Computer Vision

Feature4X: 4D Agentic AI from Monocular Video w/ Gaussian Feature Fields

DINeMo: Learns 3D models with no 3D annotations, leveraging pseudo-correspondence from visual foundation models for enhanced pose estimation.

BIZGEN: Article-level Visual Text Rendering for Infographics Generation

LongTextAR advances long-text image generation via a novel tokenizer, enabling accurate, controllable, and high-fidelity text rendering in images.

TokenHSI: Unified Transformer for Physical Human-Scene Interactions through Task Tokenization.

Opt-CWM: Self-supervised motion learning via counterfactual optimization, achieving state-of-the-art without labels!

Inference-time scaling for flow models enhances alignment with user preferences via stochastic generation and budget allocation.

Visually perfect generations aren’t always optimal! GenHancer finds that subtly imperfect generations can greatly improve vision-centric tasks.

Attention-IoU reveals model biases by analyzing attention maps, offering insights beyond dataset labels and improving debiasing techniques.

AccVideo accelerates video diffusion by 8.5x with a synthetic dataset and trajectory-based distillation, maintaining quality and enabling higher resolution video generation.

Video-T1 enhances video generation through test-time scaling, improving quality and consistency by viewing generation as a search for optimal video trajectories.

Bottleneck Sampling: Accelerate diffusion models without retraining by cleverly using low-resolution priors for efficient inference!

LSRNA: Super-resolution in latent space enhances image generation with diffusion models, achieving faster speeds and improved detail.

FRESA: fast feedforward 3D personalized avatar creation from few images.

FDConv: Adaptable convolution via frequency domain learning, enhancing performance without heavy parameter cost.

Aligning image generation subtasks: Equivariant modeling boosts efficiency and generalization by leveraging natural visual signal invariance.

Diffusion-4K: Synthesizing ultra-high-resolution images with a new benchmark dataset and wavelet-based fine-tuning that makes 4K image creation more detailed and accessible!

CFG-Zero*: A better Classifier-Free Guidance to improve the image quality and text alignment in Flow Matching models.

Hummingbird: An efficient text-to-video model that balances quality and computational efficiency via pruning and visual feedback learning.

AETHER: a unified framework enabling geometry-aware reasoning in world models, achieving zero-shot generalization from synthetic to real-world data.