-
MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models
Paper • 2501.02955 • Published • 44 -
2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining
Paper • 2501.00958 • Published • 107 -
MMVU: Measuring Expert-Level Multi-Discipline Video Understanding
Paper • 2501.12380 • Published • 85 -
VideoWorld: Exploring Knowledge Learning from Unlabeled Videos
Paper • 2501.09781 • Published • 28
Collections
Discover the best community collections!
Collections including paper arxiv:2501.19054
-
CraftsMan: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refiner
Paper • 2405.14979 • Published • 19 -
PLA4D: Pixel-Level Alignments for Text-to-4D Gaussian Splatting
Paper • 2405.19957 • Published • 10 -
GECO: Generative Image-to-3D within a SECOnd
Paper • 2405.20327 • Published • 11 -
gsplat: An Open-Source Library for Gaussian Splatting
Paper • 2409.06765 • Published • 17
-
FlashWorld: High-quality 3D Scene Generation within Seconds
Paper • 2510.13678 • Published • 70 -
NANO3D: A Training-Free Approach for Efficient 3D Editing Without Masks
Paper • 2510.15019 • Published • 62 -
GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction
Paper • 2509.18090 • Published • 3 -
Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation
Paper • 2509.19296 • Published • 22
-
LinFusion: 1 GPU, 1 Minute, 16K Image
Paper • 2409.02097 • Published • 34 -
Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion
Paper • 2409.11406 • Published • 27 -
Diffusion Models Are Real-Time Game Engines
Paper • 2408.14837 • Published • 126 -
Segment Anything with Multiple Modalities
Paper • 2408.09085 • Published • 22
-
TextureDreamer: Image-guided Texture Synthesis through Geometry-aware Diffusion
Paper • 2401.09416 • Published • 11 -
SHINOBI: Shape and Illumination using Neural Object Decomposition via BRDF Optimization In-the-wild
Paper • 2401.10171 • Published • 14 -
DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Model
Paper • 2311.09217 • Published • 22 -
GALA: Generating Animatable Layered Assets from a Single Scan
Paper • 2401.12979 • Published • 9
-
MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models
Paper • 2501.02955 • Published • 44 -
2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining
Paper • 2501.00958 • Published • 107 -
MMVU: Measuring Expert-Level Multi-Discipline Video Understanding
Paper • 2501.12380 • Published • 85 -
VideoWorld: Exploring Knowledge Learning from Unlabeled Videos
Paper • 2501.09781 • Published • 28
-
LinFusion: 1 GPU, 1 Minute, 16K Image
Paper • 2409.02097 • Published • 34 -
Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion
Paper • 2409.11406 • Published • 27 -
Diffusion Models Are Real-Time Game Engines
Paper • 2408.14837 • Published • 126 -
Segment Anything with Multiple Modalities
Paper • 2408.09085 • Published • 22
-
CraftsMan: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refiner
Paper • 2405.14979 • Published • 19 -
PLA4D: Pixel-Level Alignments for Text-to-4D Gaussian Splatting
Paper • 2405.19957 • Published • 10 -
GECO: Generative Image-to-3D within a SECOnd
Paper • 2405.20327 • Published • 11 -
gsplat: An Open-Source Library for Gaussian Splatting
Paper • 2409.06765 • Published • 17
-
TextureDreamer: Image-guided Texture Synthesis through Geometry-aware Diffusion
Paper • 2401.09416 • Published • 11 -
SHINOBI: Shape and Illumination using Neural Object Decomposition via BRDF Optimization In-the-wild
Paper • 2401.10171 • Published • 14 -
DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Model
Paper • 2311.09217 • Published • 22 -
GALA: Generating Animatable Layered Assets from a Single Scan
Paper • 2401.12979 • Published • 9
-
FlashWorld: High-quality 3D Scene Generation within Seconds
Paper • 2510.13678 • Published • 70 -
NANO3D: A Training-Free Approach for Efficient 3D Editing Without Masks
Paper • 2510.15019 • Published • 62 -
GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction
Paper • 2509.18090 • Published • 3 -
Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation
Paper • 2509.19296 • Published • 22