4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Models
Paper
•
2503.10437
•
Published
•
32
scene4D
-
-
Open-Sora 2.0: Training a Commercial-Level Video Generation Model in $200k
Paper • 2503.09642 • Published • 19 -
VGGT: Visual Geometry Grounded Transformer
Paper • 2503.11651 • Published • 33 -
1000+ FPS 4D Gaussian Splatting for Dynamic Scene Rendering
Paper • 2503.16422 • Published • 14 -
SynCity: Training-Free Generation of 3D Worlds
Paper • 2503.16420 • Published • 27 -
M3: 3D-Spatial MultiModal Memory
Paper • 2503.16413 • Published • 15 -
MetaSpatial: Reinforcing 3D Spatial Reasoning in VLMs for the Metaverse
Paper • 2503.18470 • Published • 3 -
Any6D: Model-free 6D Pose Estimation of Novel Objects
Paper • 2503.18673 • Published • 3 -
FirePlace: Geometric Refinements of LLM Common Sense Reasoning for 3D Object Placement
Paper • 2503.04919 • Published • 8 -
FlexWorld: Progressively Expanding 3D Scenes for Flexiable-View Synthesis
Paper • 2503.13265 • Published • 15 -
Feature4X: Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fields
Paper • 2503.20776 • Published • 10 -
Segment Any Motion in Videos
Paper • 2503.22268 • Published • 19 -
Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal Consistency
Paper • 2503.20785 • Published • 22 -
VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step
Paper • 2504.01956 • Published • 41 -
TAPIP3D: Tracking Any Point in Persistent 3D Geometry
Paper • 2504.14717 • Published • 8 -
Towards Understanding Camera Motions in Any Video
Paper • 2504.15376 • Published • 158 -
EmbodiedGen: Towards a Generative 3D World Engine for Embodied Intelligence
Paper • 2506.10600 • Published • 8 -
StreamSplat: Towards Online Dynamic 3D Reconstruction from Uncalibrated Video Streams
Paper • 2506.08862 • Published • 5 -
PlayerOne: Egocentric World Simulator
Paper • 2506.09995 • Published • 34 -
π^3: Scalable Permutation-Equivariant Visual Geometry Learning
Paper • 2507.13347 • Published • 64 -
SpatialTrackerV2: 3D Point Tracking Made Easy
Paper • 2507.12462 • Published • 18 -
PhysX: Physical-Grounded 3D Asset Generation
Paper • 2507.12465 • Published • 43 -
Streaming 4D Visual Geometry Transformer
Paper • 2507.11539 • Published • 14 -
Yume: An Interactive World Generation Model
Paper • 2507.17744 • Published • 85 -
Reconstructing 4D Spatial Intelligence: A Survey
Paper • 2507.21045 • Published • 35 -
HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels
Paper • 2507.21809 • Published • 131 -
NeRF Is a Valuable Assistant for 3D Gaussian Splatting
Paper • 2507.23374 • Published • 11 -
DreamScene: 3D Gaussian-based End-to-end Text-to-3D Scene Generation
Paper • 2507.13985 • Published • 6 -
Matrix-3D: Omnidirectional Explorable 3D World Generation
Paper • 2508.08086 • Published • 75 -
UniEgoMotion: A Unified Model for Egocentric Motion Reconstruction, Forecasting, and Generation
Paper • 2508.01126 • Published • 5 -
G-CUT3R: Guided 3D Reconstruction with Camera and Depth Prior Integration
Paper • 2508.11379 • Published • 12 -
STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer
Paper • 2508.10893 • Published • 31 -
MeshSplat: Generalizable Sparse-View Surface Reconstruction via Gaussian Splatting
Paper • 2508.17811 • Published • 6 -
Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixels
Paper • 2508.17437 • Published • 37 -
DA^2: Depth Anything in Any Direction
Paper • 2509.26618 • Published • 25 -
TTT3R: 3D Reconstruction as Test-Time Training
Paper • 2509.26645 • Published • 14 -
Game-TARS: Pretrained Foundation Models for Scalable Generalist Multimodal Game Agents
Paper • 2510.23691 • Published • 51