DistScene: Object-to-Scene Distillation for 3D Scene Generation
cs.CV
Submitted: 2026-10-03
Updated: 2026-10-03
Comments: Project page:https://coolbeam.github.io/DistScene/
Project page: https://coolbeam.github.io/DistScene
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Boxer: Robust Lifting of Open-World 2D Bounding Boxes to 3D
- Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material
- Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details
- CraftsMan3D: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refiner
- Depth Anything 3: Recovering the Visual Space from Any Views
- AutoWeather4D: Autonomous Driving Video Weather Conversion via G-Buffer Dual-Pass Editing
- SpatialLM: Training Large Language Models for Structured Indoor Modeling
- Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks
- ZeroScene: A Zero-Shot Framework for 3D Scene Generation from a Single Image and Controllable Texture Editing
- GRUtopia: Dream General Robots in a City at Scale
- VGGT-$\Omega$
- $\pi^3$: Permutation-Equivariant Visual Geometry Learning
- 3D-Fixer: Coarse-to-Fine In-place Completion for 3D Scenes from a Single Image
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models