LocalMamba: Visual State Space Model with Windowed Selective Scan
Paper • 2403.09338 • Published • 8
cv
-
-
GiT: Towards Generalist Vision Transformer through Universal Language Interface
Paper • 2403.09394 • Published • 26 -
Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers
Paper • 2402.19479 • Published • 35 -
Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection
Paper • 2405.10300 • Published • 30 -
EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model
Paper • 2406.20076 • Published • 10 -
SVGCraft: Beyond Single Object Text-to-SVG Synthesis with Comprehensive Canvas Layout
Paper • 2404.00412 • Published • 2 -
LKCell: Efficient Cell Nuclei Instance Segmentation with Large Convolution Kernels
Paper • 2407.18054 • Published • 12 -
Matting by Generation
Paper • 2407.21017 • Published • 24 -
SAM 2: Segment Anything in Images and Videos
Paper • 2408.00714 • Published • 122 -
NeuFlow v2: High-Efficiency Optical Flow Estimation on Edge Devices
Paper • 2408.10161 • Published • 15 -
Sapiens: Foundation for Human Vision Models
Paper • 2408.12569 • Published • 94 -
DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos
Paper • 2409.02095 • Published • 37 -
General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
Paper • 2409.01704 • Published • 83 -
Mamba-YOLO-World: Marrying YOLO-World with Mamba for Open-Vocabulary Detection
Paper • 2409.08513 • Published • 14 -
OmniGen: Unified Image Generation
Paper • 2409.11340 • Published • 115 -
Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think
Paper • 2409.11355 • Published • 30 -
Degradation-Guided One-Step Image Super-Resolution with Diffusion Priors
Paper • 2409.17058 • Published • 13 -
Self-Supervised Any-Point Tracking by Contrastive Random Walks
Paper • 2409.16288 • Published • 6 -
Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction
Paper • 2409.18124 • Published • 33 -
MinerU: An Open-Source Solution for Precise Document Content Extraction
Paper • 2409.18839 • Published • 41 -
Depth Pro: Sharp Monocular Metric Depth in Less Than a Second
Paper • 2410.02073 • Published • 43 -
Towards Natural Image Matting in the Wild via Real-Scenario Prior
Paper • 2410.06593 • Published • 4 -
SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree
Paper • 2410.16268 • Published • 70 -
SMITE: Segment Me In TimE
Paper • 2410.18538 • Published • 16 -
GrounDiT: Grounding Diffusion Transformers via Noisy Patch Transplantation
Paper • 2410.20474 • Published • 14 -
DELTA: Dense Efficient Long-range 3D Tracking for any video
Paper • 2410.24211 • Published • 9 -
Face Anonymization Made Simple
Paper • 2411.00762 • Published • 9 -
ITACLIP: Boosting Training-Free Semantic Segmentation with Image, Text, and Architectural Enhancements
Paper • 2411.12044 • Published • 14 -
SEAGULL: No-reference Image Quality Assessment for Regions of Interest via Vision-Language Instruction Tuning
Paper • 2411.10161 • Published • 9 -
SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory
Paper • 2411.11922 • Published • 19 -
DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding
Paper • 2411.14347 • Published • 16 -
Knowledge Transfer Across Modalities with Natural Language Supervision
Paper • 2411.15611 • Published • 16 -
Edge Weight Prediction For Category-Agnostic Pose Estimation
Paper • 2411.16665 • Published • 6 -
EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Duality
Paper • 2411.15241 • Published • 7 -
Scaling Image Tokenizers with Grouped Spherical Quantization
Paper • 2412.02632 • Published • 10 -
EMOv2: Pushing 5M Vision Model Frontier
Paper • 2412.06674 • Published • 13 -
Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks
Paper • 2501.08326 • Published • 34 -
iFormer: Integrating ConvNet and Transformer for Mobile Application
Paper • 2501.15369 • Published • 13 -
MatAnyone: Stable Video Matting with Consistent Memory Propagation
Paper • 2501.14677 • Published • 34 -
PixelWorld: Towards Perceiving Everything as Pixels
Paper • 2501.19339 • Published • 17 -
SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders
Paper • 2501.18052 • Published • 8 -
GroundingSuite: Measuring Complex Multi-Granular Pixel Grounding
Paper • 2503.10596 • Published • 18 -
SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion
Paper • 2503.11576 • Published • 156 -
Semantic Library Adaptation: LoRA Retrieval and Fusion for Open-Vocabulary Semantic Segmentation
Paper • 2503.21780 • Published • 9 -
TAPNext: Tracking Any Point (TAP) as Next Token Prediction
Paper • 2504.05579 • Published • 5 -
DC-SAM: In-Context Segment Anything in Images and Videos via Dual Consistency
Paper • 2504.12080 • Published • 8 -
Group Downsampling with Equivariant Anti-aliasing
Paper • 2504.17258 • Published • 9 -
Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysis
Paper • 2505.09358 • Published • 27 -
PictSure: Pretraining Embeddings Matters for In-Context Learning Image Classifiers
Paper • 2506.14842 • Published • 7 -
Adapting Vehicle Detectors for Aerial Imagery to Unseen Domains with Weak Supervision
Paper • 2507.20976 • Published • 11 -
IAUNet: Instance-Aware U-Net
Paper • 2508.01928 • Published • 9 -
A Coarse-to-Fine Approach to Multi-Modality 3D Occupancy Grounding
Paper • 2508.01197 • Published • 5 -
DINOv3
Paper • 2508.10104 • Published • 303 -
UniPixel: Unified Object Referring and Segmentation for Pixel-Level Visual Reasoning
Paper • 2509.18094 • Published • 4 -
SAM 3: Segment Anything with Concepts
Paper • 2511.16719 • Published • 134