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
MammAlps: A Multi-view Video Behavior Monitoring Dataset of Wild Mammals in the Swiss Alps
MangaNinja: Line Art Colorization with Precise Reference Following
Mani-GS: Gaussian Splatting Manipulation with Triangular Mesh
ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning
ManiVideo: Generating Hand-Object Manipulation Video with Dexterous and Generalizable Grasping
MANTA: A Large-Scale Multi-View and Visual-Text Anomaly Detection Dataset for Tiny Objects
MANTA: Diffusion Mamba for Efficient and Effective Stochastic Long-Term Dense Action Anticipation
MAR-3D: Progressive Masked Auto-regressor for High-Resolution 3D Generation
MARBLE: Material Recomposition and Blending in CLIP-Space
MaRI: Material Retrieval Integration across Domains
MarkushGrapher: Joint Visual and Textual Recognition of Markush Structures
Marten: Visual Question Answering with Mask Generation for Multi-modal Document Understanding
MARVEL-40M+: Multi-Level Visual Elaboration for High-Fidelity Text-to-3D Content Creation
MASH-VLM: Mitigating Action-Scene Hallucination in Video-LLMs through Disentangled Spatial-Temporal Representations
Mask^2DiT: Dual Mask-based Diffusion Transformer for Multi-Scene Long Video Generation
Mask-Adapter: The Devil is in the Masks for Open-Vocabulary Segmentation
Masked Point-Entity Contrast for Open-Vocabulary 3D Scene Understanding
Masked Scene Modeling: Narrowing the Gap Between Supervised and Self-Supervised Learning in 3D Scene Understanding
MaskGaussian: Adaptive 3D Gaussian Representation from Probabilistic Masks
MaskGWM: A Generalizable Driving World Model with Video Mask Reconstruction
Masking meets Supervision: A Strong Learning Alliance
MaSS13K: A Matting-level Semantic Segmentation Benchmark
MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors
MatAnyone: Stable Video Matting with Consistent Memory Propagation
MAtCha Gaussians: Atlas of Charts for High-Quality Geometry and Photorealism From Sparse Views
MATCHA: Towards Matching Anything
Material Anything: Generating Materials for Any 3D Object via Diffusion
Matrix3D: Large Photogrammetry Model All-in-One
Matrix-Free Shared Intrinsics Bundle Adjustment
MBQ: Modality-Balanced Quantization for Large Vision-Language Models
MC^2: Multi-concept Guidance for Customized Multi-concept Generation
MCCD: Multi-Agent Collaboration-based Compositional Diffusion for Complex Text-to-Image Generation
MDP: Multidimensional Vision Model Pruning with Latency Constraint
MEAT: Multiview Diffusion Model for Human Generation on Megapixels with Mesh Attention
Medal S: Spatio-Textual Prompt Model for Medical Segmentation
MedUnifier: Unifying Vision-and-Language Pre-training on Medical Data with Vision Generation Task using Discrete Visual Representations
Medusa: A Multi-Scale High-order Contrastive Dual-Diffusion Approach for Multi-View Clustering
MEET: Towards Memory-Efficient Temporal Sparse Deep Neural Networks
MeGA: Hybrid Mesh-Gaussian Head Avatar for High-Fidelity Rendering and Head Editing
MegaLoc: One Retrieval to Place Them All
MEGA: Masked Generative Autoencoder for Human Mesh Recovery
MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos
MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data
Mem2Ego: Empowering Vision-Language Models with Global-to-Ego Memory for Long-Horizon Embodied Navigation
Memories of Forgotten Concepts
Memory-based Adapters for Online 3D Scene Perception
MERGE: Multi-faceted Hierarchical Graph-based GNN for Gene Expression Prediction from Whole Slide Histopathology Images
MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization
MESC-3D: Mining Effective Semantic Cues for 3D Reconstruction from a Single Image
MeshGen: Generating PBR Textured Mesh with Render-Enhanced Auto-Encoder and Generative Data Augmentation

« prev Page 32/59 next »