Computer Vision

Move-in-2D generates realistic human motion sequences conditioned on a 2D scene image and text prompt, overcoming limitations of existing approaches and improving video synthesis.

Edit many objects at once in videos! MIVE does it accurately without affecting other areas, a big step for AI video editing.

ChatDiT enables zero-shot, multi-turn image generation using pretrained diffusion transformers and a novel multi-agent framework.

Generate wide-scope 3D scenes from single images in a snap!

Create realistic 3D heads with specific hairstyles from text, no 3D hair data needed!

Leveraging video models, researchers achieve state-of-the-art 3D super-resolution by generating ‘video-like’ sequences from unordered images, eliminating artifacts and computational demands.

MOVIS enhances 3D scene generation by improving cross-view consistency in multi-object novel view synthesis.

IDArb: A diffusion model for decomposing images into intrinsic components like albedo, normal, and material properties, handling varying views and lighting.

ColorFlow, a new AI model, accurately colorizes black-and-white image sequences while preserving character identity.

Training-free method adds physical properties to 3D models using vision-language models.

New attack fools breast ultrasound AI using subtle text prompts.

BrushEdit revolutionizes interactive image editing with instructions & inpainting.

Neural LightRig uses multi-light diffusion to accurately estimate object normals and materials from a single image, outperforming existing methods.

LoRACLR merges multiple LoRA models for high-fidelity multi-concept image generation, using a contrastive objective to ensure concept distinctiveness and prevent interference.

WaLLOC: a novel neural codec boosts compressed-domain learning by combining wavelet transforms with asymmetric autoencoders, achieving high compression ratios with minimal computation and uniform dime…

InstanceCap improves text-to-video generation through detailed, instance-aware captions.

Gaze-LLE achieves state-of-the-art gaze estimation by using a frozen DINOv2 encoder and a lightweight decoder, simplifying architecture and improving efficiency.

FreeSplatter: a novel feed-forward framework reconstructs high-quality 3D scenes from uncalibrated sparse-view images, estimating camera poses in seconds.

FreeScale generates stunning 8K images and high-fidelity videos without retraining.

Edit images precisely with AI, no masks needed!