Related papers: IRISformer: Dense Vision Transformers for Single-I…
The computer vision community has developed numerous techniques for digitally restoring true scene information from single-view degraded photographs, an important yet extremely ill-posed task. In this work, we tackle image restoration from…
We present Reversible Vision Transformers, a memory efficient architecture design for visual recognition. By decoupling the GPU memory requirement from the depth of the model, Reversible Vision Transformers enable scaling up architectures…
Indoor scene recognition is a multi-faceted and challenging problem due to the diverse intra-class variations and the confusing inter-class similarities. This paper presents a novel approach which exploits rich mid-level convolutional…
Dense scene reconstruction for photo-realistic view synthesis has various applications, such as VR/AR, autonomous vehicles. However, most existing methods have difficulties in large-scale scenes due to three core challenges: \textit{(a)…
Existing inverse rendering combined with neural rendering methods can only perform editable novel view synthesis on object-specific scenes, while we present intrinsic neural radiance fields, dubbed IntrinsicNeRF, which introduce intrinsic…
Given a single photo of a room and a large database of furniture CAD models, our goal is to reconstruct a scene that is as similar as possible to the scene depicted in the photograph, and composed of objects drawn from the database. We…
Differentiable volumetric rendering is a powerful paradigm for 3D reconstruction and novel view synthesis. However, standard volume rendering approaches struggle with degenerate geometries in the case of limited viewpoint diversity, a…
We propose DepR, a depth-guided single-view scene reconstruction framework that integrates instance-level diffusion within a compositional paradigm. Instead of reconstructing the entire scene holistically, DepR generates individual objects…
Image rescaling is a commonly used bidirectional operation, which first downscales high-resolution images to fit various display screens or to be storage- and bandwidth-friendly, and afterward upscales the corresponding low-resolution…
Recent Transformer-based low-light enhancement methods have made promising progress in recovering global illumination. However, they still struggle with non-uniform lighting scenarios, such as backlit and shadow, appearing as over-exposure…
Accurate modelling of object deformations is crucial for a wide range of robotic manipulation tasks, where interacting with soft or deformable objects is essential. Current methods struggle to generalise to unseen forces or adapt to new…
Scene and object reconstruction is an important problem in robotics, in particular in planning collision-free trajectories or in object manipulation. This paper compares two strategies for the reconstruction of nonvisible parts of the…
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…
The goal of inverse rendering is to decompose geometry, lights, and materials given pose multi-view images. To achieve this goal, we propose neural direct and joint inverse rendering, NDJIR. Different from prior works which relies on some…
Image restoration in adverse weather conditions is a difficult task in computer vision. In this paper, we propose a novel transformer-based framework called GridFormer which serves as a backbone for image restoration under adverse weather…
Reconstructing coherent 3D geometry and appearance from unposed multi-view images is a fundamental yet challenging problem in computer vision. Most existing visual geometry foundation models predict explicit geometry by regressing…
The reconstruction of indoor scenes from multi-view RGB images is challenging due to the coexistence of flat and texture-less regions alongside delicate and fine-grained regions. Recent methods leverage neural radiance fields aided by…
Given the broad application of infrared technology across diverse fields, there is an increasing emphasis on investigating super-resolution techniques for infrared images within the realm of deep learning. Despite the impressive results of…
Recent neural rendering methods have demonstrated accurate view interpolation by predicting volumetric density and color with a neural network. Although such volumetric representations can be supervised on static and dynamic scenes,…
We present a method that tackles the challenge of predicting color and depth behind the visible content of an image. Our approach aims at building up a Layered Depth Image (LDI) from a single RGB input, which is an efficient representation…