output
19942026
Showing 2023 · cs.CVShow all

17 papers · 2 filters

cs.CV2023★ 18 cited

DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Driving

Erfei Cui, Wenhai Wang, Zhiqi Li +7

Large language models (LLMs) have opened up new possibilities for intelligent agents, endowing them with human-like thinking and cognitive abilities. In this work, we delve into th…

cs.CV2023★ 7 cited

Hulk: A Universal Knowledge Translator for Human-Centric Tasks

Yizhou Wang, Yixuan Wu, Weizhen He +8

Human-centric perception tasks, e.g., pedestrian detection, skeleton-based action recognition, and pose estimation, have wide industrial applications, such as metaverse and sports…

cs.CV2023★ 45 cited

How does spatial structure affect psychological restoration? A method based on Graph Neural Networks and Street View Imagery

Haoran Ma, Yan Zhang, Pengyuan Liu +2

The Attention Restoration Theory (ART) presents a theoretical framework with four essential indicators (being away, extent, fascinating, and compatibility) for comprehending urban…

cs.CV2023★ 47 cited

VR-NeRF: High-Fidelity Virtualized Walkable Spaces

Linning Xu, Vasu Agrawal, William Laney +10

We present an end-to-end system for the high-fidelity capture, model reconstruction, and real-time rendering of walkable spaces in virtual reality using neural radiance fields. To…

cs.CV2023★ 33 cited

Text-Guided Texturing by Synchronized Multi-View Diffusion

Yuxin Liu, Minshan Xie, Hanyuan Liu +1

This paper introduces a novel approach to synthesize texture to dress up a given 3D object, given a text prompt. Based on the pretrained text-to-image (T2I) diffusion model, existi…

cs.CV2023★ 1 cited

SeamlessNeRF: Stitching Part NeRFs with Gradient Propagation

Bingchen Gong, Yuehao Wang, Xiaoguang Han +1

Neural Radiance Fields (NeRFs) have emerged as promising digital mediums of 3D objects and scenes, sparking a surge in research to extend the editing capabilities in this domain. T…

cs.CV2023★ 74 cited

TransXNet: Learning Both Global and Local Dynamics with a Dual Dynamic Token Mixer for Visual Recognition

Meng Lou, Shu Zhang, Hong-Yu Zhou +3

Recent studies have integrated convolutions into transformers to introduce inductive bias and improve generalization performance. However, the static nature of conventional convolu…

cs.CV2023★ 19 cited

Open-Vocabulary Animal Keypoint Detection with Semantic-feature Matching

Hao Zhang, Lumin Xu, Shenqi Lai +5

Current image-based keypoint detection methods for animal (including human) bodies and faces are generally divided into full-supervised and few-shot class-agnostic approaches. The…

cs.CV2023★ 25 cited

SimCol3D -- 3D Reconstruction during Colonoscopy Challenge

Anita Rau, Sophia Bano, Yueming Jin +19

Colorectal cancer is one of the most common cancers in the world. While colonoscopy is an effective screening technique, navigating an endoscope through the colon to detect polyps…

cs.CV2023★ 12 cited

Toward Fairness Through Fair Multi-Exit Framework for Dermatological Disease Diagnosis

Ching-Hao Chiu, Hao-Wei Chung, Yu-Jen Chen +2

Fairness has become increasingly pivotal in medical image recognition. However, without mitigating bias, deploying unfair medical AI systems could harm the interests of underprivil…

cs.CV2023★ 114 cited

3DSAM-adapter: Holistic adaptation of SAM from 2D to 3D for promptable tumor segmentation

Shizhan Gong, Yuan Zhong, Wenao Ma +5

Despite that the segment anything model (SAM) achieved impressive results on general-purpose semantic segmentation with strong generalization ability on daily images, its demonstra…

cs.CV2023★ 1 cited

Taming Reversible Halftoning via Predictive Luminance

Cheuk-Kit Lau, Menghan Xia, Tien-Tsin Wong

Traditional halftoning usually drops colors when dithering images with binary dots, which makes it difficult to recover the original color information. We proposed a novel halftoni…

cs.CV2023★ 6 cited

Spatial-Frequency Discriminability for Revealing Adversarial Perturbations

Chao Wang, Shuren Qi, Zhiqiu Huang +4

The vulnerability of deep neural networks to adversarial perturbations has been widely perceived in the computer vision community. From a security perspective, it poses a critical…

cs.CV2023★ 142 cited

Generalist Vision Foundation Models for Medical Imaging: A Case Study of Segment Anything Model on Zero-Shot Medical Segmentation

Peilun Shi, Jianing Qiu, Sai Mu Dalike Abaxi +3

In this paper, we examine the recent Segment Anything Model (SAM) on medical images, and report both quantitative and qualitative zero-shot segmentation results on nine medical ima…

cs.CV2023★ 51 cited

Self-supervised Action Representation Learning from Partial Spatio-Temporal Skeleton Sequences

Yujie Zhou, Haodong Duan, Anyi Rao +2

Self-supervised learning has demonstrated remarkable capability in representation learning for skeleton-based action recognition. Existing methods mainly focus on applying global d…

cs.CV2023★ 2 cited

Make Your Brief Stroke Real and Stereoscopic: 3D-Aware Simplified Sketch to Portrait Generation

Yasheng Sun, Qianyi Wu, Hang Zhou +6

Creating the photo-realistic version of people sketched portraits is useful to various entertainment purposes. Existing studies only generate portraits in the 2D plane with fixed v…

cs.CV2023★ 25 cited

RecolorNeRF: Layer Decomposed Radiance Fields for Efficient Color Editing of 3D Scenes

Bingchen Gong, Yuehao Wang, Xiaoguang Han +1

Radiance fields have gradually become a main representation of media. Although its appearance editing has been studied, how to achieve view-consistent recoloring in an efficient ma…