When Depth Lies: Benchmarking Vision-Language Models on Mirror-Induced RGB-D Ambiguity
cs.CV
Submitted: 2026-10-30
Updated: 2026-10-30
Comments: NeurIPS 2026 E&D Track accepted
Code: https://github.com/EvaYin-cloud/MIRA-Bench
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Gradio: Hassle-Free Sharing and Testing of ML Models in the Wild
- Qwen3-VL Technical Report
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- Multimodal Referring Segmentation: A Survey
- BLINK: Multimodal Large Language Models Can See but Not Perceive
- SSMNBench: Diagnosing Image-based Cross-View Human-Object Understanding via Single-View Sufficiency and Multi-View Necessity
- Spatial Reasoning in Multimodal Large Language Models: A Survey of Tasks, Benchmarks and Methods
- N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models
- MirrorSAM2: Segment Mirror in Videos with Depth Perception
- Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks
- Video-MSR: Benchmarking Multi-hop Spatial Reasoning Capabilities of MLLMs
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs