CVPR 2025

2,907 papers

Top Research Directions

Research directions most represented by CVPR 2025 papers.

Overcoming the Static Scene Assumption 49
Mitigating Multi View Inconsistency in Generative 3D Modeling 48
Eliminating Per-Scene Optimization with Feed-Forward 3D Reconstruction 42
Generalizing from Synthetic Data to the Real World 39
Material Lighting Disentanglement for 3D Reconstruction 37
Spatial Attention Masking in Generative Diffusion Models 36
Error Propagation in Monocular Depth Priors 32
Overcoming the Iterative Inference Latency of Diffusion Models 31
Exploiting Temporal Redundancy in Video Neural Networks 29
Aligning Global Semantics with Local Spatial Precision 28
Scaling Visual Attention Beyond Quadratic Complexity 28
Accelerating Neural Scene Representations for Real Time Rendering 27
Visual Grounding and Hallucination in Vision Language Models 27
Completing Unobserved Geometry with Generative Diffusion Priors 24
The Cross Modal Representation Gap 24

Top Authors

AuthorPapers
Yujun Shen17
Marc Pollefeys15
Daniel Cremers13
Jian Yang13
Jan Kautz11
Ziwei Liu11
Federico Tombari10
Guangtao Zhai10
Jiangning Zhang10
Christian Theobalt9
Jiajun Wu9
Ming-Hsuan Yang9
Ranjay Krishna9
Wei-Shi Zheng9
Xiongkuo Min9
Zhe Lin9
Zheng-Jun Zha9
Andrea Vedaldi8
Chen Change Loy8
Cheng Wang8

Impactful Papers

Papers from CVPR 2025 that shaped research clusters.

Foundational

Influential

Papers

Title
Homogeneous Dynamics Space for Heterogeneous Humans
HOP: Heterogeneous Topology-based Multimodal Entanglement for Co-Speech Gesture Generation
Horizon-GS: Unified 3D Gaussian Splatting for Large-Scale Aerial-to-Ground Scenes
HORP: Human-Object Relation Priors Guided HOI Detection
HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos
HOTFormerLoc: Hierarchical Octree Transformer for Versatile Lidar Place Recognition Across Ground and Aerial Views
HOT: Hadamard-based Optimized Training
HotSpot: Signed Distance Function Optimization with an Asymptotically Sufficient Condition
HoVLE: Unleashing the Power of Monolithic Vision-Language Models with Holistic Vision-Language Embedding
How Do I Do That? Synthesizing 3D Hand Motion and Contacts for Everyday Interactions
How to Merge Your Multimodal Models Over Time?
HRAvatar: High-Quality and Relightable Gaussian Head Avatar
HSI: A Holistic Style Injector for Arbitrary Style Transfer
HSI-GPT: A General-Purpose Large Scene-Motion-Language Model for Human Scene Interaction
Human-centered Interactive Learning via MLLMs for Text-to-Image Person Re-identification
HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation
HumanMM: Global Human Motion Recovery from Multi-shot Videos
Human Motion Instruction Tuning
HumanRig: Learning Automatic Rigging for Humanoid Character in a Large Scale Dataset
HumMorph: Generalized Dynamic Human Neural Fields from Few Views
HuMoCon: Concept Discovery for Human Motion Understanding
HUNet: Homotopy Unfolding Network for Image Compressive Sensing
HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animation
HuPerFlow: A Comprehensive Benchmark for Human vs. Machine Motion Estimation Comparison
HUSH: Holistic Panoramic 3D Scene Understanding using Spherical Harmonics
HVI: A New Color Space for Low-light Image Enhancement
Hybrid Concept Bottleneck Models
Hybrid Global-Local Representation with Augmented Spatial Guidance for Zero-Shot Referring Image Segmentation
HybridGS: Decoupling Transients and Statics with 2D and 3D Gaussian Splatting
Hybrid-Level Instruction Injection for Video Token Compression in Multi-modal Large Language Models
HybridMQA: Exploring Geometry-Texture Interactions for Colored Mesh Quality Assessment
Hybrid Reciprocal Transformer with Triplet Feature Alignment for Scene Graph Generation
Hyperbolic Safety-Aware Vision-Language Models
Hyperbolic Uncertainty-Aware Few-Shot Incremental Point Cloud Segmentation
Hyperdimensional Uncertainty Quantification for Multimodal Uncertainty Fusion in Autonomous Vehicles Perception
HyperFree: A Channel-adaptive and Tuning-free Foundation Model for Hyperspectral Remote Sensing Imagery
HyperGLM: HyperGraph for Video Scene Graph Generation and Anticipation
Hypergraph Vision Transformers: Images are More than Nodes, More than Edges
HyperGS: Hyperspectral 3D Gaussian Splatting
HyperLoRA: Parameter-Efficient Adaptive Generation for Portrait Synthesis
HyperNet Fields: Efficiently Training Hypernetworks without Ground Truth by Learning Weight Trajectories
HyperNVD: Accelerating Neural Video Decomposition via Hypernetworks
HyperPose: Hypernetwork-Infused Camera Pose Localization and an Extended Cambridge Landmarks Dataset
HyperSeg: Hybrid Segmentation Assistant with Fine-grained Visual Perceiver
Hyperspectral Pansharpening via Diffusion Models with Iteratively Zero-Shot Guidance
I2VGuard: Safeguarding Images against Misuse in Diffusion-based Image-to-Video Models
IAAO: Interactive Affordance Learning for Articulated Objects in 3D Environments
IceDiff: High Resolution and High-Quality Arctic Sea Ice Forecasting with Generative Diffusion Prior
Ice Hockey Puck Localization Using Contextual Cues
ICE: Intrinsic Concept Extraction from a Single Image via Diffusion Models

« prev Page 25/59 next »