Cvpr 2026 Flowportal

CVPR 2026

Adaptive Spatial-Temporal Window: Unlocking the Potential of Event Cameras in Heterogeneous Velocity Scenarios Zhipeng Sui, ...

How much do video diffusion models know about the 4D world? By introducing a 4D VAE, we jointly estimate geometry and ...

Disentangle-then-Align: Non-Iterative Hybrid Multimodal Image Registration via Cross-Scale Feature Disentanglement.

Title:MU-GeNeRF: Multi-view Uncertainty-guided Generalizable Neural Radiance Fields for Distractor-aware Scene ...

VIMCAN: Visual-Inertial 3D Human Pose Estimation with Hybrid Mamba-Cross-Attention Network.

MixerCSeg: An Efficient Mixer Architecture for Crack Segmentation via Decoupled Mamba Attention.

Video for FG-Portrait: 3D Flow Guided Editable Portrait Animation (

Large-Scale Codec Avatars (LCA): The Unreasonable Effectiveness of Large-Scale Avatar Pretraining

Paper: https://arxiv.org/abs/2512.01390 Project Page: https://cmlab-korea.github.io/FRAMER/ Authors/Affiliations: [Seungho ...

[

UniPR: Unified Object-level Real-to-Sim Perception and Reconstruction from a Single Stereo Pair Project Page: ...

The 5-minute introduction video of IntrinsicWeather.

CVPR 2026

DiffusionFF: A Diffusion-based Framework for Joint Face Forgery Detection and Fine-Grained Artifact Localization (

Differentiable Stroke Planning with Dual Parameterization for Efficient and High-Fidelity Painting Creation》 In stroke-based ...

[CVPR 2026] VGent: Visual Grounding via Modular Design for Disentangling Reasoning and Prediction

Youtube video presentation of

In this video, we introduce a novel video object detection framework called D2FANet. D2FANet is the first framework to jointly ...