Computer Vision

Boosting video temporal grounding, NumPro empowers Vid-LLMs by adding frame numbers, making temporal localization as easy as flipping through manga.

MagicQuill: an intelligent interactive image editing system enabling intuitive, precise image edits via brushstrokes and real-time intent prediction by a multimodal LLM.

Sharingan extracts user action sequences from desktop recordings using novel VLM-based methods, achieving 70-80% accuracy and enabling RPA.

EgoVid-5M: First high-quality dataset for egocentric video generation, enabling realistic human-centric world simulations.

WaLa: a billion-parameter 3D generative model using wavelet encodings achieves state-of-the-art results, generating high-quality 3D shapes in seconds.

GaussianAnything: Interactive point cloud latent diffusion enables high-quality, editable 3D models from images or text, overcoming existing 3D generation limitations.

SAMPart3D: Zero-shot 3D part segmentation across granularities, scaling to large datasets & handling part ambiguity.

OmniEdit, a novel instruction-based image editing model, surpasses existing methods by leveraging specialist supervision and high-quality data, achieving superior performance across diverse editing ta…

Edify Image: groundbreaking pixel-perfect photorealistic image generation using cascaded pixel-space diffusion models with a novel Laplacian diffusion process, enabling diverse applications including …

Add-it: Training-free object insertion in images using pretrained diffusion models by cleverly balancing information from the scene, text prompt, and generated image, achieving state-of-the-art result…

KMM: Key Frame Mask Mamba generates extended, diverse human motion from text prompts by innovatively masking key frames in the Mamba architecture and using contrastive learning for improved text-motio…

StdGEN: Generate high-quality, semantically decomposed 3D characters from a single image in minutes, enabling flexible customization for various applications.

SVDQuant boosts 4-bit diffusion models by absorbing outliers via low-rank components, achieving 3.5x memory reduction and 3x speedup on 12B parameter models.

SG-I2V: Zero-shot controllable image-to-video generation using a self-guided approach that leverages pre-trained models for precise object and camera motion control.

ReCapture generates videos with novel camera angles from user videos using masked video fine-tuning, preserving scene motion and plausibly hallucinating unseen parts.

GazeGen uses real-time gaze tracking to enable intuitive hands-free visual content creation and editing, setting a new standard for accessible AR/VR interaction.

DimensionX generates photorealistic 3D and 4D scenes from a single image via controllable video diffusion, enabling precise manipulation of spatial structure and temporal dynamics.

GarVerseLOD introduces a novel dataset and framework for high-fidelity 3D garment reconstruction from a single image, achieving unprecedented robustness via a hierarchical approach and leveraging a ma…

Visual saliency boosts object detection accuracy more than depth estimation, especially for larger objects, offering valuable insights for model and dataset improvement.

Training-free Regional Prompting for FLUX boosts compositional text-to-image generation by cleverly manipulating attention mechanisms, achieving fine-grained control without retraining.