Computer Vision

Neural Gaffer: Relighting any object via diffusion using a single image and an environment map to produce high-quality, realistic relit images.

Boosting implicit neural representations, Neural Experts uses a Mixture of Experts architecture to achieve faster, more accurate, and memory-efficient signal reconstruction across various tasks.

This study introduces a neural cover selection framework for image steganography, optimizing latent spaces in generative models to improve message recovery and image quality.

The Neural Concept Binder (NCB) framework learns expressive, inspectable, and revisable visual concepts unsupervised, integrating both continuous and discrete representations for seamless use in neura…

NeuMA: a novel neural material adaptor corrects existing physical models, accurately learning complex dynamics from visual observations.

NaRCan: High-quality video editing via diffusion priors and hybrid deformation fields.

MVSplat360: Generating stunning 360° views from just a few images!

MVSDet uses efficient plane sweeps for accurate indoor 3D object detection from multiple images, significantly outperforming previous NeRF-based methods.

MVInpainter: Pose-free multi-view consistent inpainting bridges 2D and 3D editing by simplifying 3D editing to a multi-view 2D inpainting task.

MVGamba: A unified, feed-forward 3D content generation model achieving state-of-the-art quality and speed using an RNN-like state space model for efficient multi-view Gaussian reconstruction.

MV2Cyl: A novel method reconstructs 3D extrusion cylinder CAD models directly from multi-view images, surpassing accuracy of methods using raw 3D geometry.

AI models struggle to understand 3D space like humans do. This paper introduces Multiview Scene Graphs (MSGs) – a new topological scene representation using interconnected place and object nodes buil…

New method distills slow diffusion models into fast, few-step models by matching data expectations, achieving state-of-the-art results on ImageNet.

MultiPull: a novel method reconstructing detailed 3D surfaces from raw point clouds using multi-step optimization of multi-level features, significantly improving accuracy and detail.

Multi-view Masked Contrastive Representation Learning (M²CRL) significantly boosts endoscopic video analysis by using a novel multi-view masking strategy and contrastive learning, achieving state-of-t…

Ref-MC2 reconstructs high-fidelity 3D objects with inter-reflections by using a novel multi-times Monte Carlo sampling strategy, achieving superior performance in accuracy and efficiency.

MSVMamba: A novel multi-scale vision model leveraging state-space models, achieves high accuracy in image classification and object detection while maintaining linear complexity, solving the long-rang…

Hierarchical Sinkhorn Tree (HST) robustly retrieves accurate 3D point cloud correspondences using multi-scale consistency, outperforming state-of-the-art methods.

MHCDIFF: a novel pipeline using multi-hypotheses conditioned point cloud diffusion for accurate 3D human reconstruction from occluded images, outperforming state-of-the-art methods.

MTGS: a unified framework jointly predicts gaze and social gaze (shared attention, mutual gaze) for multiple people in videos, achieving state-of-the-art results using a temporal transformer model and…