Showing 1–12 of 12 results
/ Date/ Name
Nov 30, 2021Pyramid Adversarial Training Improves ViT PerformanceFeb 14, 2023VQ3D: Learning a 3D-Aware Generative Model on ImageNetSep 2, 2021SLIDE: Single Image 3D Photography with Soft Layering and Depth-aware InpaintingOct 27, 2023ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single ImageDec 17, 2025VLIC: Vision-Language Models As Perceptual Judges for Human-Aligned Image CompressionMar 14, 2025Flow to the Mode: Mode-Seeking Diffusion Autoencoders for State-of-the-Art Image TokenizationDec 4, 2022Self-supervised AutoFlowJun 15, 2023NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose AnnotationsFeb 11, 2026Latent Forcing: Reordering the Diffusion Trajectory for Pixel-Space Image GenerationDec 6, 2023WonderJourney: Going from Anywhere to EverywhereMay 23, 2024Generative Camera Dolly: Extreme Monocular Dynamic Novel View SynthesisSep 5, 2024View-Invariant Policy Learning via Zero-Shot Novel View Synthesis