Old projects are Here. Standard Projects CPAM Context-Preserving Adaptive Manipulation for Zero-Shot Real Image Editing PANDORA Pixel-wise attention dissolution and latent guidance for zero-shot object removal PhysMirror Physics-Aware Mirror Object Generation Shape2Animal Creative animal generation from natural silhouettes ShowFlow From Robust Single Concept to Condition-Free Multi-Concept Generation PhysPlan Physics-Aware Video Generation via Agentic Planning and Graph-Guided Optimization SketchBloom Training-Free Vector Sketch Outpainting with Stroke-Level Style Control FocusDiff A tuning-free framework for precise region-specific image manipulation based on refocusing cross-attention. Semi-Supervised Video Instance Segmentation Semi-supervised video instance segmentation in CVPR DAVIS Challenge series SeeME Retrieval-augmented framework for imaginative animal art generation from ambiguous silhouettes GUNNEL Multi-model fusion and guided mixup augmentation for robust aquatic animal instance segmentation MaskDiff Modeling mask distribution with diffusion models for few-shot instance segmentation NearbyPatchCL Self-supervised patch-level classification in WSIs using nearby patch contrast ACS-nnU-Net Efficient 3D brain tumor segmentation with Axial-Coronal-Sagittal embedding Dataset Projects EVENTA Event-Enriched Image Analysis project enriches images with event-level understanding to reveal story beyond pixels CogCanvas A Benchmark for Evaluating Multi-Subject Reference-Based Image Generation ForgedCalamity Challenging synthetic disaster detection with cross-domain evaluation on unseen diffusion models. OpenForensics Large-scale dataset for multi-face forgery segmentation in-the-wild AAS Fine-grained aquatic animal species dataset with 46 distinct categories CAMO Pioneering work on camouflaged object segmentation CAMO++ Camouflaged instance segmentation in-the-wild VietFashion A new benchmark for sketch–text composed image retrieval centered on the Áo Dài, a traditional Vietnamese garment. GarmentSketch A novel dataset comprising over 26,275 fashion sketches across 21 garment categories, each paired with detailed textual descriptions. TMP-AoDai SketchANIMAR Fine-grained 3D animal model retrieval using hand-drawn sketch queries TextANIMAR Natural language-based fine-grained retrieval for 3D animal models VoFoCD Laryngeal image dataset for vocal fold classification and endoscopic analysis eKYC-DF Large-scale deepfake dataset for identity-proofing and liveness detection systems
