Computer Vision

Concat-ID: A universal, scalable framework for identity-preserving video synthesis, balancing consistency and editability.

WideRange4D: A new benchmark & reconstruction method for high-quality 4D scenes with wide-range movements, pushing the boundaries of 4D reconstruction.

KDTalker: Accurate & efficient audio-driven talking portrait via implicit keypoint-based spatiotemporal diffusion, unlocking diverse & realistic animations.

Rewards Are Enough!

MM-Spatial enhances multimodal LLMs with 3D spatial reasoning via a novel dataset and benchmark, improving performance on spatial understanding tasks.

Infinite Mobility: Procedural generation of high-fidelity articulated objects for scalable embodied AI training.

Edit Transfer: Learns image edits from a single example and applies it to new images, surpassing text/reference-based methods!

DreamRenderer: Taming attribute control in large-scale text-to-image models with a plug-and-play, training-free approach for enhanced content creation.

BlobCtrl: Precisely edit images at the element level with a unified, flexible framework, bridging the gap between generation and editing.

MagicID: ID-consistent & dynamic-preserved video customization via hybrid preference optimization.

Reflect-DiT: Scaling Text-to-Image Diffusion Transformers via In-Context Reflection!

VGGT: a fast, end-to-end transformer that infers complete 3D scene attributes from multiple views, outperforming optimization-based methods.

Unified Copernicus Foundation Model for Earth Vision: A multimodal approach to improve scalability, versatility, and adaptability of EO models.

ReCamMaster: Re-shoots videos via generative rendering, controlling camera movement from a single source, for novel perspectives and enhanced video creation.

MTV-Inpaint: A unified framework for multi-task long video inpainting, enabling versatile object insertion, scene completion, editing, and removal.

LCT: Fine-tunes single-shot video diffusion models for coherent multi-shot video generation without extra parameters!

LHM: Animatable 3D avatars from a single image in seconds.

GoT: Reasoning guides vivid image generation and editing!

ETCH: Equivariantly fitting bodies to clothed humans through tightness for better pose and shape accuracy.

Distilling diffusion models?💡 This paper shows you how to retain base model diversity while keeping the distilled model’s speed!