CineRecon: Benchmarking Frontier Models for Agentic Cinematic Reconstruction
cs.CV
Submitted: 2026-10-12
Updated: 2026-10-12
Comments: 24 pages, 19 figures. Project page: https://cinerecon.github.io/
Project page: https://cinerecon.github.io
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- TC-Bench: Benchmarking Temporal Compositionality in Text-to-Video and Image-to-Video Generation
- 3DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via Code
- Thinking in Blender: Staged Executable Inverse Graphics with Vision-Language Models
- CameraCtrl: Enabling Camera Control for Text-to-Video Generation
- Re-Thinking Inverse Graphics With Large Language Models
- VisPhyWorld: Probing Physical Reasoning via Code-Driven Video Reconstruction
- SimWorlds: A Multi-Agent System for Dynamic 3D Scene Creation
- 4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes
- BVB: Benchmarking Agentic Video Understanding via Programmatic Reconstruction in Blender
- Code2Worlds: Empowering Coding LLMs for 4D World Generation
- SceneActBench: Can Agents Act on the 3D Scenes They See?
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