:: Library Catalog

Image de couverture de livre

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Prestel, Ulrich, Baumann, Stefan Andreas, Stracke, Nick, Ommer, Björn
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Accès en ligne:	https://arxiv.org/abs/2605.31535
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

What If : Understanding Motion Through Sparse Interactions
par: Baumann, Stefan Andreas, et autres
Publié: (2025)

CleanDIFT: Diffusion Features without Noise
par: Stracke, Nick, et autres
Publié: (2024)

CTRLorALTer: Conditional LoRAdapter for Efficient 0-Shot Control & Altering of T2I Models
par: Stracke, Nick, et autres
Publié: (2024)

Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions
par: Baumann, Stefan Andreas, et autres
Publié: (2024)

Learning Long-term Motion Embeddings for Efficient Kinematics Generation
par: Stracke, Nick, et autres
Publié: (2026)

Probabilistic Precipitation Nowcasting with Rectified Flow Transformers
par: Schusterbauer, Johannes, et autres
Publié: (2026)

Boosting Latent Diffusion with Flow Matching
par: Schusterbauer, Johannes, et autres
Publié: (2023)

DepthFM: Fast Monocular Depth Estimation with Flow Matching
par: Gui, Ming, et autres
Publié: (2024)

Envisioning the Future, One Step at a Time
par: Baumann, Stefan Andreas, et autres
Publié: (2026)

TREAD: Token Routing for Efficient Architecture-agnostic Diffusion Training
par: Krause, Felix, et autres
Publié: (2025)

[MASK] is All You Need
par: Hu, Vincent Tao, et autres
Publié: (2024)

True Self-Supervised Novel View Synthesis is Transferable
par: Mitchel, Thomas W., et autres
Publié: (2025)

Unsupervised View-Invariant Human Posture Representation
par: Sardari, Faegheh, et autres
Publié: (2021)

DisMo: Disentangled Motion Representations for Open-World Motion Transfer
par: Ressler-Antal, Thomas, et autres
Publié: (2025)

ZigMa: A DiT-style Zigzag Mamba Diffusion Model
par: Hu, Vincent Tao, et autres
Publié: (2024)

Novel View Synthesis with Neural Radiance Fields for Industrial Robot Applications
par: Hillemann, Markus, et autres
Publié: (2024)

MaskFlow: Discrete Flows For Flexible and Efficient Long Video Generation
par: Fuest, Michael, et autres
Publié: (2025)

Latent Drifting in Diffusion Models for Counterfactual Medical Image Synthesis
par: Yeganeh, Yousef, et autres
Publié: (2024)

Guiding Token-Sparse Diffusion Models
par: Krause, Felix, et autres
Publié: (2026)

CAGE: Unsupervised Visual Composition and Animation for Controllable Video Generation
par: Davtyan, Aram, et autres
Publié: (2024)

Scalable High-Resolution Pixel-Space Image Synthesis with Hourglass Diffusion Transformers
par: Crowson, Katherine, et autres
Publié: (2024)

Scaling Image Tokenizers with Grouped Spherical Quantization
par: Wang, Jiangtao, et autres
Publié: (2024)

Adapting Self-Supervised Representations as a Latent Space for Efficient Generation
par: Gui, Ming, et autres
Publié: (2025)

Diffusion Models and Representation Learning: A Survey
par: Fuest, Michael, et autres
Publié: (2024)

RendBEV: Semantic Novel View Synthesis for Self-Supervised Bird's Eye View Segmentation
par: Monteagudo, Henrique Piñeiro, et autres
Publié: (2025)

Diversity-Driven View Subset Selection for Indoor Novel View Synthesis
par: Wang, Zehao, et autres
Publié: (2024)

Self-Supervised Radiograph Anatomical Region Classification -- How Clean Is Your Real-World Data?
par: Langer, Simon, et autres
Publié: (2024)

RayGaussX: Accelerating Gaussian-Based Ray Marching for Real-Time and High-Quality Novel View Synthesis
par: Blanc, Hugo, et autres
Publié: (2025)

MVEB: Self-Supervised Learning with Multi-View Entropy Bottleneck
par: Wen, Liangjian, et autres
Publié: (2024)

DT-NVS: Diffusion Transformers for Novel View Synthesis
par: Jang, Wonbong, et autres
Publié: (2025)

RenderWorld: World Model with Self-Supervised 3D Label
par: Yan, Ziyang, et autres
Publié: (2024)

Self-Supervised Learning for Endoscopic Video Analysis
par: Hirsch, Roy, et autres
Publié: (2023)

Novel View Synthesis as Video Completion
par: Wu, Qi, et autres
Publié: (2026)

Fast and Lightweight Novel View Synthesis with Differentiable Multiplane Image
par: Zhang, Kaidi, et autres
Publié: (2026)

PhysWorld: From Real Videos to World Models of Deformable Objects via Physics-Aware Demonstration Synthesis
par: Yang, Yu, et autres
Publié: (2025)

SCFlow: Implicitly Learning Style and Content Disentanglement with Flow Models
par: Ma, Pingchuan, et autres
Publié: (2025)

A Mechanistic View on Video Generation as World Models: State and Dynamics
par: Wang, Luozhou, et autres
Publié: (2026)

VisionNVS: Self-Supervised Inpainting for Novel View Synthesis under the Virtual-Shift Paradigm
par: Lu, Hongbo, et autres
Publié: (2026)

From None to All: Self-Supervised 3D Reconstruction via Novel View Synthesis
par: Huang, Ranran, et autres
Publié: (2026)

Enhancing Close-up Novel View Synthesis via Pseudo-labeling
par: Xia, Jiatong, et autres
Publié: (2025)