Related papers: Mask Guided Gated Convolution for Amodal Content C…

Image inpainting has made significant advances in recent years. However, it is still challenging to recover corrupted images with both vivid textures and reasonable structures. Some specific methods only tackle regular textures while losing…

We present a new meshing algorithm called guided and augmented meshing, GAMesh, which uses a mesh prior to generate a surface for the output points of a point network. By projecting the output points onto this prior and simplifying the…

Recent approaches to jointly reconstruct 3D humans and objects from a single RGB image represent 3D shapes with template-based or coarse models, which fail to capture details of loose clothing on human bodies. In this paper, we introduce a…

Compositing an object into an image involves multiple non-trivial sub-tasks such as object placement and scaling, color/lighting harmonization, viewpoint/geometry adjustment, and shadow/reflection generation. Recent generative image…

Multimodal abstractive summarization (MAS) models that summarize videos (vision modality) and their corresponding transcripts (text modality) are able to extract the essential information from massive multimodal data on the Internet.…

In recent decades, 3D morphable model (3DMM) has been commonly used in image-based photorealistic 3D face reconstruction. However, face images are often corrupted by serious occlusion by non-face objects including eyeglasses, masks, and…

Masked image modeling (MIM) as pre-training is shown to be effective for numerous vision downstream tasks, but how and where MIM works remain unclear. In this paper, we compare MIM with the long-dominant supervised pre-trained models from…

We propose a text-guided variational image generation method to address the challenge of getting clean data for anomaly detection in industrial manufacturing. Our method utilizes text information about the target object, learned from…

Semi-supervised learning is a challenging problem which aims to construct a model by learning from a limited number of labeled examples. Numerous methods have been proposed to tackle this problem, with most focusing on utilizing the…

Camouflaged object detection (COD) aims to segment camouflaged objects which exhibit very similar patterns with the surrounding environment. Recent research works have shown that enhancing the feature representation via the frequency…

We consider inpainting in an unsupervised setting where there is neither access to paired nor unpaired training data. The only available information is provided by the uncomplete observations and the inpainting process statistics. In this…

The ability to predict future visual observations conditioned on past observations and motor commands can enable embodied agents to plan solutions to a variety of tasks in complex environments. This work shows that we can create good video…

Masked autoencoder has been widely explored in point cloud self-supervised learning, whereby the point cloud is generally divided into visible and masked parts. These methods typically include an encoder accepting visible patches…

With the remarkable recent progress on learning deep generative models, it becomes increasingly interesting to develop models for controllable image synthesis from reconfigurable inputs. This paper focuses on a recent emerged task,…

Camouflaged Object Detection (COD) demands models to expeditiously and accurately distinguish objects which conceal themselves seamlessly in the environment. Owing to the subtle differences and ambiguous boundaries, COD is not only a…

We present a method to populate an unknown environment with models of previously seen objects, placed in a Euclidean reference frame that is inferred causally and on-line using monocular video along with inertial sensors. The system we…

Manipulating articulated objects with robotic arms is challenging due to the complex kinematic structure, which requires precise part segmentation for efficient manipulation. In this work, we introduce a novel superpoint-based perception…

In this work, we present an end-to-end network for stereo-consistent image inpainting with the objective of inpainting large missing regions behind objects. The proposed model consists of an edge-guided UNet-like network using Partial…

We propose a new algorithm to learn a one-hidden-layer convolutional neural network where both the convolutional weights and the outputs weights are parameters to be learned. Our algorithm works for a general class of (potentially…

Due to the optical properties, transparent objects often lead depth cameras to generate incomplete or invalid depth data, which in turn reduces the accuracy and reliability of robotic grasping. Existing approaches typically input the RGB-D…