OuroReward: Sequential Reward Scheduling for Reinforcement Learning in Text-to-3D Generation
cs.CV
Submitted: 2026-10-02
Updated: 2026-10-02
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material
- MeshWeaver: Sparse-Voxel-Guided Surface Weaving for Autoregressive Mesh Generation
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Focal Reward: Balanced Reinforcement Learning under Rubric-Based Rewards
- Recent Advances in 3D Object and Scene Generation: A Survey
- A Survey On Text-to-3D Contents Generation In The Wild
- LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models
- FACE: A Face-based Autoregressive Representation for High-Fidelity and Efficient Mesh Generation
- FLUX3D: High-Fidelity 3D Gaussian Generation with Diffusion-Aligned Sparse Representation
- GT23D-Bench: A Comprehensive General Text-to-3D Generation Benchmark
- Point-E: A System for Generating 3D Point Clouds from Complex Prompts
- Shap-E: Generating Conditional 3D Implicit Functions
- Flow Matching for Generative Modeling
- MeshFlow: Mesh Generation with Equivariant Flow Matching
- Home3D 1.0: A High-Fidelity Image-to-3D Asset Generation System for Interior Design
- Meshy T2: Fast Native Mesh Generation with Flow Matching
- Enhancing Multi-Modal LLMs Reasoning via Difficulty-Aware Group Normalization
- Advances in GRPO for Generation Models: A Survey
- DanceGRPO: Unleashing GRPO on Visual Generation
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