HARMONY: Hierarchical Agentic Reasoning for MONocular Image-to-Scene Synthesis

arXiv:2609.26793 · cs.CV · Submitted 2026-09-22 · Read on arXiv

cs.CV

Submitted: 2026-09-22

Updated: 2026-10-05

Code: https://github.com/FishWoWater/CAST

Project page: https://cwchenwang.github.io/harmony

Terminology

• Alignment — 12× in this paper · explained in 1 episode
• Calibration — 11× in this paper · explained in 7 episodes
• Grounding — 8× in this paper · explained in 3 episodes
• Agentic Reasoning — 6× in this paper · explained in 1 episode
• Fidelity — 6× in this paper · explained in 2 episodes
• Foundation Model — 6× in this paper · explained in 3 episodes
• Foundation Models — 6× in this paper · explained in 7 episodes
• Verification — 6× in this paper · explained in 2 episodes
• Point Clouds — 5× in this paper · explained in 2 episodes
• Benchmark — 4× in this paper · explained in 2 episodes
• Diffusion Model — 4× in this paper · explained in 8 episodes
• Embodied AI — 4× in this paper · explained in 2 episodes
• Transactions on Graphics — 4× in this paper
• Transformer — 4× in this paper · explained in 2 episodes
• Instance Segmentation — 3× in this paper · explained in 3 episodes
• Structured Reasoning — 3× in this paper · explained in 3 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Amodal Completion — 2× in this paper · explained in 1 episode
• Clustering — 2× in this paper · explained in 2 episodes
• Conference on Computer Vision and Pattern Recognition — 2× in this paper
• Consistency — 2× in this paper · explained in 3 episodes
• Diffusion Models — 2× in this paper · explained in 6 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Generative Model — 2× in this paper · explained in 2 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Sparse Attention — 2× in this paper · explained in 5 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Affordance — 1× in this paper · explained in 1 episode
• Chamfer Distance — 1× in this paper
• Decode — 1× in this paper · explained in 2 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Human-in-the-Loop — 1× in this paper · explained in 3 episodes
• Metallicity — 1× in this paper · explained in 3 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Principal Component Analysis — 1× in this paper
• Principal Component Analysis (PCA) — 1× in this paper · explained in 4 episodes
• Rectified Flow — 1× in this paper · explained in 3 episodes
• Semantic Alignment — 1× in this paper · explained in 3 episodes
• Semantic Understanding — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
• Qwen2.5-VL Technical Report
• HOLODECK 2.0: Vision-Language-Guided 3D World Generation with Editing
• Segment Anything
• Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection
• Agentic 3D Scene Generation with Spatially Contextualized VLMs
• SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass
• SceneSmith: Agentic Generation of Simulation-Ready Indoor Scenes
• SAM 2: Segment Anything in Images and Videos
• SAM 3D: 3Dfy Anything in Images
• 3D-RE-GEN: 3D Reconstruction of Indoor Scenes with a Generative Framework
• ZeroScene: A Zero-Shot Framework for 3D Scene Generation from a Single Image and Controllable Texture Editing
• Qwen3 Technical Report
• Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details
• Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation
• Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
• LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding
• Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention
• SAGE: Scalable Agentic 3D Scene Generation for Embodied AI
• Structured 3D Latents for Scalable and Versatile 3D 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