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
Scene Splatter: Momentum 3D Scene Generation from Single Image with Video Diffusion Model
SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments
SCFlow2: Plug-and-Play Object Pose Refiner with Shape-Constraint Scene Flow
Schedule On the Fly: Diffusion Time Prediction for Faster and Better Image Generation
Science-T2I: Addressing Scientific Illusions in Image Synthesis
ScribbleLight: Single Image Indoor Relighting with Scribbles
SCSA: A Plug-and-Play Semantic Continuous-Sparse Attention for Arbitrary Semantic Style Transfer
SDBF: Steep-Decision-Boundary Fingerprinting for Hard-Label Tampering Detection of DNN Models
SDGOCC: Semantic and Depth-Guided Bird's-Eye View Transformation for 3D Multimodal Occupancy Prediction
Sea-ing in Low-light
SEAL: Semantic Attention Learning for Long Video Representation
Search and Detect: Training-Free Long Tail Object Detection via Web-Image Retrieval
SeCap: Self-Calibrating and Adaptive Prompts for Cross-view Person Re-Identification in Aerial-Ground Networks
SEC-Prompt: SEmantic Complementary Prompting for Few-Shot Class-Incremental Learning
Secret Lies in Color: Enhancing AI-Generated Images Detection with Color Distribution Analysis
SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restoration
See Further When Clear: Curriculum Consistency Model
SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding
Seeing A 3D World in A Grain of Sand
Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding
Seeing is Not Believing: Adversarial Natural Object Optimization for Hard-Label 3D Scene Attacks
Seeing More with Less: Human-like Representations in Vision Models
Seeing Speech and Sound: Distinguishing and Locating Audio Sources in Visual Scenes
Seeing the Abstract: Translating the Abstract Language for Vision Language Models
Seeing What Matters: Empowering CLIP with Patch Generation-to-Selection
Seek Common Ground While Reserving Differences: Semi-Supervised Image-Text Sentiment Recognition
Seeking Consistent Flat Minima for Better Domain Generalization via Refining Loss Landscapes
SEEN-DA: SEmantic ENtropy guided Domain-aware Attention for Domain Adaptive Object Detection
SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories
SegEarth-OV: Towards Training-Free Open-Vocabulary Segmentation for Remote Sensing Images
SegMAN: Omni-scale Context Modeling with State Space Models and Local Attention for Semantic Segmentation
Segment Any Motion in Videos
Segment Any-Quality Images with Generative Latent Space Enhancement
Segment Anything, Even Occluded
Segmenting Maxillofacial Structures in CBCT Volumes
Segment This Thing: Foveated Tokenization for Efficient Point-Prompted Segmentation
Self-Cross Diffusion Guidance for Text-to-Image Synthesis of Similar Subjects
Self-Evolving Visual Concept Library using Vision-Language Critics
Self-Expansion of Pre-trained Models with Mixture of Adapters for Continual Learning
Self-Learning Hyperspectral and Multispectral Image Fusion via Adaptive Residual Guided Subspace Diffusion Model
SelfSplat: Pose-Free and 3D Prior-Free Generalizable 3D Gaussian Splatting
Self-supervised ControlNet with Spatio-Temporal Mamba for Real-world Video Super-resolution
Self-Supervised Cross-View Correspondence with Predictive Cycle Consistency
Self-Supervised Large Scale Point Cloud Completion for Archaeological Site Restoration
Self-Supervised Learning for Color Spike Camera Reconstruction
Self-Supervised Spatial Correspondence Across Modalities
SemAlign3D: Semantic Correspondence between RGB-Images through Aligning 3D Object-Class Representations
Semantic and Expressive Variations in Image Captions Across Languages
Semantic and Sequential Alignment for Referring Video Object Segmentation
SemanticDraw: Towards Real-Time Interactive Content Creation from Image Diffusion Models

« prev Page 46/59 next »