CVPR 2024
2,857 papers
Top Research Directions
Research directions most represented by CVPR 2024 papers.
Top Authors
Impactful Papers
Papers from CVPR 2024 that shaped research clusters.
Foundational
MemFlow: Optical Flow Estimation and Prediction with Memory
foundational
Entropy Invariant Attention Scaling for
Customize your NeRF: Adaptive Source Driven 3D Scene Editing via Local-Global Iterative Training
foundational
Identity Preserving Textual Inversion
TransNeXt: Robust Foveal Visual Perception for Vision Transformers
foundational
Entropy Invariant Attention Scaling for
Style Injection in Diffusion: A Training-Free Approach for Adapting Large-Scale Diffusion Models for
foundational
Adaptive Latent Normalization in Diffusi
GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussi
foundational
Isotropic Regularization for 3D Gaussian
DiffusionTrack: Point Set Diffusion Model for Visual Object Tracking
foundational
Object Detection as a Denoising Diffusio
Overload: Latency Attacks on Object Detection for Edge Devices
foundational
Exploiting Post Processing Bottlenecks i
GoMAvatar: Efficient Animatable Human Modeling from Monocular Video Using Gaussians-on-Mesh
foundational
Mesh Embedded 3D Gaussian Splatting
BA-SAM: Scalable Bias-Mode Attention Mask for Segment Anything Model
foundational
Logarithmic Attention Scaling for Long C
Influential
TI2V-Zero: Zero-Shot Image Conditioning for Text-to-Video Diffusion Models
influential
Autoregressive Video Generation via Sequ
Text2QR: Harmonizing Aesthetic Customization and Scanning Robustness for Text-Guided QR Code Generat
influential
Harmonizing Visual Aesthetics and Machin
VideoLLM-online: Online Video Large Language Model for Streaming Video
influential
Parallel and Decoupled Video Processing
TI2V-Zero: Zero-Shot Image Conditioning for Text-to-Video Diffusion Models
influential
Localized Spatiotemporal Control via Mas
PortraitBooth: A Versatile Portrait Model for Fast Identity-Preserved Personalization
influential
Tuning Free Identity Preservation in Gen
Generating Human Motion in 3D Scenes from Text Descriptions
influential
Scene-Constrained 3D Human Motion Synthe
Make Pixels Dance: High-Dynamic Video Generation
influential
Autoregressive Video Generation via Sequ
DyBluRF: Dynamic Neural Radiance Fields from Blurry Monocular Video
influential
Sharp 3D Reconstruction from Motion Blur
Sonic VisionLM: Playing Sound with Vision Language Models
influential
Text as a Semantic Pivot for Multimodal