Computer Vision

TryOn-Refiner: Conditional Rectified-flow-based TryOn Refiner for More Accurate Detail Reconstruction ICCV 2025 TSAM: Temporal SAM Augmented with Multimodal Prompts for Referring Audio-Visual Segmentation CVPR 2025 TSC-Net: Prediction of Pedestrian Trajectories by Trajectory-Scene-Cell Classification ICLR 2025 TSDF-Based Efficient Motion-Compensated Temporal Interpolation for 3D Dynamic Sequences AAAI 2025 TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolution CVPR 2025 TSDT-Net: Ultra-Low-Complexity Two-Stage Model Combining Dual-Path-Transformer and Transform-Average-Concatenate Network for Speech Enhancement Interspeech 2025 TSP-Mamba: The Travelling Salesman Problem Meets Mamba for Image Super-resolution and Beyond CVPR 2025 T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching ICLR 2025 TUNA: Comprehensive Fine-grained Temporal Understanding Evaluation on Dense Dynamic Videos ACL 2025 Tune-Your-Style: Intensity-tunable 3D Style Transfer with Gaussian Splatting ICCV 2025 Turbo2K: Towards Ultra-Efficient and High-Quality 2K Video Synthesis ICCV 2025 TurboFill: Adapting Few-step Text-to-image Model for Fast Image Inpainting CVPR 2025 TurboReg: TurboClique for Robust and Efficient Point Cloud Registration ICCV 2025 TurboVSR: Fantastic Video Upscalers and Where to Find Them ICCV 2025 TurnBack: A Geospatial Route Cognition Benchmark for Large Language Models through Reverse Route EMNLP 2025 TVQACML: Benchmarking Text-Centric Visual Question Answering in Multilingual Chinese Minority Languages EMNLP 2025 TweedieMix: Improving Multi-Concept Fusion for Diffusion-based Image/Video Generation ICLR 2025 Twinner: Shining Light on Digital Twins in a Few Snaps CVPR 2025 TWIST: Text-encoder Weight-editing for Inserting Secret Trojans in Text-to-Image Models ACL 2025 Two by Two: Learning Multi-Task Pairwise Objects Assembly for Generalizable Robot Manipulation CVPR 2025 Twofold Debiasing Enhances Fine-Grained Learning with Coarse Labels AAAI 2025 Two Heads Are Enough: DualU-Net, a Fast and Efficient Architecture for Nuclei Instance Segmentation MIDL 2025 Two Losses, One Goal: Balancing Conflict Gradients for Semi-supervised Semantic Segmentation ICCV 2025 Two-stream Beats One-stream: Asymmetric Siamese Network for Efficient Visual Tracking AAAI 2025 Type-R: Automatically Retouching Typos for Text-to-Image Generation CVPR 2025