Related papers: CountFormer: Multi-View Crowd Counting Transformer
Recent advancements in leveraging pre-trained 2D diffusion models achieve the generation of high-quality novel views from a single in-the-wild image. However, existing works face challenges in producing controllable novel views due to the…
We present Multi-View Attentive Contextualization (MvACon), a simple yet effective method for improving 2D-to-3D feature lifting in query-based multi-view 3D (MV3D) object detection. Despite remarkable progress witnessed in the field of…
Vision-based 3D semantic scene completion (SSC) describes autonomous driving scenes through 3D volume representations. However, the occlusion of invisible voxels by scene surfaces poses challenges to current SSC methods in hallucinating…
Self-supervised methods have showed promising results on depth estimation task. However, previous methods estimate the target depth map and camera ego-motion simultaneously, underusing multi-frame correlation information and ignoring the…
We propose Radar-Camera fusion transformer (RaCFormer) to boost the accuracy of 3D object detection by the following insight. The Radar-Camera fusion in outdoor 3D scene perception is capped by the image-to-BEV transformation--if the depth…
Vision-language models have been key to the development of open-vocabulary 2D semantic segmentation. Lifting these models from 2D images to 3D scenes, however, remains a challenging problem. Existing approaches typically back-project and…
The recent advances in query-based multi-camera 3D object detection are featured by initializing object queries in the 3D space, and then sampling features from perspective-view images to perform multi-round query refinement. In such a…
We propose a method to address audio-visual target speaker enhancement in multi-talker environments using event-driven cameras. State of the art audio-visual speech separation methods shows that crucial information is the movement of the…
The Bird's-Eye-View (BEV) representation is a critical factor that directly impacts the 3D object detection performance, but the traditional BEV grid representation induces quadratic computational cost as the spatial resolution grows. To…
While local-window self-attention performs notably in vision tasks, it suffers from limited receptive field and weak modeling capability issues. This is mainly because it performs self-attention within non-overlapped windows and shares…
We propose VIAFormer, a Voxel-Image Alignment Transformer model designed for Multi-view Conditioned Voxel Refinement--the task of repairing incomplete noisy voxels using calibrated multi-view images as guidance. Its effectiveness stems from…
We present WidthFormer, a novel transformer-based module to compute Bird's-Eye-View (BEV) representations from multi-view cameras for real-time autonomous-driving applications. WidthFormer is computationally efficient, robust and does not…
Aerial Image Segmentation is a top-down perspective semantic segmentation and has several challenging characteristics such as strong imbalance in the foreground-background distribution, complex background, intra-class heterogeneity,…
In this paper, we aim to tackle the challenging few-shot segmentation task from a new perspective. Typical methods follow the paradigm to firstly learn prototypical features from support images and then match query features in pixel-level…
Due to the lack of a definitive ground truth for the image fusion problem, the loss functions are structured based on evaluation metrics, such as the structural similarity index measure (SSIM). However, in doing so, a bias is introduced…
The core of Multi-view Stereo(MVS) is the matching process among reference and source pixels. Cost aggregation plays a significant role in this process, while previous methods focus on handling it via CNNs. This may inherit the natural…
Novel view synthesis is a long-standing problem. In this work, we consider a variant of the problem where we are given only a few context views sparsely covering a scene or an object. The goal is to predict novel viewpoints in the scene,…
The 3D visual grounding task aims to ground a natural language description to the targeted object in a 3D scene, which is usually represented in 3D point clouds. Previous works studied visual grounding under specific views. The…
In recent years, many video tasks have achieved breakthroughs by utilizing the vision transformer and establishing spatial-temporal decoupling for feature extraction. Although multi-view 3D reconstruction also faces multiple images as…
Multi-view action recognition aims to recognize human actions using multiple camera views and deals with occlusion caused by obstacles or crowds. In this task, cooperation among views, which generates a joint representation by combining…