · Feng Zhu · Hongzhi Zhang · Wei Zhang · Wangmeng Zuo
多模态推理Multimodal, Video & Document UnderstandingOpenReview 作者位次 #5/6ECCV 2026Poster
Beyond Common Sense: Grounding Logical Anomaly Detection in Inspection Criteria
Yuanze Li · Shihao Yuan · Zimeng Zhu · Ming LIU · Wangmeng Zuo · Guangming Shi
推理Recognition, Tracking, Re-ID & Anomaly DetectionOpenReview 作者位次 #5/5ECCV 2026Poster
ScrollScape: Unlocking 32K Image Generation With Video Diffusion Priors
Haodong Yu · Yabo Zhang · Donglin Di · Ruyi Zhang · Wangmeng Zuo
多模态Image Generation, Editing & DiffusionOpenReview 作者位次 #12/12ECCV 2026Poster
Illuminating Unified Multimodal Model for Free-form Interleaved Text-Image Generation
Chonghuinan Wang · Zhikai Chen · Chunwei Wang · Yecong Wan · Junwei Yang · Zhixin Wang · Wei Zhang · Jiaqi Xu · Renjing Pei · Xiaohe Wu · FAN LI · Wangmeng Zuo
多模态Image Generation, Editing & DiffusionOpenReview 作者位次 #7/7ECCV 2026Poster
PhysChoreo: Physics-Controllable Video Generation with Part-Aware Semantic Grounding
Haoze Zhang · Tianyu Huang · Zichen Wan · Xiaowei Jin · Hongzhi Zhang · Hui Li · Wangmeng Zuo
多模态Video Generation, Avatars & Dynamic WorldsOpenReview 作者位次 #11/11ECCV 2026Poster
Anchoring on Reality: Breaking the Pseudo-Target Ceiling in Makeup Transfer
Bo Wei · Xianhui Lin · Yi Dong · Zhongzhong Li · Zonghui Li · Zirui Wang · Jiachen Yang · Xing Liu · Hong Gu · Xiaoming Li · Wangmeng Zuo
多模态Image Generation, Editing & DiffusionOpenReview