Geowizard: Unleashing the diffusion priors for 3d geometry estimation from a single image

X Fu, W Yin, M Hu, K Wang, Y Ma, P Tan… - … on Computer Vision, 2024 - Springer
We introduce GeoWizard, a new generative foundation model designed for estimating
geometric attributes, eg, depth and normals, from single images. While significant research …

Direct2. 5: Diverse text-to-3d generation via multi-view 2.5 d diffusion

Y Lu, J Zhang, S Li, T Fang… - Proceedings of the …, 2024 - openaccess.thecvf.com
Recent advances in generative AI have unveiled significant potential for the creation of 3D
content. However current methods either apply a pre-trained 2D diffusion model with the …

Controllable generation with text-to-image diffusion models: A survey

P Cao, F Zhou, Q Song, L Yang - arxiv preprint arxiv:2403.04279, 2024 - arxiv.org
In the rapidly advancing realm of visual generation, diffusion models have revolutionized the
landscape, marking a significant shift in capabilities with their impressive text-guided …

Comprehensive Generative Replay for Task-Incremental Segmentation with Concurrent Appearance and Semantic Forgetting

W Li, J Zhang, PA Heng, L Gu - International Conference on Medical Image …, 2024 - Springer
Generalist segmentation models are increasingly favored for diverse tasks involving various
objects from different image sources. Task-Incremental Learning (TIL) offers a privacy …

Exploring Representation-Aligned Latent Space for Better Generation

W Xu, X Yue, Z Wang, Y Teng, W Zhang, X Liu… - arxiv preprint arxiv …, 2025 - arxiv.org
Generative models serve as powerful tools for modeling the real world, with mainstream
diffusion models, particularly those based on the latent diffusion model paradigm, achieving …

Joint Learning of Depth and Appearance for Portrait Image Animation

X Ji, G Zoss, P Chandran, L Yang, X Cao… - arxiv preprint arxiv …, 2025 - arxiv.org
2D portrait animation has experienced significant advancements in recent years. Much
research has utilized the prior knowledge embedded in large generative diffusion models to …

DAKD: Data Augmentation and Knowledge Distillation using Diffusion Models for SAR Oil Spill Segmentation

J Moon, J Yun, J Kim, J Lee, M Kim - arxiv preprint arxiv:2412.08116, 2024 - arxiv.org
Oil spills in the ocean pose severe environmental risks, making early detection essential.
Synthetic aperture radar (SAR) based oil spill segmentation offers robust monitoring under …

ZERO-1-TO-G: TAMING PRETRAINED 2D DIFFUSION MODEL FOR DIRECT 3D GENERATION

GG Splats - openreview.net
Recent advances in 2D image generation have achieved remarkable quality, largely driven
by the capacity of diffusion models and the availability of large-scale datasets. However …