5 papers · 1 filter
ArmorOCR: Grounded Adversarial Visual Perception via Observation-Transferred Self-Distillation
Linhan Cao, Siyuan Li, Jun Lan +8
Large multimodal models (LMMs) have demonstrated strong OCR recognition capabilities, yet remain vulnerable to adversarial visual text that is readable to humans but challenging fo…
Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception
Lai Wei, Liangbo He, Jun Lan +9
Multimodal Large Language Models (MLLMs) excel at broad visual understanding but still struggle with fine-grained perception, where decisive evidence is small and easily overwhelme…
ProDyG: Progressive Dynamic Scene Reconstruction via Gaussian Splatting from Monocular Videos
Shi Chen, Erik Sandström, Sandro Lombardi +2
Achieving truly practical dynamic 3D reconstruction requires online operation, global pose and map consistency, detailed appearance modeling, and the flexibility to handle both RGB…
Multi-View 3D Point Tracking
Frano Rajič, Haofei Xu, Marko Mihajlovic +7
We introduce the first data-driven multi-view 3D point tracker, designed to track arbitrary points in dynamic scenes using multiple camera views. Unlike existing monocular trackers…
Enhancing Image Generation Fidelity via Progressive Prompts
Zhen Xiong, Yuqi Li, Chuanguang Yang +4
The diffusion transformer (DiT) architecture has attracted significant attention in image generation, achieving better fidelity, performance, and diversity. However, most existing…