Computer Vision › Analysis ›

Scene Understanding

1887 directly classified papers

Papers per year

Papers

Masked Scene Modeling: Narrowing the Gap Between Supervised and Self-Supervised Learning in 3D Scene Understanding CVPR 2025

IAAO: Interactive Affordance Learning for Articulated Objects in 3D Environments CVPR 2025

Robust and Efficient 3D Gaussian Splatting for Urban Scene Reconstruction ICCV 2025

FG^2: Fine-Grained Cross-View Localization by Fine-Grained Feature Matching CVPR 2025

Building Vision Models upon Heat Conduction CVPR 2025

Reasoning Mamba: Hypergraph-Guided Region Relation Calculating for Weakly Supervised Affordance Grounding CVPR 2025

Do It Yourself: Learning Semantic Correspondence from Pseudo-Labels ICCV 2025

MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling CVPR 2025

MovieBench: A Hierarchical Movie Level Dataset for Long Video Generation CVPR 2025

Unified Reconstruction of Static and Dynamic Scenes from Events CVPR 2025

Gaze-LLE: Gaze Target Estimation via Large-Scale Learned Encoders CVPR 2025

Lifting the Structural Morphing for Wide-Angle Images Rectification: Unified Content and Boundary Modeling ICCV 2025

MATCHA: Towards Matching Anything CVPR 2025

Hierarchical 3D Scene Graphs Construction Outdoors ICCV 2025

Supercharging Floorplan Localization with Semantic Rays ICCV 2025

Less is More: Empowering GUI Agent with Context-Aware Simplification ICCV 2025

ChartPoint: Guiding MLLMs with Grounding Reflection for Chart Reasoning ICCV 2025

2HandedAfforder: Learning Precise Actionable Bimanual Affordances from Human Videos ICCV 2025

A Unified Framework for Industrial Cel-Animation Colorization with Temporal-Structural Awareness ICCV 2025

PanSt3R: Multi-view Consistent Panoptic Segmentation ICCV 2025

CLIPSym: Delving into Symmetry Detection with CLIP ICCV 2025

MAVias: Mitigate any Visual Bias ICCV 2025

Trial-Oriented Visual Rearrangement ICCV 2025

NoiseController: Towards Consistent Multi-view Video Generation via Noise Decomposition and Collaboration ICCV 2025

Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstruction ICCV 2025