2025 Highlight "diffusion models" Papers

20 papers found

BADGR: Bundle Adjustment Diffusion Conditioned by Gradients for Wide-Baseline Floor Plan Reconstruction

Yuguang Li, Ivaylo Boyadzhiev, Zixuan Liu et al.

CVPR 2025highlightarXiv:2503.19340

Boosting Domain Generalized and Adaptive Detection with Diffusion Models: Fitness, Generalization, and Transferability

Boyong He, Yuxiang Ji, Zhuoyue Tan et al.

ICCV 2025highlightarXiv:2506.21042
1
citations

Contact-Aware Amodal Completion for Human-Object Interaction via Multi-Regional Inpainting

Seunggeun Chi, Pin-Hao Huang, Enna Sachdeva et al.

ICCV 2025highlightarXiv:2508.00427
2
citations

DAMM-Diffusion: Learning Divergence-Aware Multi-Modal Diffusion Model for Nanoparticles Distribution Prediction

Junjie Zhou, Shouju Wang, Yuxia Tang et al.

CVPR 2025highlightarXiv:2503.09491
1
citations

DexGrasp Anything: Towards Universal Robotic Dexterous Grasping with Physics Awareness

Yiming Zhong, Qi Jiang, Jingyi Yu et al.

CVPR 2025highlightarXiv:2503.08257
19
citations

Edit360: 2D Image Edits to 3D Assets from Any Angle

Junchao Huang, Xinting Hu, Shaoshuai Shi et al.

ICCV 2025highlightarXiv:2506.10507
4
citations

Extrapolating and Decoupling Image-to-Video Generation Models: Motion Modeling is Easier Than You Think

Zhenyi Lu, Xiaoye Qu, Zhenyi Lu et al.

CVPR 2025highlightarXiv:2503.00948
10
citations

Geometry Distributions

Biao Zhang, Jing Ren, Peter Wonka

ICCV 2025highlightarXiv:2411.16076

Guiding Diffusion-Based Articulated Object Generation by Partial Point Cloud Alignment and Physical Plausibility Constraints

Jens U. Kreber, Joerg Stueckler

ICCV 2025highlightarXiv:2508.00558
2
citations

InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance Parsing

Jinlu Zhang, Yixin Chen, Zan Wang et al.

CVPR 2025highlightarXiv:2505.24315
7
citations

Latent Drifting in Diffusion Models for Counterfactual Medical Image Synthesis

Yousef Yeganeh, Ioannis Charisiadis, Marta Hasny et al.

CVPR 2025highlightarXiv:2412.20651
4
citations

MangaNinja: Line Art Colorization with Precise Reference Following

Zhiheng Liu, Ka Leong Cheng, Xi Chen et al.

CVPR 2025highlightarXiv:2501.08332
15
citations

Memories of Forgotten Concepts

Matan Rusanovsky, Shimon Malnick, Amir Jevnisek et al.

CVPR 2025highlightarXiv:2412.00782
4
citations

Panorama Generation From NFoV Image Done Right

Dian Zheng, Cheng Zhang, Xiao-Ming Wu et al.

CVPR 2025highlightarXiv:2503.18420
7
citations

SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation

Junsong Chen, Shuchen Xue, Yuyang Zhao et al.

ICCV 2025highlightarXiv:2503.09641
37
citations

Satellite Observations Guided Diffusion Model for Accurate Meteorological States at Arbitrary Resolution

Siwei Tu, Ben Fei, Weidong Yang et al.

CVPR 2025highlightarXiv:2502.07814
6
citations

SCSA: A Plug-and-Play Semantic Continuous-Sparse Attention for Arbitrary Semantic Style Transfer

Chunnan Shang, Zhizhong Wang, Hongwei Wang et al.

CVPR 2025highlightarXiv:2503.04119
1
citations

StyleSSP: Sampling StartPoint Enhancement for Training-free Diffusion-based Method for Style Transfer

ruojun xu, Weijie Xi, Xiaodi Wang et al.

CVPR 2025highlightarXiv:2501.11319
6
citations

SummDiff: Generative Modeling of Video Summarization with Diffusion

Kwanseok Kim, Jaehoon Hahm, Sumin Kim et al.

ICCV 2025highlightarXiv:2510.08458

Unleashing Vecset Diffusion Model for Fast Shape Generation

Zeqiang Lai, Zhao Yunfei, Zibo Zhao et al.

ICCV 2025highlightarXiv:2503.16302
14
citations