Related papers: Sapiens2

Earth observation offers new insight into anthropogenic changes to nature, and how these changes are effecting (and are effected by) the built environment and the real economy. With the global availability of medium-resolution (10-30m)…

Image-to-image translation has recently achieved remarkable results. But despite current success, it suffers from inferior performance when translations between classes require large shape changes. We attribute this to the high-resolution…

Due to the current lack of large-scale datasets at the million-scale level, tasks involving panoramic images predominantly rely on existing two-dimensional pre-trained image benchmark models as backbone networks. However, these networks are…

Data size is the bottleneck for developing deep saliency models, because collecting eye-movement data is very time consuming and expensive. Most of current studies on human attention and saliency modeling have used high quality stereotype…

This report introduces the Qwen2 series, the latest addition to our large language models and large multimodal models. We release a comprehensive suite of foundational and instruction-tuned language models, encompassing a parameter range…

The vision community is witnessing a modeling shift from CNNs to Transformers, where pure Transformer architectures have attained top accuracy on the major video recognition benchmarks. These video models are all built on Transformer layers…

Realistic human-centric rendering plays a key role in both computer vision and computer graphics. Rapid progress has been made in the algorithm aspect over the years, yet existing human-centric rendering datasets and benchmarks are rather…

The Sentinel-2 mission provides multispectral imagery with 13 bands at resolutions of 10m, 20m, and 60m. In particular, the 10m bands offer fine structural detail, while the 20m bands capture richer spectral information. In this paper, we…

Statistical shape modeling is the computational process of discovering significant shape parameters from segmented anatomies captured by medical images (such as MRI and CT scans), which can fully describe subject-specific anatomy in the…

We present a new self-supervised pre-training of Vision Transformers for dense prediction tasks. It is based on a contrastive loss across views that compares pixel-level representations to global image representations. This strategy…

High-quality saliency maps are essential in several machine learning application areas including explainable AI and weakly supervised object detection and segmentation. Many techniques have been developed to generate better saliency using…

Training general-purpose vision models on purely sequential visual data, eschewing linguistic inputs, has heralded a new frontier in visual understanding. These models are intended to not only comprehend but also seamlessly transit to…

Human-centric perceptions include a variety of vision tasks, which have widespread industrial applications, including surveillance, autonomous driving, and the metaverse. It is desirable to have a general pretrain model for versatile…

Deep learning has significantly advanced medical imaging analysis, yet variations in image resolution remain an overlooked challenge. Most methods address this by resampling images, leading to either information loss or computational…

Vision Transformers (ViTs) have achieved overwhelming success, yet they suffer from vulnerable resolution scalability, i.e., the performance drops drastically when presented with input resolutions that are unseen during training. We…

Understanding and predicting the human visual attentional mechanism is an active area of research in the fields of neuroscience and computer vision. In this work, we propose DeepFix, a first-of-its-kind fully convolutional neural network…

This work presents a new fine-grained transparent object segmentation dataset, termed Trans10K-v2, extending Trans10K-v1, the first large-scale transparent object segmentation dataset. Unlike Trans10K-v1 that only has two limited…

Segment Anything Model 2 (SAM2) shows excellent performance in video object segmentation tasks; however, the heavy computational burden hinders its application in real-time video processing. Although there have been efforts to improve the…

Transformers are widely used deep learning architectures. Existing transformers are mostly designed for sequences (texts or time series), images or videos, and graphs. This paper proposes a novel transformer model for massive (up to a…

Quality assessment and aesthetics assessment aim to evaluate the perceived quality and aesthetics of visual content. Current learning-based methods suffer greatly from the scarcity of labeled data and usually perform sub-optimally in terms…