8 papers
Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model
Jing He, Haodong Li, Mingzhi Sheng +1
Recovering pixel-wise geometric properties from a single image is fundamentally ill-posed due to appearance ambiguity and non-injective mappings between 2D observations and 3D stru…
SDPose: Exploiting Diffusion Priors for Out-of-Domain and Robust Pose Estimation
Shuang Liang, Jing He, Chuanmeizhi Wang +4
Pre-trained diffusion models provide rich latent features across U-Net levels and are emerging as powerful vision backbones. While prior works such as Marigold and Lotus repurpose…
DA: Depth Anything in Any Direction
Haodong Li, Wangguangdong Zheng, Jing He +5
Panorama has a full FoV (360180), offering a more complete visual description than perspective images. Thanks to this characteristic, panoramic depth estimati…
Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimation
Jiyuan Wang, Chunyu Lin, Cheng Guan +5
In this paper, we propose Jasmine, the first Stable Diffusion (SD)-based self-supervised framework for monocular depth estimation, which effectively harnesses SD's visual priors to…
Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction
Jing He, Haodong Li, Wei Yin +6
Leveraging the visual priors of pre-trained text-to-image diffusion models offers a promising solution to enhance zero-shot generalization in dense prediction tasks. However, exist…
RADA: Robust and Accurate Feature Learning with Domain Adaptation
Jingtai He, Gehao Zhang, Tingting Liu +1
Recent advancements in keypoint detection and descriptor extraction have shown impressive performance in local feature learning tasks. However, existing methods generally exhibit s…