Computer Vision

RelaCtrl: Relevance-guided control boosts diffusion transformer efficiency, cutting parameters by intelligently allocating resources.

Personalizing video models for dynamic concepts is now achievable with Set-and-Sequence: enabling high-fidelity generation, editing, and composition!

New geolocation dataset & reasoning framework enhance accuracy and interpretability by leveraging human gameplay data.

MagicArticulate automates 3D model animation preparation by generating skeletons and skinning weights, overcoming prior manual methods’ limitations, and introducing Articulation-XL, a large-scale benc…

AI models learn intuitive physics from self-supervised video pretraining.

Diffusion-Sharpening enhances diffusion model fine-tuning by optimizing sampling trajectories, achieving faster convergence and high inference efficiency without extra NFEs, leading to improved alignm…

Step-Video-T2V: A 30B parameter text-to-video model generating high-quality videos up to 204 frames, pushing the boundaries of video foundation models.

CAPI: a novel masked image modeling framework boosts self-supervised visual representation learning by predicting latent clusterings, achieving state-of-the-art ImageNet accuracy and mIoU.

VidCRAFT3 enables high-quality image-to-video generation with precise control over camera movement, object motion, and lighting, pushing the boundaries of visual content creation.

Next-Block Prediction (NBP) revolutionizes video generation by using a semi-autoregressive model that predicts blocks of video content simultaneously, resulting in significantly faster inference.

MRS: a novel, training-free sampler, drastically speeds up controllable image generation using Mean Reverting Diffusion, achieving 10-20x speedup across various tasks.

Magic141 generates one-minute video clips in under a minute by cleverly factorizing the generation task and employing optimization techniques.

Enhance-A-Video boosts video generation quality without retraining, by enhancing cross-frame correlations in diffusion transformers, resulting in improved coherence and visual fidelity.

TripoSG: High-fidelity 3D shapes synthesized via large-scale rectified flow models, pushing image-to-3D generation to new heights.

Lumina-Video: Efficient and flexible video generation using a multi-scale Next-DiT architecture with motion control.

EFFICIENT-VDIT accelerates video generation by 7.8x using sparse attention and multi-step distillation.

CustomVideoX: Zero-shot personalized video generation, exceeding existing methods in quality & consistency via 3D reference attention and dynamic adaptation.

Animate Anyone 2 creates high-fidelity character animations by incorporating environmental context, resulting in seamless character-environment integration and more realistic object interactions.

Dual Caption Preference Optimization (DCPO) significantly boosts diffusion model image quality by using paired captions to resolve data distribution conflicts and irrelevant prompt issues.

3CAD: A new large-scale, real-world dataset with diverse 3C product anomalies boosts unsupervised anomaly detection, enabling superior algorithm development via a novel Coarse-to-Fine framework.