Sanja Fidler

Latest

• L4GM: Large 4D Gaussian Reconstruction Model
• Align Your Steps: Optimizing Sampling Schedules in Diffusion Models
• Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models
• Outdoor Scene Extrapolation with Hierarchical Generative Cellular Automata
• WildFusion: Learning 3D-Aware Latent Diffusion Models in View Space
• DreamTeacher: Pretraining Image Backbones with Deep Generative Models
• End-to-end 3D Tracking with Decoupled Queries
• Learning Human Dynamics in Autonomous Driving Scenarios
• TexFusion: Synthesizing 3D Textures with Text-Guided Image Diffusion Models
• Learning Physically Simulated Tennis Players from Broadcast Videos
• Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models
• Magic3D: High-Resolution Text-to-3D Content Creation
• NeuralField-LDM: Scene Generation with Hierarchical Latent Diffusion Models
• Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusion
• VoxFormer: Sparse voxel transformer for camera-based 3D semantic scene completion
• LION: Latent Point Diffusion Models for 3D Shape Generation
• Neural Light Field Estimation for Outdoor Scenes with Differentiable Virtual Object Insertion
• M$^2$BEV: Multi-camera joint 3D detection and segmentation with unified birds-eye view representation
• Don't Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence
• Learning Indoor Inverse Rendering with 3D Spatially-Varying Lighting