Computer Vision

Concept-Incremental Flexible Customization (CIFC) model tackles catastrophic forgetting and concept neglect in continually adapting text-to-image diffusion models, enabling flexible personalization.

Diffusion models surprisingly learn factorized representations, enabling compositional generalization, but struggle with interpolation; training with independent factors drastically improves data effi…

HOPE: a novel shape matching method achieving both accuracy and smoothness by aligning different k-hop neighborhoods and refining maps via local map distortion.

Hollowed Net efficiently personalizes text-to-image diffusion models on-device by temporarily removing deep U-Net layers during training, drastically reducing memory usage without sacrificing performa…

HOI-Swap: a novel diffusion model flawlessly swaps objects in videos while intelligently preserving natural hand interactions, producing high-quality edits.

HisTPT: Historical Test-Time Prompt Tuning memorizes past learning, enabling robust online prompt adaptation for vision models, overcoming performance degradation in continuously changing data streams…

AICT: Adaptive-Interval Color Transformation harmonizes high-resolution images by predicting pixel-wise color changes, adaptively adjusting sampling intervals to capture local variations, and using a …

Visualizing high-dimensional posterior distributions is challenging. This paper introduces ‘Posterior Trees,’ a novel method using tree-structured neural network predictions for hierarchical uncertai…

Hierarchical Selective Classification (HSC) improves deep learning model reliability for risk-sensitive tasks by leveraging hierarchical class relationships to provide more informative predictions eve…

HiCoM, a novel framework, achieves high-fidelity streamable dynamic scene reconstruction by using a hierarchical coherent motion mechanism and parallel processing to significantly reduce training time…

HiCo: Hierarchical Controllable Diffusion Model achieves superior layout-to-image generation by disentangling spatial layouts through a multi-branch network structure, resulting in high-quality images…

HDR-GS: 1000x faster HDR novel view synthesis via Gaussian splatting!

Boost self-supervised visual learning: This paper introduces theoretical insights and practical recommendations to significantly improve SSL’s efficiency and reduce data needs.

DiMoP3D: Predicting diverse, physically realistic human motions in 3D scenes by harmonizing stochasticity and determinism.

Happy: a novel debiased learning framework, excels at continually discovering new categories from unlabeled data while retaining knowledge of previously learned ones, overcoming existing bias issues a…

Hamba: a novel graph-guided framework for single-view 3D hand reconstruction, significantly outperforms existing methods by efficiently modeling spatial relationships between joints using a fraction o…

Hallo3D: a tuning-free method resolving 3D generation hallucinations via multi-modal inconsistency detection and mitigation for consistent 3D content.

HairFastGAN achieves realistic and robust hairstyle transfer in near real-time using a novel encoder-based approach, significantly outperforming optimization-based methods.

HairDiffusion uses latent diffusion models and a multi-stage blending technique to achieve vivid, multi-colored hair editing in images, preserving other facial features.

GVKF: A novel method achieves highly efficient and accurate 3D surface reconstruction in open scenes by integrating fast 3D Gaussian splatting with continuous scene representation using kernel regres…