Related papers: Fast-MVSNet: Sparse-to-Dense Multi-View Stereo Wit…
Accuracy and processing speed are two important factors that affect the use of video object segmentation (VOS) in real applications. With the advanced techniques of deep neural networks, the accuracy has been significantly improved,…
We present a novel, practical approach to speed up sparse matrix-vector multiplication (SpMVM) on GPUs. The novel key idea is to apply lossless entropy coding to further compress the sparse matrix when stored in one of the commonly…
Novel View Synthesis (NVS) from sparse views presents a formidable challenge in 3D reconstruction, where limited multi-view constraints lead to severe overfitting, geometric distortion, and fragmented scenes. While 3D Gaussian Splatting…
Symbol detection for Massive Multiple-Input Multiple-Output (MIMO) is a challenging problem for which traditional algorithms are either impractical or suffer from performance limitations. Several recently proposed learning-based approaches…
Maps of brain microarchitecture are important for understanding neurological function and behavior, including alterations caused by chronic conditions such as neurodegenerative disease. Techniques such as knife-edge scanning microscopy…
Generalizable neural surface reconstruction has become a compelling technique to reconstruct from few images without per-scene optimization, where dense 3D feature volume has proven effective as a global representation of scenes. However,…
In this paper we present ActiveStereoNet, the first deep learning solution for active stereo systems. Due to the lack of ground truth, our method is fully self-supervised, yet it produces precise depth with a subpixel precision of $1/30th$…
Multi-view photometric stereo (MVPS) is a preferred method for detailed and precise 3D acquisition of an object from images. Although popular methods for MVPS can provide outstanding results, they are often complex to execute and limited to…
Computing accurate depth from multiple views is a fundamental and longstanding challenge in computer vision. However, most existing approaches do not generalize well across different domains and scene types (e.g. indoor vs. outdoor).…
In this paper, we present TANDEM a real-time monocular tracking and dense mapping framework. For pose estimation, TANDEM performs photometric bundle adjustment based on a sliding window of keyframes. To increase the robustness, we propose a…
The limited and dynamically varied resources on edge devices motivate us to deploy an optimized deep neural network that can adapt its sub-networks to fit in different resource constraints. However, existing works often build sub-networks…
We propose an accurate and lightweight convolutional neural network for stereo estimation with depth completion. We name this method fully-convolutional deformable similarity network with depth completion (FCDSN-DC). This method extends…
Dichotomous Image Segmentation (DIS) has recently emerged towards high-precision object segmentation from high-resolution natural images. When designing an effective DIS model, the main challenge is how to balance the semantic dispersion of…
We present a method to estimate dense depth by optimizing a sparse set of points such that their diffusion into a depth map minimizes a multi-view reprojection error from RGB supervision. We optimize point positions, depths, and weights…
Video Semantic Segmentation (VSS) involves assigning a semantic label to each pixel in a video sequence. Prior work in this field has demonstrated promising results by extending image semantic segmentation models to exploit temporal…
Neural implicit representations have revolutionized dense multi-view surface reconstruction, yet their performance significantly diminishes with sparse input views. A few pioneering works have sought to tackle the challenge of sparse-view…
Accurate stereo depth estimation plays a critical role in various 3D tasks in both indoor and outdoor environments. Recently, learning-based multi-view stereo methods have demonstrated competitive performance with a limited number of views.…
Recent advanced studies have spent considerable human efforts on optimizing network architectures for stereo matching but hardly achieved both high accuracy and fast inference speed. To ease the workload in network design, neural…
Recently, patch deformation-based methods have demonstrated significant strength in multi-view stereo by adaptively expanding the reception field of patches to help reconstruct textureless areas. However, such methods mainly concentrate on…
In this work, we present a new multi-view depth estimation method that utilizes both conventional reconstruction and learning-based priors over the recently proposed neural radiance fields (NeRF). Unlike existing neural network based…