Diffusionff Cvpr 2026

DiffusionFF

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

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

Joonki Min, Chaeyun Kim, Hyungwook Choi, Yejin Kim, Kihyun Kim, Yohan Jo, Joonseok Lee. Fine-Grained Multi-Image Object ...

Title: Scene-Centric Unsupervised Video Panoptic Segmentation Authors: Christoph Reich*, Oliver Hahn*, Nikita Araslanov, ...

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

Poster Presentation

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

[

Chengxing Lin, Jinhong Deng, Yinjie Lei, Wen Li. "Deformation-based In-Context Learning for Point Cloud Understanding.

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

Hyun Lee, Hyemin Jeong, Yejin Kim, Hyungwook Choi, Hyunsoo Cho, Soo Kyung Kim, Joonseok Lee. A More Word-like Image ...

Video2Robo: 3DGS-based Synthetic Data from One Video Enables Scalable Robot Learning Project page: ...

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

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

TAPE: Task-Adaptive Prototype Evolution in Audio-Language Models for Fully Few-shot Class-incremental Audio Classification.

This is the official 5-minute poster presentation video for

CVPR 2026

Toward Real-world Infrared Image Super-Resolution: A Unified Autoregressive Framework and Benchmark Dataset Official ...

This is a mandatory video for