OVOW reconstructs instance-level, simulation-ready 4D mesh scenes from monocular video via a four-stage training-free pipeline and introduces a new benchmark for structured Video-to-4D evaluation.
Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
abstract
Vision-as-inverse-graphics, the concept of reconstructing images into editable programs, remains challenging for Vision-Language Models (VLMs), which inherently lack fine-grained spatial grounding in one-shot settings. To address this, we introduce VIGA (Vision-as-Inverse-Graphics Agent), an interleaved multimodal reasoning framework where symbolic logic and visual perception actively cross-verify each other. VIGA operates through a tightly coupled code-render-inspect loop: synthesizing symbolic programs, projecting them into visual states, and inspecting discrepancies to guide iterative edits. Equipped with high-level semantic skills and an evolving multimodal memory, VIGA sustains evidence-based modifications over long horizons. This training-free, task-agnostic framework seamlessly supports 2D document generation, 3D reconstruction, multi-step 3D editing, and 4D physical interaction. Finally, we introduce BlenderBench, a challenging visual-to-code benchmark. Empirically, VIGA substantially improves accuracy compared with one-shot baselines in BlenderGym (35.32%), SlideBench (117.17%) and our proposed BlenderBench (124.70%).
citation-role summary
background 1
citation-polarity summary
years
2026 10roles
background 1polarities
background 1representative citing papers
P3D-Bench is a benchmark with three task families that scores MLLMs on generating executable parametric 3D programs, finding failures in precise geometry and part assembly.
SEIG uses staged VLM prompting to output executable Blender programs that reconstruct editable 3D scenes from single images, showing improved fidelity over non-staged baselines.
SceneOrchestra trains an orchestrator to generate full tool-call trajectories for 3D scene synthesis and uses a discriminator during training to select high-quality plans, yielding state-of-the-art results with lower runtime.
SimWorlds presents a multi-agent system with planner-coder-reviewer workflow, layered scene protocol, and runtime inspection tools to create dynamic 4D scenes from text, plus the 4DBuildBench benchmark showing outperformance over baselines.
Closed-loop VLM agents with multi-view feedback, object axes overlays, and single-axis rotations predict text-guided goal 6D poses better than prior methods and improve zero-shot robot manipulation.
SceneConductor decomposes single-image 3D scene generation into initialization, environment construction, and multi-agent refinement stages with a geometry-aware layout predictor trained on sparse geometric priors from point maps.
Code-as-Room is an MLLM-based agentic pipeline that parses top-down images into multi-stage Blender code synthesis with cross-stage memory to generate functional 3D rooms.
LychSim introduces a controllable simulation platform on Unreal Engine 5 with Python API, procedural generation, and LLM integration for vision research tasks.
citing papers explorer
-
One Video, One World: Turning Monocular Video into Physical 4D Scenes
OVOW reconstructs instance-level, simulation-ready 4D mesh scenes from monocular video via a four-stage training-free pipeline and introduces a new benchmark for structured Video-to-4D evaluation.
-
P3D-Bench: Benchmarking MLLMs for Parametric 3D Generation and Structural Reasoning
P3D-Bench is a benchmark with three task families that scores MLLMs on generating executable parametric 3D programs, finding failures in precise geometry and part assembly.
-
Thinking in Blender: Staged Executable Inverse Graphics with Vision-Language Models
SEIG uses staged VLM prompting to output executable Blender programs that reconstruct editable 3D scenes from single images, showing improved fidelity over non-staged baselines.
-
SceneOrchestra: Efficient Agentic 3D Scene Synthesis via Full Tool-Call Trajectory Generation
SceneOrchestra trains an orchestrator to generate full tool-call trajectories for 3D scene synthesis and uses a discriminator during training to select high-quality plans, yielding state-of-the-art results with lower runtime.
-
SimWorlds: A Multi-Agent System for Dynamic 3D Scene Creation
SimWorlds presents a multi-agent system with planner-coder-reviewer workflow, layered scene protocol, and runtime inspection tools to create dynamic 4D scenes from text, plus the 4DBuildBench benchmark showing outperformance over baselines.
-
Text-Guided 6D Object Pose Rearrangement via Closed-Loop VLM Agents
Closed-loop VLM agents with multi-view feedback, object axes overlays, and single-axis rotations predict text-guided goal 6D poses better than prior methods and improve zero-shot robot manipulation.
-
SceneConductor: 3D Scene Generation from a Single Image with Multi-Agent Orchestration
SceneConductor decomposes single-image 3D scene generation into initialization, environment construction, and multi-agent refinement stages with a geometry-aware layout predictor trained on sparse geometric priors from point maps.
-
Code-as-Room: Generating 3D Rooms from Top-Down View Images via Agentic Code Synthesis
Code-as-Room is an MLLM-based agentic pipeline that parses top-down images into multi-stage Blender code synthesis with cross-stage memory to generate functional 3D rooms.
-
LychSim: A Controllable and Interactive Simulation Framework for Vision Research
LychSim introduces a controllable simulation platform on Unreal Engine 5 with Python API, procedural generation, and LLM integration for vision research tasks.
- REST3D: Reconstructing Physically Stable 3D Scenes from a Single Image