1

Déjà View: Looping Transformers for Multi-View 3D Reconstruction
NeurIPS 2026 Oral
TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens
Computer Vision and Pattern Recognition (CVPR) 2026 - Highlight
Lyra 2.0: Explorable Generative 3D Worlds
SIGGRAPH Asia 2026
Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation
ICLR 2026
InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models
ICCV 2025
GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control
Computer Vision and Pattern Recognition (CVPR) 2025 - Highlight
STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes
ArXiv 2025
SCube: Instant Large-Scale Scene Reconstruction using VoxSplats
NeurIPS 2024
XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies
Computer Vision and Pattern Recognition (CVPR) 2024 - Highlight
Approximately Piecewise E(3) Equivariant Point Networks
International Conference on Learning Representations (ICLR) 2024