Scene Understanding

ASHiTA: Automatic Scene-grounded HIerarchical Task Analysis CVPR 2025 A Unified Framework for Industrial Cel-Animation Colorization with Temporal-Structural Awareness ICCV 2025 Auto-Controlled Image Perception in MLLMs via Visual Perception Tokens ICCV 2025 Axis-level Symmetry Detection with Group-Equivariant Representation ICCV 2025 Beyond Grids: Exploring Elastic Input Sampling for Vision Transformers WACV 2025 Beyond Visual Understanding Introducing PARROT-360V for Vision Language Model Benchmarking COLING 2025 Bootstraping Clustering of Gaussians for View-consistent 3D Scene Understanding AAAI 2025 Breaking the Frame: Visual Place Recognition by Overlap Prediction WACV 2025 Bridging Language and Scenes through Explicit 3-D Model Construction COLING 2025 Bridging Viewpoint Gaps: Geometric Reasoning Boosts Semantic Correspondence CVPR 2025 Building Vision Models upon Heat Conduction CVPR 2025 Can Machines Understand Composition? Dataset and Benchmark for Photographic Image Composition Embedding and Understanding CVPR 2025 Change3D: Revisiting Change Detection and Captioning from A Video Modeling Perspective CVPR 2025 ChartCap: Mitigating Hallucination of Dense Chart Captioning ICCV 2025 ChartPoint: Guiding MLLMs with Grounding Reflection for Chart Reasoning ICCV 2025 CityNav: A Large-Scale Dataset for Real-World Aerial Navigation ICCV 2025 ClaraVid: A Holistic Scene Reconstruction Benchmark From Aerial Perspective With Delentropy-Based Complexity Profiling ICCV 2025 Class-Agnostic Visio-Temporal Scene Sketch Semantic Segmentation WACV 2025 ClimateViz: A Benchmark for Statistical Reasoning and Fact Verification on Scientific Charts EMNLP 2025 CLIP is Almost All You Need: Towards Parameter-Efficient Scene Text Retrieval without OCR CVPR 2025 CLIPSym: Delving into Symmetry Detection with CLIP ICCV 2025 CObL: Toward Zero-Shot Ordinal Layering without User Prompting ICCV 2025 Compositional Scene Understanding through Inverse Generative Modeling ICML 2025 Contact-Aware Amodal Completion for Human-Object Interaction via Multi-Regional Inpainting ICCV 2025 Contrastive Learning of Image Representations Guided by Spatial Relations WACV 2025