Latest

• BlobGEN-Vid: Compositional Text-to-Video Generation with Blob Video Representations
• NaVILA: Legged Robot Vision-Language-Action Model for Navigation
• NVILA: Efficient Frontier Visual Language Models
• Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks
• Parallel Sequence Modeling via Generalization Spatial Propagation Network (GSPN)
• Recreating 1940s Tom and Jerry with Test-Time Training
• Scaling Vision Pre-Training to 4K Resolution
• BlobGEN-3D: Compositional 3D-Consistent Freeview Image Generation with 3D Blobs
• CosAE: Learnable Fourier Series for Image Restoration
• Cosine Autoencoder with Extremely Narrow Bottleneck for Image Restoration
• SpatialRGPT: Grounded Spatial Reasoning in Vision-Language Models
• AGG: Amortized Generative 3D Gaussians for Single Image to 3D
• Compositional Text-to-Image Generation with Dense Blob Representations
• COLMAP-Free 3D Gaussian Splatting
• Dream-in-4D: A Unified Approach for Text- and Image-guided 4D Scene Generation
• HOIDiffusion: Generating Realistic 3D Hand-Object Interaction Data
• RegionGPT: Towards Region Understanding Vision Language Model
• RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videos
• 3D Reconstruction with Generalizable Neural Fields using Scene Priors
• Generalizable One-shot Neural Head Avatar
• Affordance Diffusion: Synthesizing Hand-Object Interactions
• Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models
• Zero-shot Pose Transfer for Unrigged Stylized 3D Characters
• Autoregressive 3D shape generation via canonical mapping
• Scraping Textures from Natural Images for Synthesis and Editing
• CoordGAN: Self-Supervised Dense Correspondences Emerge from GANs
• GroupViT: Semantic Segmentation Emerges From Text Supervision
• Learning contrastive representation for semantic correspondence
• Coupled Segmentation and Edge Learning Using Dynamic Graph Propagation
• Coupled Segmentation and Edge Learning via Dynamic Graph Propagation
• Hierarchical Contrastive Motion Learning for Video Action Recognition
• Self-Supervised Object Detection via Generative Image Synthesis
• Learning to Track Instances without Video Annotations
• Learning continuous environment fields via implicit functions
• Online adaptation for consistent mesh reconstruction in the wild
• Self-supervised single-view 3D reconstruction via semantic consistency
• Self-Supervised Viewpoint Learning from Image Collections