Related papers: TORE: Token Reduction for Efficient Human Mesh Rec…

Event cameras are an exciting, new sensor modality enabling high-speed imaging with extremely low-latency and wide dynamic range. Unfortunately, most machine learning architectures are not designed to directly handle sparse data, like that…

Monocular 4D human-object interaction (HOI) reconstruction - recovering a moving human and a manipulated object from a single RGB video - remains challenging due to depth ambiguity and frequent occlusions. Existing methods often rely on…

Transformers have revolutionized medical image restoration, but the quadratic complexity still poses limitations for their application to high-resolution medical images. The recent advent of the Receptance Weighted Key Value (RWKV) model in…

Existing auto-regressive mesh generation approaches suffer from ineffective topology preservation, which is crucial for practical applications. This limitation stems from previous mesh tokenization methods treating meshes as simple…

We present a new pipeline for acquiring a textured mesh in the wild with a single smartphone which offers access to images, depth maps, and valid poses. Our method first introduces an RGBD-aided structure from motion, which can yield…

Recent developments in Transformers have achieved notable strides in enhancing video comprehension. Nonetheless, the O($N^2$) computation complexity associated with attention mechanisms presents substantial computational hurdles when…

Since the introduction of the Vision Transformer (ViT), researchers have sought to make ViTs more efficient by removing redundant information in the processed tokens. While different methods have been explored to achieve this goal, we still…

We propose SelfRecon, a clothed human body reconstruction method that combines implicit and explicit representations to recover space-time coherent geometries from a monocular self-rotating human video. Explicit methods require a predefined…

Most prior works in perceiving 3D humans from images reason human in isolation without their surroundings. However, humans are constantly interacting with the surrounding objects, thus calling for models that can reason about not only the…

In the field of medical images, although various works find Swin Transformer has promising effectiveness on pixelwise dense prediction, whether pre-training these models without using extra dataset can further boost the performance for the…

Autoregressive (AR) models, long dominant in language generation, are increasingly applied to image synthesis but are often considered less competitive than Diffusion-based models. A primary limitation is the substantial number of image…

3D hand pose estimation has found broad application in areas such as gesture recognition and human-machine interaction tasks. As performance improves, the complexity of the systems also increases, which can limit the comparative analysis…

Transformers have recently been shown to generate high quality images from text input. However, the existing method of pose conditioning using skeleton image tokens is computationally inefficient and generate low quality images. Therefore…

Human pose estimation has seen widespread use of transformer models in recent years. Pose transformers benefit from the self-attention map, which captures the correlation between human joint tokens and the image. However, training such…

The landscape of image generation has been forever changed by open vocabulary diffusion models. However, at their core these models use transformers, which makes generation slow. Better implementations to increase the throughput of these…

We introduce Token Merging (ToMe), a simple method to increase the throughput of existing ViT models without needing to train. ToMe gradually combines similar tokens in a transformer using a general and light-weight matching algorithm that…

Transformers have emerged as the state-of-the-art architecture in medical image registration, outperforming convolutional neural networks (CNNs) by addressing their limited receptive fields and overcoming gradient instability in deeper…

Recently, Transformer-based image restoration networks have achieved promising improvements over convolutional neural networks due to parameter-independent global interactions. To lower computational cost, existing works generally limit…

3D hand pose estimation and shape recovery are challenging tasks in computer vision. We introduce a novel framework HandTailor, which combines a learning-based hand module and an optimization-based tailor module to achieve high-precision…

In Transformer architectures, tokens\textemdash discrete units derived from raw data\textemdash are formed by segmenting inputs into fixed-length chunks. Each token is then mapped to an embedding, enabling parallel attention computations…