Huan Ling

Latest

• DiffusionRenderer: Neural Inverse and Forward Rendering with Video Diffusion Models
• Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models
• GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control
• SCube: Instant Large-Scale Scene Reconstruction using VoxSplats
• DreamTeacher: Pretraining Image Backbones with Deep Generative Models
• Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models
• BigDatasetGAN: Synthesizing ImageNet with Pixel-wise Annotations
• EditGAN: High-Precision Semantic Image Editing
• DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort
• Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering
• Variational Amodal Object Completion
• Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer