Computer Vision

VisionReward, a novel reward model, surpasses existing methods by precisely capturing multi-dimensional human preferences for image and video generation, enabling more accurate and stable model optimi…

Edicho: a novel training-free method for consistent image editing across diverse images, achieving precise consistency by leveraging explicit correspondence.

3to4D: Animate any 3D object with text prompts, preserving visual quality and achieving realistic motion!

VideoMaker achieves high-fidelity zero-shot customized video generation by cleverly harnessing the inherent power of video diffusion models, eliminating the need for extra feature extraction and injec…

PartGen generates compositional 3D objects with meaningful parts from text, images, or unstructured 3D data using multi-view diffusion models, enabling flexible 3D part editing.

Orient Anything: Learning robust object orientation estimation directly from rendered 3D models, achieving state-of-the-art accuracy on real images.

DiTCtrl achieves state-of-the-art multi-prompt video generation without retraining by cleverly controlling attention in a diffusion transformer, enabling smooth transitions between video segments.

DepthLab: a novel image-conditioned depth inpainting model enhances downstream 3D tasks by effectively completing partial depth information, showing superior performance and generalization.

SBS Figures creates a massive, high-quality figure QA dataset via a novel stage-by-stage synthesis pipeline, enabling efficient pre-training of visual language models.

Distilled Decoding (DD) drastically speeds up image generation from autoregressive models by using flow matching to enable one-step sampling, achieving significant speedups while maintaining acceptabl…

CLEAR: Conv-Like Linearization boosts pre-trained Diffusion Transformers, achieving 6.3x faster 8K image generation with minimal quality loss.

UIP2P: Unsupervised instruction-based image editing achieves high-fidelity edits by enforcing Cycle Edit Consistency, eliminating the need for ground-truth data.

Boosting autoregressive visual generation speed by 3.6-9.5x, this research introduces parallel processing while preserving model simplicity and generation quality.

LeviTor: Revolutionizing image-to-video synthesis with intuitive 3D trajectory control, generating realistic videos from static images by abstracting object masks into depth-aware control points.

DI-PCG uses a lightweight diffusion transformer to efficiently and accurately estimate parameters of procedural generators from images, enabling high-fidelity 3D asset creation.

Affordance-Aware Object Insertion uses a novel Mask-Aware Dual Diffusion model & SAM-FB dataset to realistically place objects in scenes, considering contextual relationships.

Prompting unlocks 4K metric depth from low-cost LiDAR.

FashionComposer revolutionizes fashion image creation through flexible composition of garments, faces, and poses.

AniDoc automates cartoon animation line art video colorization, making animation creation easier!

VidTok: an open-source, top performing video tokenizer.