6 papers · 1 filter
SigLIP-HD by Fine-to-Coarse Supervision
Lihe Yang, Zhen Zhao, Hengshuang Zhao
High-quality visual representation is a long-standing pursuit in computer vision. In the context of multimodal LLMs (MLLMs), feeding higher-resolution images can produce more fine-…
SCOPE: Scale-Consistent One-Pass Estimation of 3D Geometry
Zheng Zhang, Lihe Yang, Tianyu Yang +6
We present SCOPE (Scale-Consistent One-Pass Estimation of 3D Geometry), a novel approach for estimating 3D geometry from extended monocular video sequences, where existing methods…
In Pursuit of Pixel Supervision for Visual Pre-training
Lihe Yang, Shang-Wen Li, Yang Li +5
At the most basic level, pixels are the source of the visual information through which we perceive the world. Pixels contain information at all levels, ranging from low-level attri…
Depth Anything with Any Prior
Zehan Wang, Siyu Chen, Lihe Yang +4
This work presents Prior Depth Anything, a framework that combines incomplete but precise metric information in depth measurement with relative but complete geometric structures in…
UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation
Lihe Yang, Zhen Zhao, Hengshuang Zhao
Semi-supervised semantic segmentation (SSS) aims at learning rich visual knowledge from cheap unlabeled images to enhance semantic segmentation capability. Among recent works, UniM…
Depth Anything V2
Lihe Yang, Bingyi Kang, Zilong Huang +4
This work presents Depth Anything V2. Without pursuing fancy techniques, we aim to reveal crucial findings to pave the way towards building a powerful monocular depth estimation mo…