Scene Understanding

Leveraging BEV Paradigm for Ground-to-Aerial Image Synthesis ICCV 2025 Leveraging Local Patch Alignment to Seam-cutting for Large Parallax Image Stitching ICCV 2025 Leveraging Panoptic Scene Graph for Evaluating Fine-Grained Text-to-Image Generation ICCV 2025 Lifting the Structural Morphing for Wide-Angle Images Rectification: Unified Content and Boundary Modeling ICCV 2025 LLMs Can Compensate for Deficiencies in Visual Representations EMNLP 2025 Local Scale Equivariance with Latent Deep Equilibrium Canonicalizer ICCV 2025 Look Around Before Locating: Considering Content and Structure Information for Visual Grounding AAAI 2025 MammAlps: A Multi-view Video Behavior Monitoring Dataset of Wild Mammals in the Swiss Alps CVPR 2025 Masked Scene Modeling: Narrowing the Gap Between Supervised and Self-Supervised Learning in 3D Scene Understanding CVPR 2025 MATCHA: Towards Matching Anything CVPR 2025 MAVias: Mitigate any Visual Bias ICCV 2025 MemFusionMap: Working Memory Fusion for Online Vectorized HD Map Construction WACV 2025 Mesh Mamba: A Unified State Space Model for Saliency Prediction in Non-Textured and Textured Meshes CVPR 2025 MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling CVPR 2025 Mind the Gap: Aligning Vision Foundation Models to Image Feature Matching ICCV 2025 MINIMA: Modality Invariant Image Matching CVPR 2025 MirrorVerse: Pushing Diffusion Models to Realistically Reflect the World CVPR 2025 Mitigating Hallucinations in Multimodal Spatial Relations through Constraint-Aware Prompting NAACL 2025 Monocular Semantic Scene Completion via Masked Recurrent Networks ICCV 2025 MovieBench: A Hierarchical Movie Level Dataset for Long Video Generation CVPR 2025 MSR2: A Benchmark for Multi-Source Retrieval and Reasoning in Visual Question Answering NAACL 2025 MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering ACL 2025 MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding ICLR 2025 Multi-Modal Aerial-Ground Cross-View Place Recognition with Neural ODEs CVPR 2025 Multi-Modal Synergistic Implicit Image Enhancement for Efficient Optical Flow Estimation CVPR 2025