Computer Vision

Low-Rank Feature Learning (LRFL) significantly boosts thorax disease classification accuracy by reducing noise and background interference in medical images.

Create animatable interacting hand avatars from a single image using a novel two-stage interaction-aware 3D Gaussian splatting framework!

PaDIS: Patch-based diffusion inverse solver learns efficient image priors from image patches, enabling high-resolution inverse problem solutions with reduced computational costs and data needs.

This paper proposes a novel method to model group actions within autoencoders by learning these actions in the latent space, enhancing model versatility and improving performance in various real-world…

Self-Supervised Controllable Generation (SCG) framework achieves brain-like associative generation by using a modular autoencoder with equivariance constraints and a self-supervised pattern completion…

LOFF-TA leverages offline foundation model features and tensor augmentations for efficient, resource-light training, achieving up to 37x faster training and 26x less GPU memory usage.

FADA: a novel frequency-adapted learning scheme boosts domain-generalized semantic segmentation by decoupling style and content using Haar wavelets, achieving state-of-the-art results.

DisPA: a novel disentangled representation learning framework for perceptual point cloud quality assessment achieves superior performance by minimizing mutual information between content and distortio…

DebLoRA: A novel unsupervised learning approach debiases LoRA for remote sensing imagery, boosting minor class performance without sacrificing major class accuracy.

Progressive Contrastive Learning with Hard & Dynamic Prototypes (PCLHD) revolutionizes unsupervised visible-infrared person re-identification by effectively capturing data commonality, divergence, and…

Learned Bregman divergences significantly improve image corruption robustness in adversarial training.

Animates diverse garments realistically from a single cloth’s trajectory using a disentangled learning approach and Energy Unit Network (EUNet).

3D surface reconstruction revolutionized: PEIF leverages patch-level pose-invariant representations and 3D patch-level equivariance for state-of-the-art accuracy, even with varied poses and datasets!

LCM: a novel, locally constrained, compact point cloud model surpasses Transformer-based methods by significantly improving performance and efficiency in various downstream tasks.

AI now draws almost as well as humans, thanks to novel latent diffusion model regularizations that mimic human cognitive biases.

Large Spatial Model (LSM) achieves real-time semantic 3D reconstruction from just two unposed images, unifying multiple 3D vision tasks in a single feed-forward pass.

LAM3D: A novel framework uses point cloud data to boost single-image 3D mesh reconstruction accuracy, achieving state-of-the-art results in just 6 seconds.

L4GM: The first 4D model generating high-quality animated 3D objects from single-view videos in a single feed-forward pass.

L-TTA: A lightweight test-time adaptation method using a versatile stem layer minimizes channel-wise uncertainty for rapid and memory-efficient adaptation to new domains.

KOALA: New efficient text-to-image diffusion models achieving 4x speed and 69% size reduction of SDXL, generating 1024px images on consumer GPUs with 8GB VRAM.