CoDimRecon: Agentic Reconstruction of Sim-Ready 3D Scenes with Deformable Curves, Surfaces, and Volumes

arXiv:2609.36024 · cs.CV, cs.GR, cs.RO · Submitted 2026-09-28 · Read on arXiv

cs.CV, cs.GR, cs.RO

Submitted: 2026-09-28

Updated: 2026-10-03

Code: https://github.com/LiteReality/LiteReality-Agent

Project page: https://shuzhaoxie.github.io/CoDimRecon

Terminology

• Alignment — 14× in this paper · explained in 1 episode
• Verification — 9× in this paper · explained in 2 episodes
• Ablation — 8× in this paper · explained in 1 episode
• Agentic Framework — 4× in this paper · explained in 6 episodes
• Latent Similarity — 4× in this paper
• Clustering — 3× in this paper · explained in 2 episodes
• Conference on Computer Vision and Pattern Recognition — 3× in this paper
• Cosine Similarity — 3× in this paper · explained in 3 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Fidelity — 2× in this paper · explained in 2 episodes
• Gaussian Splatting — 2× in this paper · explained in 4 episodes
• Grounding — 2× in this paper · explained in 3 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Agentic Loop — 1× in this paper · explained in 1 episode
• Agentic System — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 4 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Embodied AI — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Instance Segmentation — 1× in this paper · explained in 3 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Self-Supervised Learning — 1× in this paper · explained in 8 episodes

Sources

• SAM 3: Segment Anything with Concepts
• Engine-Native Editable 3D World Reconstruction with Objects and Lighting
• ReplicateAnyScene: Zero-Shot Video-to-3D Composition via Textual-Visual-Spatial Alignment
• LiteReality: Graphics-Ready 3D Scene Reconstruction from RGB-D Scans
• SimuScene: Simulation-Ready Compositional 3D Scene Reconstruction from a Single Image
• $\phi$-Scene: Physically Grounded Image-to-3D Scene Reconstruction
• Advances in 3D Generation: A Survey
• Gaussian Object Carver: Object-Compositional Gaussian Splatting with surfaces completion
• REST3D: Reconstructing Physically Stable 3D Scenes from a Single Image
• V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning
• PhyRecon: Physically Plausible Neural Scene Reconstruction
• Decompositional Neural Scene Reconstruction with Generative Diffusion Prior
• SceneSmith: Agentic Generation of Simulation-Ready Indoor Scenes
• Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling
• SAM 3D: 3Dfy Anything in Images
• The Replica Dataset: A Digital Replica of Indoor Spaces
• BVB: Benchmarking Agentic Video Understanding via Programmatic Reconstruction in Blender
• VGGT-$\Omega$
• TabletopGen: Tabletop Scene Generation and Interactive Simulation for Robotic Manipulation
• FIRE3D: Feed-forward Interactive 3D Scene Reconstruction Within A Minute

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