Research map / 3D vision / 3D generation
AREA3D: Active Reconstruction Agent with Unified Feed-Forward 3D Perception and Vision-Language Guidance
Tianling Xu, Shengzhe Gan, Leslie Gu, Yuelei Li, Fangneng Zhan, Hanspeter Pfister
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add feed-forward geometric uncertainty to VLM guidance (ablation) | AREA3D · Object-level ablation | PSNR: 29.02 -> 32.09 | Improved |
| add feed-forward geometric uncertainty to VLM guidance (ablation) | AREA3D · Scene-level ablation | PSNR: 29.10 -> 32.40 | Improved |
| add VLM semantic guidance to feed-forward uncertainty (ablation) | AREA3D · Scene-level ablation | PSNR: 31.26 -> 32.40 | Improved |
| add VLM semantic guidance to feed-forward uncertainty (ablation) | AREA3D · Object-level ablation | SSIM: 0.896 -> 0.886 | Hurt |
| add VLM guidance (ablation) | AREA3D · Object-level (OmniObject3D) single-object | PSNR: 29.74 -> 31.59 | Improved |
| add VLM guidance (ablation) | AREA3D · Replica room0 | PSNR: 28.53 -> 29.23 | Improved |
| AREA3D vs FisherRF view selection | AREA3D · Replica office0 | PSNR: 27.13 -> 32.98 | Improved |
| naive VLM-based planner instead of random sampling | VLM-based baseline · Replica room0 | PSNR: 28.17 -> 27.21 | Hurt |
| AREA3D vs Air-Embodied on multi-object scenes | AREA3D · Object-level 7-objects 1 | PSNR: 28.35 -> 33.44 | Improved |
| lower voxel size from 0.5 to 0.2 (ablation) | AREA3D · Scalability | runtime (s): 138 -> 207 | Hurt |
Closest papers by meaning
- Active3D: Active High-Fidelity 3D Reconstruction via Multi-Level Uncertainty Quantification (AAAI 2026 · similarity 0.89)
- IR3D-Bench: Evaluating Vision-Language Model Scene Understanding as Agentic Inverse Rendering (NeurIPS 2025 · similarity 0.88)
- Agent3D-Zero: An Agent for Zero-shot 3D Understanding (ECCV 2024 · similarity 0.88)
- EA3D: Online Open-World 3D Object Extraction from Streaming Videos (NeurIPS 2025 · similarity 0.86)
- Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoning (CVPR 2024 · similarity 0.85)
- Video Perception Models for 3D Scene Synthesis (NeurIPS 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
